Publications

Journal articles, conference papers and preprints in computer vision, image processing and machine learning, with code, data and BibTeX.

Google Scholar DBLP ORCID

Search publications

2026

PGMS: Pyramidal Gaussian Mixture Splatting for 3DGS Compression

X. Zhang, Z. Wu, M. Feng, S. Anwar, and A. Mian

Conference on Neural Information Processing Systems (NeurIPS), 2026

Official PDFarXivProject page

@inproceedings{Zhang2026PGMS,
  title={PGMS: Pyramidal Gaussian Mixture Splatting for 3DGS Compression},
  author={Xiaoge Zhang and Zijie Wu and Mingtao Feng and Saeed Anwar and Ajmal Mian},
  booktitle={Conference on Neural Information Processing Systems},
  year={2026}
}

Beyond Red and Green: Flashing Traffic Light Recognition in Autonomous Driving

S. Ali, Md T. Islam, S. Anwar, R. Scherer, S. Bakshi, H. OH, and K. Muhammad

Asian Conference on Computer Vision (ACCV), 2026

Official PDFarXivProject page

@InProceedings{Ali2026FlashNet,
    title={Beyond Red and Green: Flashing Traffic Light Recognition in Autonomous Driving},
    author	= {Shehzad Ali and Md Tanvir Islam and Saeed Anwar and Rafał Scherer and Sambit Bakshi and HAYOUNG OH and Khan Muhammad},
    booktitle = {IEEE/CVF Asian Conference on Computer Vision},
    year={2026}
}

TDiR: Transformer based Diffusion for Image Restoration Tasks

A. Anwar, I. Radwan, A. A. Nasir, M. Masood, and S. Anwar

Asian Conference on Computer Vision (ACCV), 2026

Official PDFarXiv

@inproceedings{Anwar2026TDiR,
  title={TDiR: Transformer based Diffusion for Image Restoration Tasks},
  author={Anwar, Abbas and Radwan, Ibrahim and Nasir, Ali Arshad and Masood, Mudassir and Anwar, Saeed},
  booktitle={Asian Conference on Computer Vision},
  year={2026}
}

PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation

Y. He, H. Yu, M. Feng, T. Chen, Z. Li, A. Ulhaq, S. Anwar, and A. Mian

IEEE Transactions on Automation Science and Engineering (TASE), 2026

Official PDF arXivProject page

@article{Yong2026PointDiffuse,
  author={He, Yong and Yu, Hongshan and Feng, Mingtao and Li, Zechuan and Chen, Tongjia and Ulhaq, Anwaar and Anwar, Saeed and Mian, Ajmal},
  journal={IEEE Transactions on Automation Science and Engineering},
  title={PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation},
  year={2026},
  doi={10.1109/TASE.2026.3722737}
}

Do Vision-Language Models Truly Count? Revealing the Semantic-Localization Gap in Dense Crowd Understanding

B. Das, U. K. Nareti, S. Prajapati, C. Adak, S. Chattopadhyay, M. Saqib and S. Anwar

International Conference on Neural Information Processing (ICONIP), 2026

Official PDFarXivCode

@inproceedings{Bibek2026count,
  author    = {Das, Bibek and Prajapati, Sourabh and Adak, Chandranath and Chattopadhyay, Soumi and Saqib, Muhammad and Anwar, Saeed},
  title     = {Do Vision-Language Models Truly Count? Revealing the Semantic-Localization Gap in Dense Crowd Understanding},
  booktitle = {International Conference on Neural Information Processing (ICONIP)},
  year      = {2026}
}

From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Image-Grounded Review Assistance

U. K. Nareti, A. Bansal, K. Priya, C. Adak, S. Chattopadhyay, M. Saqib and S. Anwar

International Conference on Neural Information Processing (ICONIP), 2026

Official PDFarXivCode

@inproceedings{Nareti2026Visual,
  author    = {Nareti, Utsav Kumar and Bansal, Ayush and Priya, Kumari and Adak, Chandranath and Chattopadhyay, Soumi and Saqib, Muhammad and Anwar, Saeed},
  title     = {From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Image-Grounded Review Assistance},
  booktitle = {International Conference on Neural Information Processing (ICONIP)},
  year      = {2026}
}

UBLLIE: Unified Backlight and Low-Light Image Enhancement

Y. Yasin, M. Usman, I. Radwan, and S. Anwar

arXiv preprint, 2026

arXiv

@misc{Yasmin2026UBLLIE,
      title={UBLLIE: Unified Backlight and Low-Light Image Enhancement},
      author={Yasmin Yasin and Muhammad Usman and Ibrahim Radwan and Saeed Anwar},
      year={2026},
      eprint={2608.04429},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2608.04429},
}

SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection

B. Jan, S. Anwar, A. H. El-Maleh, A. J. Siddiqui, and A. Bais

IEEE Transactions on Image Processing (TIP), 2026

Official PDF arXiv Code

@article{Baber2026SPEGNet,
   title={SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection},
   author={Baber Jan and Saeed Anwar and Aiman H. El-Maleh and Abdul Jabbar Siddiqui and Abdul Bais},
   journal ={Transactions on Image Processing},
   year={2026},
   organization={IEEE}
}

The Evolution of Deep Learning: From Perceptrons to Generative Foundation Models

H. Naveed, S. Anwar, S. Qiu, D. Liu, N. Barnes, I. Radwan, and A. Mian

Preprints.org preprint, 2026

Preprint

@article{Naveed2026EDL,
	year = 2026,
	month = {July},
	publisher = {Preprints},
	author = {Humza Naveed and Saeed Anwar and Shi Qiu and Daochang Liu and Nick Barnes and Ibrahim Radwan and Ajmal Mian},
	title = {The Evolution of Deep Learning: From Perceptrons to Generative Foundation Models},
	journal = {Preprints}
}

GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification

M.F.K. Khan, S Anwar, and G.M. Hassan

arXiv preprint, 2026

arXiv Code

@article{Khan2026GenSyn10,
  title={GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification},
  author={Khan, Md Faraz Kabir and Anwar, Saeed and Hassan, Ghulam Mubashar},
  journal={arXiv preprint arXiv:2607.16283},
  year={2026}
}

Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression

H. Wei, Y. Zhou, C. Ge, S. Anwar and A. Mian

arXiv preprint, 2026

arXiv Code

@misc{Wei2026SPRDiff,
      title={Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression},
      author={Hao Wei and Yanhui Zhou and Chenyang Ge and Saeed Anwar and Ajmal Mian},
      year={2026},
      eprint={2606.01608},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2606.01608},
}

NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds

R. Cui, S. Qiu, J. Liu, S. Anwar, and N. Barnes

IEEE Transactions on Visualization and Computer Graphics (TVCG), 2026

Official PDF arXiv Code

@article{Cui2024numgrad,
      title={NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds},
      author={Ruikai Cui and Binzhu Xie and Shi Qiu and Jiawei Liu and Saeed Anwar and Nick Barnes},
      journal={IEEE Transactions on Visualization \& Computer Graphics},
	  year={2026}
}

Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation

N. Nadeem, S. Anwar, M. H. Asad, and A. Bais

European Conference on Computer Vision (ECCV), 2026

arXiv Project page

@inproceedings{Nadeem2026HVLFormer,
  title={Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation},
  author={Nadeem, Numair and Anwar, Saeed and Asad, Muhammad Hamza and Bais, Abdul},
  booktitle={European Conference on Computer Vision},
  year={2026}
}

Auto-Feedback Semantic Interface Learning for Text-Based Person Retrieval

J Li, M Jiang, M Wu, J Kong, S Anwar, and A Mian

Pattern Recognition (PR), 2026

Official PDF

@article{Li2026ASIL,
	title   = {Auto-Feedback Semantic Interface Learning for Text-Based Person Retrieval},
	journal = {Pattern Recognition},
	volume  = {180},
	pages   = {114324},
	year    = {2026},
	issn    = {0031-3203},
	doi     = {https://doi.org/10.1016/j.patcog.2026.114324},
	url     = {https://www.sciencedirect.com/science/article/pii/S0031320326012896},
	author  = {Jiayi Li and Min Jiang and Meng Wu and Jun Kong and Saeed Anwar and Ajmal Mian}
}

PointCaM: Cut-and-Mix for Open-Set Point Cloud Analysis

J. Hong, S. Qiu, W. Li, S. Anwar, M. Harandi, N. Barnes, and L. Petersson

Computer Vision and Image Understanding (CVIU), 2026

Official PDF arXiv Code

@article{hong2026pointcam,
  title={Pointcam: Cut-and-mix for open-set point cloud learning},
  author={Hong, Jie and Qiu, Shi and Li, Weihao and Anwar, Saeed and Harandi, Mehrtash and Barnes, Nick and Petersson, Lars},
  journal={Computer Vision and Image Understanding},
  pages={104814},
  year={2026},
  publisher={Elsevier}
}

FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds

X. Zhang, Z. Wu, M. Feng, Z. Geng, M. Nasim, S. Anwar, and A. Mian

IEEE International Conference on Multimedia and Expo (ICME), 2026

arXiv Project page

@inproceedings{Zhang2026FLaTEC,
      title={FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds},
      author={Xiaoge Zhang and Zijie Wu and Mingtao Feng and Zichen Geng and Mehwish Nasim and Saeed Anwar and Ajmal Mian},
      booktitle={IEEE International Conference on Multimedia and Expo (ICME)},
      year={2026},
      organization={IEEE}
}

Representation-Centric Survey of Skeletal Action Recognition and the ANUBIS Benchmark

Y. Liu, J. Yang, M. Perera, P. Ji, D. Kim, M. Xu, T. Wang, S. Anwar, T. Gedeon, L. Wang, and Z. Qin

Pattern Recognition (PR), 2026

Official PDF arXiv Project page

@article{Qin2026ANUBIS,
  title={ANUBIS: Skeleton Action Recognition Dataset, Review, and Benchmark},
  author={Yang Liu and Jiyao Yang and Madhawa Perera and Pan Ji and Dongwoo Kim and Min Xu and Tianyang Wang and Saeed Anwar and Tom Gedeon and Lei Wang and Zhenyue Qin},
  journal={Pattern Recognition},
  year={2026}
}

A review on vision-centric coarse to fine-grained animal action recognition

A. Zia, R. Sharma, A. Khamis, U. Ali, X. Li, M. Husnain, N. Shafi, S. Anwar, I. Raza, M. H. Jamal, S. Schmoelzl, E. Stone, L. Petersson, and V. Rolland

Artificial Intelligence Review (AIR), 2026

arXiv

@article{Ali2026FGAnimal,
  title={A review on vision-centric coarse to fine-grained animal action recognition},
  author={Zia, Ali and Sharma, Renuka and Khamis, Abdelwahed and Ali, Usman and Li, Xuesong and Husnain, Muhammad and Shafi, Numan and Anwar, Saeed and Raza, Imran and Jamal, Muhammad Hasan and others},
  journal={Artificial Intelligence Review},
  year={2026},
  publisher={Springer}
}

Mind the Rarities: Can Rare Skin Diseases Be Reliably Diagnosed via Diagnostic Reasoning?

Y. Liu, J. Yang, H. Zhao, X. Li, Y. Ji, X. Li, R. Jiang, T. Wang, S. Anwar, D. Kim, Y. Yao, Z. Qin, and M. Xu

arXiv preprint, 2026

arXiv Project page

@article{Liu2026Mind,
  title={Mind the Rarities: Can Rare Skin Diseases Be Reliably Diagnosed via Diagnostic Reasoning?},
  author={Liu, Yang and Yang, Jiyao and Zhao, Hongjin and Li, Xiaoyong and Ji, Yanzhe and Li, Xingjian and Jiang, Runmin and Wang, Tianyang and Anwar, Saeed and Kim, Dongwoo and others},
  journal={arXiv preprint arXiv:2603.18418},
  year={2026}
}

Faithful Extreme Image Rescaling with Learnable Reversible Transformation and Semantic Priors

H. Wei, Y. Zhou, C. Ge, S. Anwar, and A. Mian

arXiv preprint, 2026

arXiv Code

@article{Wei2026Faithful,
  title={Faithful Extreme Image Rescaling with Learnable Reversible Transformation and Semantic Priors},
  author={Wei, Hao and Zhou, Yanhui and Ge, Chenyang and Anwar, Saeed and Mian, Ajmal},
  journal={arXiv preprint arXiv:2605.00605},
  year={2026}
}

DiffCom: Decoupled Sparse Priors Guided Diffusion Compression for Point Clouds

X. Zhang, Z. Wu, M. Feng, M. Nasim, S. Anwar, and A. Mian

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2026

arXiv Official PDF Project page

@article{Xiaoge2026DiffCom,
  author={Zhang, Xiaoge and Wu, Zijie and Feng, Mingtao and Nasim, Mehwish and Anwar, Saeed and Mian, Ajmal},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  title={DiffCom: Decoupled Sparse Priors Guided Diffusion Compression for Point Clouds},
  year={2026},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/TCSVT.2026.3663664}
}

RDD4D: 4D Attention-Guided Road Damage Detection And Classification

A. Alkalbani, M. Saqib, A. S. Alrawahi, A. Anwar, C. Adak, and S. Anwar

IEEE Access, 2026

arXivOfficial PDFCode

@article{Asma2026RDD4D,
      title={RDD4D: 4D Attention-Guided Road Damage Detection And Classification},
      author={Asma Alkalbani and Muhammad Saqib and Ahmed Salim Alrawahi and Abbas Anwar and Chandarnath Adak and Saeed Anwar},
      year={2025},
      journal={IEEE Access}
}

SwinIFS: Landmark Guided Swin Transformer For Identity Preserving Face Super Resolution

H. Kausar, S. Anwar, O. J. Hammad, and A. Bais

arXiv preprint, 2026

arXiv Code

@misc{Kausar2026SwinIFS,
      title={SwinIFS: Landmark Guided Swin Transformer For Identity Preserving Face Super Resolution},
      author={Habiba Kausar and Saeed Anwar and Omar Jamal Hammad and Abdul Bais},
      year={2026},
      eprint={2601.01406},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2601.01406},
}

2025

PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models

A. B. M. A. Rahman, S. Anwar, M. Usman, I. Ahmad, and A. Mian

arXiv preprint, 2025

arXiv Code

@misc{Rahman2025PENDULUM,
      title={PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models},
      author={A. B. M. Ashikur Rahman and Saeed Anwar and Muhammad Usman and Irfan Ahmad and Ajmal Mian},
      year={2025},
      eprint={2512.19350},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2512.19350},
}

C3Net: Context-Contrast Network for Camouflaged Object Detection

B. Jan, A. H. El-Maleh, A. J. Siddiqui, A. Bais, and S. Anwar

arXiv preprint, 2025

arXiv Code

@misc{Baber2025C3Net,
     title={C3Net: Context-Contrast Network for Camouflaged Object Detection},
      author={Baber Jan and Aiman H. El-Maleh and Abdul Jabbar Siddiqui and Abdul Bais and Saeed Anwar},
      year={2025},
      eprint={2511.12627},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2511.12627},
}

MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection

L. Alghamdi, M. Usman, H. Anwar, A. Bais, and S. Anwar

arXiv preprint, 2025

arXiv Code

@misc{Alghamdi2025MSRNet,
      title={MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection},
      author={Leena Alghamdi and Muhammad Usman and Hafeez Anwar and Abdul Bais and Saeed Anwar},
      year={2025},
      eprint={2511.12810},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2511.12810},
}

IARD: Intruder Activity Recognition Dataset for Threat Detection

S. Ali, M. T. Islam, I. H. Lee, S. Anwar, J. D. Ser, and K. Muhammad

ACM International Conference on Information and Knowledge Management (CIKM), 2025

Official PDF Code

@inproceedings{Ali2025IARD,
	author = {Ali, Shehzad and Islam, Md Tanvir and Lee, Ik Hyun and Anwar, Saeed and Ser, Javier Del and Muhammad, Khan},
	title = {IARD: Intruder Activity Recognition Dataset for Threat Detection},
	isbn = {9798400720406},
	publisher = {Association for Computing Machinery},
	address = {New York, NY, USA},
	url = {https://doi.org/10.1145/3746252.3761619},
	doi = {10.1145/3746252.3761619},
	booktitle = {Proceedings of the 34th ACM International Conference on Information and Knowledge Management},
	pages = {6317–6322},
	numpages = {6},
	year = {2025}
}

A Lightweight Model for Perceptual Image Compression via Implicit Priors

H. Wei, Y. Zhou, Y. Jia, C. Ge, S. Anwar, and A. Mian

Neural Networks (NN), 2025

Official PDF arXiv Code

@article{Wei2025Lightweight,
      title={A Lightweight Model for Perceptual Image Compression via Implicit Priors},
      author={Hao Wei and Yanhui Zhou and Yiwen Jia and Chenyang Ge and Saeed Anwar and Ajmal Mian},
 	  journal={Nerual Networks},
  	  year={2025},
}

DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation

A. B. M. A. Rahman, S. Anwar, M. Usman, I. Ahmad, and A. Mian

Information, 2025

arXiv Official PDF Code

@article{rahman2025defan,
AUTHOR = {Rahman, A. B. M. Ashikur and Anwar, Saeed and Usman, Muhammad and Ahmad, Irfan and Mian, Ajmal},
TITLE = {DefAn: Definitive Answer Dataset for LLM Hallucination Evaluation},
JOURNAL = {Information},
VOLUME = {16},
YEAR = {2025},
NUMBER = {11},
ARTICLE-NUMBER = {937},
ISSN = {2078-2489},
DOI = {10.3390/info16110937}
}

CRTSC: Channel-Wise Recalibration and Texture-Structural Consistency Constraint for Anomaly Detection in Medical Chest Images

M. Xiong, C. Wang, H. Cai, A. Alotaibi, S. Anwar, A. K. J. Saudagar, J. D. Ser, and K. Muhammad

Sensors, 2025

Official PDF

@article{xiong2025crtsc,
  title={CRTSC: Channel-Wise Recalibration and Texture-Structural Consistency Constraint for Anomaly Detection in Medical Chest Images},
  author={Xiong, Mingfu and Wang, Chong and Cai, Hao and Alotaibi, Aziz and Anwar, Saeed and Saudagar, Abdul Khader Jilani and Del Ser, Javier and Muhammad, Khan},
  journal={Sensors},
  volume={25},
  number={21},
  pages={6722},
  year={2025},
  publisher={MDPI}
}

Bird's-Eye View to Street-View: A Survey

K. Bajbaa, M. Usman, S. Anwar, I. Radwan, and A. Bais

Applied Intelligence (AI), 2025

Official PDF arXiv

@article{bajbaa2025birdseye,
      title={Bird's-Eye View to Street-View: A Survey},
      author={Khawlah Bajbaa and Muhammad Usman and Saeed Anwar and Ibrahim Radwan and Abdul Bais},
 	  journal={Applied Intelligence},
  	  year={2025},
  	  publisher={Springer}
}

Benchmarking Crowd Counting in Bird-Eye Images From Drones

M. Saqib, R. Sharma, S. Anwar, and N. Sharma

International Conference on Data Science and Communication (ICTDsC), 2025

Official PDF

@InProceedings{Saqib2025Benchmarking,
author="Saqib, Muhammad
and Sharma, Rabi
and Anwar, Saeed
and Sharma, Nabin",
title="Benchmarking Crowd Counting in Bird-Eye Images From Drones",
booktitle="Data Science and Communication Engineering",
year="2025",
publisher="Springer Nature Singapore",
address="Singapore",
pages="683--697",
isbn="978-981-96-4543-5"
}

Multi scale self supervised learning for deep knowledge transfer in diabetic retinopathy grading

W. Almattar, S. Anwar, S. Al-Azani, and F. A. Khan

Scientific Reports (SR), 2025

Official PDF

@article{almattar2025multi,
  title={Multi scale self supervised learning for deep knowledge transfer in diabetic retinopathy grading},
  author={Almattar, Wadha and Anwar, Saeed and Al-Azani, Sadam and Khan, Fakhri Alam},
  journal={Scientific Reports},
  volume={15},
  number={1},
  pages={33742},
  year={2025},
  publisher={Nature Publishing Group UK London}
}

Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenes

M. Ibrahim, N. Akhtar, H. Wang, S. Anwar, and A. Mian

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025Oral

arXiv Code

@inproceedings{Ibrahim2025MuStD,
  title={Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenes},
  author={Ibrahim, Muhammad and Akhtar, Naveed and Wang, Haitian and Anwar, Saeed and Mian, Ajmal},
  booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2025},
  organization={IEEE}
}

Towards Hazardous Activity Recognition for A Novel Real-World Dataset

S. Ali, M. T. Islam, I. H. Lee, M. Xiong, M.-S. Dao, S. Anwar, S. Bakshi, and K. Muhammad

ACM International Conference on Multimedia (ACM MM), 2025

Official PDF Code

@InProceedings{Ali2025RHAD,
title={Towards Hazardous Activity Recognition for A Novel Real-World Dataset},
author	={Shehzad Ali and Md Tanvir Islam and Ik Hyun Lee and  Mingfu Xiong and Minh-Son Dao and Saeed Anwar and Sambit Bakshi and Khan Muhammad},
isbn = {9798400720352},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3746027.3754795},
doi = {10.1145/3746027.3754795},
booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
pages = {5326–5335},
numpages = {10},
keywords = {child activities, hazardnet, indoor hazard, safety, surveillance},
location = {Dublin, Ireland},
series = {MM '25},
year={2025}
}

A Comprehensive Overview of Large Language Models

H. Naveed, A. U. Khan, S. Qiu, M. Saqib, S. Anwar, M. Usman, N. Barnes, and A. Mian

ACM Transactions on Intelligent Systems and Technology (TIST), 2025

Official PDF arXiv Code

@article{Humza2025LLMs,
  title = {A Comprehensive Overview of Large Language Models},
  author={Humza Naveed and Asad Ullah Khan and Shi Qiu and Muhammad Saqib and Saeed Anwar and Muhammad Usman and Nick Barnes and Ajmal Mian},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year={2025}
}

MaskAdapt: Unsupervised Geometry-Aware Domain Adaptation Using Multimodal Contextual Learning and RGB-Depth Masking

N. Nadeem, M. H. Asad, S. Anwar, and A. Bais

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025OralWorkshop

Official PDFarXiv

@InProceedings{Numair2025MaskAdapt,
    author    = {Nadeem, Numair and Asad, Muhammad Hamza and Anwar, Saeed and Bais, Abdul},
    title     = {MaskAdapt: Unsupervised Geometry-Aware Domain Adaptation Using Multimodal Contextual Learning and RGB-Depth Masking},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2025},
}

SEDNet: Synergistic Learning Network with Embedded Encoder and Dense Atrous Convolution for Vehicle Re-identification

M. Xiong, T. Gui, Z. Sun, S. Anwar, A. Alotaibi, and K Muhammad

Alexandria Engineering Journal (AEJ), 2025

Official PDF

@article{Xiong2025SEDNet,
title = {SEDNet: Synergistic Learning Network with Embedded Encoder and Dense Atrous Convolution for Vehicle Re-identification},
author = {Mingfu Xiong and Tanghao Gui and Zhihong Sun and Saeed Anwar and Aziz Alotaibi and Khan Muhammad},
journal = {Alexandria Engineering Journal},
volume = {128},
pages = {297-305},
issn = {1110-0168},
year = {2025}
}

Vehicle and License Plate Recognition with Novel Dataset for Toll Collection

M. Usama, H. Anwar, A. Anwar, and S. Anwar

Pattern Analysis and Applications (PAA), 2025

arXiv Code

@article{Usama2025VTLPR,
     title={Vehicle and License Plate Recognition with Novel Dataset for Toll Collection},
     author={Muhammad Usama and Hafeez Anwar and Abbas Anwar and Saeed Anwar},
     journal={Pattern Analysis and Applications},
     year={2024},
     publisher={Springer}
}

FSBI: Deepfakes Detection with Frequency Enhanced Self-Blended Images

A. A. Hasanaath, H. Luqman, R. Katib, and S. Anwar

Image and Vision Computing (IVC), 2025

Official PDF arXiv Code

@article{hasanaath2025fsbi,
  title={FSBI: Deepfake detection with frequency enhanced self-blended images},
  author={Hasanaath, Ahmed Abul and Luqman, Hamzah and Katib, Raed and Anwar, Saeed},
  journal={Image and Vision Computing},
  pages={105418},
  year={2025},
  publisher={Elsevier}
}

Image Colorization: A Survey and Dataset

S. Anwar, M. Tahir, C. Li, A. Mian, F. S. Khan, and A. W. Muzaffar

Information Fusion (IF), 2025

Official PDF arXiv Code

@article{Anwar2025ColorSurvey,
  title={Image Colorization: A Survey and Dataset},
  author={Saeed Anwar and Muhammad Tahir and Chongyi Li and Ajmal Mian and Fahad Shahbaz Khan and Abdul Wahab Muzaffar},
  journal={Information Fusion},
  year={2025},
  volume = {114},
  pages = {102720},
  year = {2025},
  issn = {1566-2535},
  publisher={Elsevier}
}

Deep Learning Based 3D Segmentation: A Survey

Y. He, H. Yu, X. Liu, Z. Yang, W. Sun, S. Anwar, and A. Mian

Information Fusion (IF), 2025

Official PDF arXiv

@article{he2025DL3D,
  title = {Deep learning based 3D segmentation in computer vision: A survey},
  author = {Yong He and Hongshan Yu and Xiaoyan Liu and Zhengeng Yang and Wei Sun and Saeed Anwar and Ajmal Mian},
  journal = {Information Fusion},
  volume = {115},
  pages = {102722},
  year = {2025},
  issn = {1566-2535},
  publisher={Elsevier}
}

2024

AllWeather-Net: Unified Image Enhancement for Autonomous Driving Under Adverse Weather and Low-Light Conditions

C. Qian, M. Rezaei, S. Anwar, W. Li, T. Hussain, M. Azarmi, and W. Wang

International Conference on Pattern Recognition (ICPR), 2024OralBest Paper Award

Official PDF arXiv Code

@InProceedings{Qian2024AllWeatherNet,
  title={AllWeather-Net: Unified Image Enhancement for Autonomous Driving Under Adverse Weather and Low-Light Conditions},
  author={Chenghao Qian and Mahdi Rezaei and Saeed Anwar and Wenjing Li and Tanveer Hussain and Mohsen Azarmi and Wei Wang},
  booktitle={International Conference on Pattern Recognition (ICPR)},
  year={2024},
  organization={IEEE}
}

Sketch–to–3D: Transforming Hand-Sketched Floorplans into 3D Layouts

M. Usman, A. Almulhim, M. Alaseri, M. Alzahran, H. Luqman, and S. Anwar

Digital Image Computing: Techniques and Applications (DICTA), 2024Oral

Official PDF Project page

@InProceedings{Usman2024Sketchto3D,
  author={Usman, Muhammad and Almulhim, Abdullah and Alaseri, Mohammad and Alzahran, Mona and Luqman, Hamzah and Anwar, Saeed},
  booktitle={International Conference on Digital Image Computing: Techniques and Applications (DICTA)},
  title={Sketch–to–3D: Transforming Hand-Sketched Floorplans into 3D Layouts},
  pages={359-366},
  year={2024}
}

3D Object Classification with Selective Multi-View Fusion and Shape Rendering

M. Alzahrani, M. Usman, R. Alharbi, S. Anwar, A. Mian, and T. Helmy

Digital Image Computing: Techniques and Applications (DICTA), 2024Oral

Official PDF Code

@InProceedings{Alzahrani20243DObject,
 author={Alzahrani, Mona and Usman, Muhammad and Alharbi, Randah and Anwar, Saeed and Mian, Ajmal and Helmy, Tarek},
  booktitle={International Conference on Digital Image Computing: Techniques and Applications (DICTA)},
  title={3D Object Classification with Selective Multi-View Fusion and Shape Rendering},
  pages={351-358},
  year={2024}
}

Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models

A. Munir, A. J. Siddiqui, S. Anwar, A. El-Maleh, A. H. Khan, and A. Rehman

Drones, 2024

Official PDF Code

@Article{Munir2024drones,
  AUTHOR = {Munir, Adnan and Siddiqui, Abdul Jabbar and Anwar, Saeed and El-Maleh, Aiman and Khan, Ayaz H. and Rehman, Aqsa},
  TITLE = {Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models},
  JOURNAL = {Drones},
  VOLUME = {8},
  YEAR = {2024},
  NUMBER = {11},
  ARTICLE-NUMBER = {638}
}

LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond

M. T. Islam, I. Alam, S. S. Woo, S. Anwar, I. H. Lee, and K. Muhammad

Asian Conference on Computer Vision (ACCV), 2024

Official PDF arXiv Code

@inproceedings{Islam2024loli,
      title={LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond},
      author={Md Tanvir Islam and Inzamamul Alam and Simon S. Woo and Saeed Anwar and IK Hyun Lee and Khan Muhammad},
      booktitle={Proceedings of the Asian Conference on Computer Vision (ACCV)},
      year={2024}
}

Cefdet: Cognitive Effectiveness Network Based on Fuzzy Inference for Action Detection

Z. Luo, W. Fu, S. Liu, S. Anwar, M. Saqib, S. Bakshi, and K. Muhammad

ACM International Conference on Multimedia (ACM MM), 2024

Official PDF arXiv Code

@inproceedings{Zhe2024Cefdet,
  title={Cefdet: Cognitive Effectiveness Network Based on Fuzzy Inference for Action Detection},
  author={Zhe Luo and Weina Fu and Shuai Liu and Saeed Anwar and Muhammad Saqib and Sambit Bakshi and Khan Muhammad},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  year={2024},
  doi = {10.1145/3664647.3681226}
}

HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing

M. T. Islam, N. Rahim, S. Anwar, M. Saqib, S. Bakshi, and K. Muhammad

ACM International Conference on Multimedia (ACM MM), 2024

Official PDF arXiv Code

@inproceedings{Islam2024HazeSpace2M,
  title={HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing},
  author={Islam, Md Tanvir and Rahim, Nasir and Anwar, Saeed and Saqib Muhammad and Bakshi, Sambit and Muhammad, Khan},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  year={2024},
  doi = {10.1145/3664647.3681382}
}

Dual Deep Learning Network for Abnormal Action Detection

F. U. M. Ullah, Z. A. Khan, S. W. Baik, E. Talavera, S. Anwar, and K. Muhammad

IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2024

Official PDF Code

@InProceedings{Ullah2024Detection,
  author={Ullah, Fath U Min and Khan, Zulfiqar Ahmad and Baik, Sung Wook and Talavera, Estefania and Anwar, Saeed and Muhammad, Khan},
  booktitle={IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)},
  title={Dual Deep Learning Network for Abnormal Action Detection},
  year={2024},
  pages={1-8},
}

Attention Down-Sampling Transformer, Relative Ranking and Self-Consistency for Blind Image Quality Assessment

M. Alsaafin, M. Alsheikh, S. Anwar, and M. Usman

IEEE International Conference on Image Processing (ICIP), 2024

Official PDF arXiv Code

@InProceedings{Alsaafin2024NRIQA,
  title={Attention Down-Sampling Transformer, Relative Ranking and Self-Consistency for Blind Image Quality Assessment},
  author={Mohammed Alsaafin and Musab Alsheikh and Saeed Anwar and Muhammad Usman},
  booktitle={International conference on image processing (ICIP)},
  year={2024},
  organization={IEEE}
}

Deep Models for Multi-View 3D Object Recognition: A Review

M. Alzahrani, M. Usman, S. Kammoun, S. Anwar, and T. Helmy

Artificial Intelligence Review (AIR), 2024

Official PDF arXiv

@article{alzahrani20243DSurvey,
      title={Deep Models for Multi-View 3D Object Recognition: A Review},
      author={Mona Alzahrani and Muhammad Usman and Salma Kammoun and Saeed Anwar and Tarek Helmy},
      journal={Artificial Intelligence Review},
      volume={},
      pages={},
      year={2024},
      publisher={Springer}
}

Selective Multi-View Deep Model for 3D Object Classification

M. Alzahrani, M. Usman, S. Anwar, and T. Helmy

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024Workshop

Official PDF Supplementary Code

@InProceedings{Alzahrani2024Selective,
    author    = {Alzahrani, Mona and Usman, Muhammad and Anwar, Saeed and Helmy, Tarek},
    title     = {Selective Multi-View Deep Model for 3D Object Classification},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2024},
    pages     = {728-736}
}

Improved Crop and Weed Detection with Diverse Data Ensemble Learning

M. H. Asad, S. Anwar, and A. Bais

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024OralWorkshop

Official PDF arXiv

@InProceedings{asad2024improved,
    author    = {Asad, Muhammad Hamza and Anwar, Saeed and Bais, Abdul},
    title     = {Improved Crop and Weed Detection with Diverse Data Ensemble Learning},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2024},
    pages     = {5336-5345}
}

Visual Attention Methods in Deep Learning: An In-Depth Survey

M. Hassanin, S. Anwar, I. Radwan, F. S. Khan, and A. Mian

Information Fusion (IF), 2024

Official PDF arXiv

@article{Hassanin2024attention,
  title={Visual attention methods in deep learning: An in-depth survey},
  author={Hassanin, Mohammed and Anwar, Saeed and Radwan, Ibrahim and Khan, Fahad Shahbaz and Mian, Ajmal},
  journal={Information Fusion},
  pages={102417},
  year={2024},
  publisher={Elsevier}
}

Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions

Y. Zhang, Z. Qin, S. Anwar, D. Kim, Y. Liu, P. Ji, and T. Gedeon

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024

Official PDF arXiv Code

@article{Qin2024PSGNN,
  author={Zhang, Yiqun and Qin, Zhenyue and Anwar, Saeed and Kim, Dongwoo and Liu, Yang and Ji, Pan and Gedeon, Tom},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  title={Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions},
  year={2024},
  volume={},
  number={},
  pages={1-8},
}

Investigation of UAV Detection in Images With Complex Backgrounds and Rainy Artifacts

A. Munir, A. J. Siddiqui, and S. Anwar

IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACV), 2024Workshop

Official PDF arXiv Code

@inproceedings{munir2024investigation,
  title={Investigation of UAV Detection in Images With Complex Backgrounds and Rainy Artifacts},
  author={Munir, Adnan and Siddiqui, Abdul Jabbar and Anwar, Saeed},
  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  pages={221--230},
  year={2024}
}

Survey: Image Mixing and Deleting for Data Augmentation

H. Naveed, S. Anwar, M. Hayat, K. Javed, and A. Mian

Engineering Applications of Artificial Intelligence (EAAI), 2024

Official PDF arXiv Code

@article{Humza2023Aug,
  title = {Survey: Image Mixing and Deleting for Data Augmentation},
  author = {Naveed, Humza and Anwar, Saeed and Hayat, Munawar and Javed, Kashif and Mian, Ajmal},
  journal = {Engineering Applications of Artificial Intelligence},
  year={2024}
}

2023

A Systematic Evaluation: Fine-Grained CNN vs. Traditional CNN Classifiers

S. Anwar, N. Barnes, and L. Petersson

Electronics, 2023

arXiv Official PDF Code

@article{Anwar2023Systematic,
 title={A Systematic Evaluation: Fine-Grained CNN vs. Traditional CNN Classifiers},
 author={Saeed Anwar and Nick Barnes and Lars Petersson},
 journal = {Electronics},
 volume = {12},
 year = {2023},
 number = {23},
 article-number = {4877},
}

P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds

R. Cui, S. Qiu, S. Anwar, J. Liu, C. Xing, J. Zhang, and N. Barnes

IEEE International Conference on Computer Vision (ICCV), 2023

arXiv Official PDF Code

@InProceedings{Ruikai2023P2C,
author = {Ruikai Cui and Shi Qiu and Saeed Anwar and Jiawei Liu and Chaoyue Xing and Jing Zhang and Nick Barnes},
title = {P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
year = {2023}
}

UnLoc: A Universal Localization Method for LiDAR, RADAR and/or Camera Input

M. Ibrahim, N. Akhtar, S. Anwar, and A. Mian

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

arXiv Official PDF Code

@inproceedings{Ibrahim2023UnLoc,
  title={Unloc: a universal localization method for autonomous vehicles using lidar, radar and/or camera input},
  author={Ibrahim, Muhammad and Akhtar, Naveed and Anwar, Saeed and Mian, Ajmal},
  booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages={5187--5194},
  year={2023},
  organization={IEEE}
}

Sequential Vision to Language as Story: A Storytelling Dataset and Benchmarking

Z. M. Malakan, S. Anwar, G. M. Hassan, and A. Mian

IEEE Access, 2023

Official PDF Project page

@article{Zainy2023SSID,
  author={Malakan, Zainy M. and Anwar, Saeed and Hassan, Ghulam Mubashar and Mian, Ajmal},
  journal={IEEE Access},
  title={Sequential Vision to Language as Story: A Storytelling Dataset and Benchmarking},
  year={2023},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/ACCESS.2023.3293646}}

SAT3D: Slot Attention Transformer for 3D Point Cloud Semantic Segmentation

M. Ibrahim, N. Akhtar, S. Anwar, and A. Mian

IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2023

Official PDF Code

@article{Ibrahim2023SAT3D,
  title={SAT3D: Slot Attention Transformer for 3D Point Cloud Semantic Segmentation},
  author={Ibrahim, Muhammad and Akhtar, Naveed and Anwar, Saeed and Mian, Ajmal},
  journal={IEEE Transactions on Intelligent Transportation Systems (T-ITS)},
  year={2023}
}

Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps

M. Ibrahim, N. Akhtar, S. Anwar, M. Wise, and A. Mian

IEEE International Conference on Robotics and Automation (ICRA), 2023

Official PDF arXiv Code

@inproceedings{Ibrahim2023slice,
  title={Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps},
  author={Ibrahim, Muhammad and Akhtar, Naveed and Anwar, Saeed and Wise, Michael and Mian, Ajmal},
  booktitle={IEEE International Conference on Robotics and Automation (ICRA)},
  year={2023}
}

2022

Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network

Y. Liu, S. Anwar, Z. Qin, P. Ji, S. Caldwell, and T. Gedeon

Sensors, 2022

Official PDF arXiv Code

@article{Liu2022FDN,
  title={Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network},
  author={Liu, Yang and Anwar, Saeed and Qin, Zhenyue and Ji, Pan and Caldwell, Sabrina and Gedeon, Tom},
  journal = {Sensors},
  volume = {22},
  year = {2022},
  number = {24},
  article-number = {9844},
  PubMedID = {36560213},
  issn = {1424-8220}
}

Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion

R. Cui, S. Qiu, S. Anwar, J. Zhang, and N. Barnes

British Machine Vision Conference (BMVC), 2022

Official PDF Supplementary arXiv Poster Video Code

@InProceedings{Ruikai2022EBM,
      title={Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion},
      author={Ruikai Cui and Shi Qiu and Saeed Anwar and Jing Zhang and Nick Barnes},
      booktitle={British Machine Vision Conference (BMVC)},
      year={2022}
}

PU-Transformer: Point Cloud Upsampling Transformer

S. Qiu, S. Anwar, and N. Barnes

Asian Conference on Computer Vision (ACCV), 2022

Official PDF arXiv Supplementary Poster Slides Code

@InProceedings{Shi2021PUTransformer,
      title={PU-Transformer: Point Cloud Upsampling Transformer},
      author={Shi Qiu and Saeed Anwar and Nick Barnes},
      booktitle={Proceedings of the Asian Conference on Computer Vision (ACCV)},
      pages={2475--2493},
      year={2022}
}

Fusing Higher-Order Features in Graph Neural Networks for Skeleton-Based Action Recognition

Z. Qin, Y. Liu, P. Ji, D. Kim, L. Wang, B. McKay, S. Anwar, and T. Gedeon

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022

arXiv Code

@article{qin2022leveraging,
  title={Leveraging Third-Order Features in Skeleton-Based Action Recognition},
  author={Qin, Zhenyue and Liu, Yang and Ji, Pan and Kim, Dongwoo and Wang, Lei and McKay, Bob and Anwar, Saeed and Gedeon, Tom},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2022}
}

Towards Low-Cost Classification for Novel Fine-Grained Datasets

A. Anwar, H. Anwar, and S. Anwar

Electronics, 2022

Official PDF Code

@article{Anwar2022lowCost,
  title={Towards Low-Cost Classification for Novel Fine-Grained Datasets},
  author={Anwar, Abbas and Anwar, Hafeez and Anwar, Saeed},
  journal={Electronics},
  year={2022}
}

Underwater Image Restoration via Contrastive Learning and a Real-world Dataset

J. Han, M. Shoeiby, T. Malthus, E. Botha, J. Anstee, S. Anwar, R. Wei, M. A. Armin, H. Li, and L. Petersson

Remote Sensing (RS), 2022Best Paper Award

Official PDF arXiv Code

@article{Han2022CWR,
      title={Underwater Image Restoration via Contrastive Learning and a Real-world Dataset},
      author={Junlin Han and Mehrdad Shoeiby and Tim Malthus and Elizabeth Botha and Janet Anstee and Saeed Anwar and Ran Wei and Mohammad Ali Armin and Hongdong Li and Lars Petersson},
      journal={Remote Sensing},
      year={2022}
}

Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns

Z. Qin, P. Ji, D. Kim, Y. Liu, S. Anwar, and T. Gedeon

European Conference on Computer Vision Workshops (ECCVW), 2022Workshop

Official PDF arXiv

@InProceedings{Qin2022Strengthening,
  title={Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns},
  author={Qin, Zhenyue and Kim, Dongwoo and Liu, Yang and Anwar, Saeed and Gedeon, Tom},
  booktitle={European Conference on Computer Vision Workshops},
  year={2022}
}

COVID19 detection from Radiographs: Is Deep Learning able to handle the crisis?

M. Saqib, A. Anwar, S. Anwar, L. Petersson, N. Sharma, and M. Blumenstein

Signals, 2022

Official PDF arXiv Code

@article{Anwar2022COVID19Detect,
  title={COVID-19 Detection from Radiographs: Is Deep Learning Able to Handle the Crisis?},
  author={Saqib, Muhammad and Anwar, Abbas and Anwar, Saeed and Petersson, Lars and Sharma, Nabin and Blumenstein, Michael},
  journal={Signals},
  volume={3},
  number={2},
  pages={296--312},
  year={2022}
}

Image Dehazing Transformer with Transmission-Aware 3D Position Embedding

C. Guo, Q. Yan, S. Anwar, R. Cong, W. Ren, and C. Li

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Official PDF Project page

@InProceedings{Chunle2022Dehaze,
    author    = {Guo, Chun-Le and Yan, Qixin and Anwar, Saeed and Cong, Runmin and Ren, Wenqi and Li, Chongyi},
    title     = {Image Dehazing Transformer With Transmission-Aware 3D Position Embedding},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {5812-5820}
}

Pyramidal Attention for Saliency Detection

T. Hussain, A. Anwar, S. Anwar, L. Petersson, and S. W. Baik

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022Workshop

Official PDF arXiv Code

@InProceedings{Hussain2022Pyramidal,
    author    = {Hussain, Tanveer and Anwar, Abbas and Anwar, Saeed and Petersson, Lars and Baik, Sung Wook},
    title     = {Pyramidal Attention for Saliency Detection},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2022},
    pages     = {2878-2888}
}

DRT: A Lightweight Single Image Deraining Recursive Transformer

Y. Liang, S. Anwar, and Y. Liu

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022Workshop

Official PDF arXiv Code

@InProceedings{Liang2022DRT,
    author    = {Liang, Yuanchu and Anwar, Saeed and Liu, Yang},
    title     = {DRT: A Lightweight Single Image Deraining Recursive Transformer},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2022},
    pages     = {589-598}
}

Depth Completion Auto-Encoder

K. Lu, N. Barnes, S. Anwar, and L. Zheng

IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACV), 2022Workshop

Official PDF Video

@InProceedings{Lu2022DA,
    author    = {Lu, Kaiyue and Barnes, Nick and Anwar, Saeed and Zheng, Liang},
    title     = {Depth Completion Auto-Encoder},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops},
    month     = {January},
    year      = {2022},
    pages     = {63-73}
}

Deep localization of protein structures in fluorescence microscopy images

M. Tahir*, S. Anwar*, A. Mian, and A. W. Muzaffar

Neural Computing and Applications (NCAA), 2022

Official PDF arXiv Code

@article{Anwar2021PLCNN,
  title={Deep localization of protein structures in fluorescence microscopy images},
  author={Tahir, Muhammad and Anwar, Saeed and Mian, Ajmal and Muzaffar, Abdul W.},
  journal={Neural Computing and Applications},
  year={2022},
  publisher={Springer}
}

2021

PnP-3D: A Plug-and-Play for 3D Point Clouds

S. Qiu, S. Anwar, and N. Barnes

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

Official PDF arXiv Code

@article{Qiu2021PnP3D,
      title={PnP-3D: A Plug-and-Play for 3D Point Clouds},
      author={Shi Qiu and Saeed Anwar and Nick Barnes},
      journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
      year={2021}
}

Attention Based Real Image Restoration

S. Anwar, N. Barnes, and L. Petersson

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021

PDF Supplementary arXiv Code

@article{Anwar2021R2NET,
    title={Attention Based Real Image Restoration},
    author={Saeed Anwar and Nick Barnes and Lars Petersson},
    journal={Transactions on Neural Networks and Learning Systems},
    year={2021},
    publisher={IEEE}
}

Investigating Attention Mechanism in 3D Point Cloud Object Detection

S. Qiu, Y. Wu, S. Anwar, and C. Li

IEEE International Conference on 3D Vision (3DV), 2021

Official PDF arXiv Poster Code

@inproceedings{Qiu2021Att3Ddetection,
      title={Investigating Attention Mechanism in 3D Point Cloud Object Detection},
      author={Shi Qiu and Yunfan Wu and Saeed Anwar and Chongyi Li},
      year={2021},
      booktitle={International Conference on 3D Vision (3DV)},
      organization={IEEE}
}

Light-DehazeNet: A Novel Lightweight CNN Architecture for Single Image Dehazing

H. Ullah, K. Muhammad, M. Irfan, S. Anwar, M. Sajjad, S. Imran, and V. H. C. D. Albuquerque

IEEE Transactions on Image Processing (TIP), 2021

Official PDF Code

@article{Hayat2021DehazeNet,
   author = {Ullah, Hayat and Muhammad, Khan and Irfan, Muhammad and Anwar, Saeed and Sajjad, Muhammad and Imran, Shariq and  De Albuquerque, Victor Hugo C.},
   title = {Light-DehazeNet: A Novel Lightweight CNN Architecture for Single Image Dehazing},
   journal ={Transactions on Image Processing},
   year={2021},
   organization={IEEE}
}

Transformers in Pedestrian Image Retrieval and Person Re-Identification in a Multi-Camera Surveillance System

M. Tahir, and S. Anwar

Applied Sciences (AS), 2021

Official PDF Code

@article{Tahir2021ReID,
AUTHOR = {Tahir, Muhammad and Anwar, Saeed},
TITLE = {Transformers in Pedestrian Image Retrieval and Person Re-Identification in a Multi-Camera Surveillance System},
JOURNAL = {Applied Sciences},
VOLUME = {11},
YEAR = {2021},
NUMBER = {19},
ARTICLE-NUMBER = {9197},
ISSN = {2076-3417},
}

Geometric Back-Projection Network for Point Cloud Classification

S. Qiu, S. Anwar, and N. Barnes

IEEE Transactions on Multimedia (TMM), 2021ESI Highly Cited

Official PDF arXiv Slides Code

@article{qiu2021geometric,
    title={Geometric Back-Projection Network for Point Cloud Classification},
    author={Shi Qiu and Saeed Anwar and Nick Barnes},
    journal = {IEEE Transaction on MultiMedia},
    year={2021}
}

Uncertainty Inspired RGB-D Saliency Detection

J. Zhang, D.P. Fan, Y. Dai, S. Anwar, F.S. Saleh, S. Aliakbarian, and N. Barnes

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

Official PDF Code

@article{Jing2021uncertainty,
  title={Uncertainty Inspired RGB-D Saliency Detection},
  author={Zhang, Jing and Fan, Deng-Ping and Dai, Yuchao and Anwar, Saeed and Saleh, Fatemeh and Aliakbarian, Sadegh and Barnes, Nick},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2021}
}

Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding

C. Li, S. Anwar, J. Hou, R. Cong, C. Guo, and W. Ren

IEEE Transactions on Image Processing (TIP), 2021

Official PDF arXiv Code Project page

@article{Chongyi2021MultiColor,
title  = {Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding},
author = {Li, Chongyi and  Anwar, Saeed and Hou, Junhui and Cong, Runmin and Guo, Chunle and Ren, Wenqi},
journal	= {IEEE Transactions on Image Processing (TIP)},
year	= {2021},
}

Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion

S. Qiu, S. Anwar, and N. Barnes

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Official PDF Supplementary arXiv Poster Slides Code

@InProceedings{QIU2021BAAF,
    author    = {Qiu, Shi and Anwar, Saeed and Barnes, Nick},
    title     = {Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion},
    booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year      = {2021},
}

Invertible Denoising Network: A Light Solution for Real Noise Removal

Y. Liu, Z. Qin, S. Anwar, P. Ji, D. Kim, S. Cadwell, and T. Gedeon

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Official PDF arXiv Code

@inproceedings{Yang2020InvDN,
  author = {Liu, Yang and Qin, Zhenyue and Anwar, Saeed and Ji, Pan and Kim, Dongwoo and Cadwell, Sabrina and Gedeon, Tom },
  title = {Invertible Denoising Network: A Light Solution for Real Noise Removal},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021}
}

Single Underwater Image Restoration by contrastive learning

J. Han, M. Shoeiby, T. Malthus, E. Botha, J. Anstee, S. Anwar, R. Wei, L. Petersson, and M. A. Armin

International Geoscience and Remote Sensing Symposium (IGARSS), 2021Oral

Official PDF arXiv Code

@inproceedings{Han2020CWR,
  author = {Han, Junlin and Shoeiby, Mehrdad and Malthus, Tim and Botha, Elizabeth and Anstee, Janet and  Anwar, Saeed  and Wei, Ran and Petersson, Lars  and Armin, Mohammad Ali
},
  title = {Single Underwater Image Restoration by contrastive learning},
  booktitle = {International Geoscience and Remote Sensing Symposium (IGARSS)},
  year = {2021}
}

Multi-FAN: Multi-Spectral Mosaic Super-Resolution Via Multi-Scale Feature Aggregation Network

M. Shoeiby, S. Aliakbarian, S. Anwar, and L. Petersson

Machine Vision and Applications (MVA), 2021

Official PDF arXiv

@article{Shoeiby2021multiSR,
  title={Multi-FAN: Multi-Spectral Mosaic Super-Resolution Via Multi-Scale Feature Aggregation Network},
  author={Shoeiby, Mehrdad and Aliakbarian, Sadegh and Anwar, Saeed and Petersson, Lars},
  journal={ Machine Vision and Applications},
  year={2021}
}

Densely Deformable Efficient Salient Object Detection Network

T. Hussain, S. Anwar, A. Ullah, K. Muhammad, and S. W. Baik

arXiv preprint, 2021

arXiv Code

@misc{Tan2021DDNET,
      title={Densely Deformable Efficient Salient Object Detection Network},
      author={Tanveer Hussain and Saeed Anwar and Amin Ullah and Khan Muhammad and Sung Wook Baik},
      year={2021},
      eprint={2102.06407},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Deep Ancient Roman Republican Coin Classification via Feature Fusion and Attention

H. Anwar*, S. Anwar*, S. Zambanini, and F. Porikli

Pattern Recognition (PR), 2021

Official PDF arXiv Code

@article{Anwar2021CoinNet,
title = {Deep Ancient Roman Republican Coin Classification via Feature Fusion and Attention},
journal = {Pattern Recognition},
pages = {107871},
year = {2021},
issn = {0031-3203},
doi = {https://doi.org/10.1016/j.patcog.2021.107871},
url = {https://www.sciencedirect.com/science/article/pii/S0031320321000583},
author = {Hafeez Anwar and Saeed Anwar and Sebastian Zambanini and Fatih Porikli},
}

Deblur and Deep Depth from a Defocus Image

S. Anwar, Z. Hayder, and F. Porikli

Machine Vision and Applications (MVA), 2021

Official PDF arXiv Code

@article{Anwar2021DefocusMVA,
  title={Deblur and deep depth from single defocus image},
  author={Anwar, Saeed and Hayder, Zeeshan and Porikli, Fatih},
  journal={Machine Vision and Applications},
  volume={32},
  number={1},
  pages={1--13},
  year={2021},
  publisher={Springer}
}

Dense-Resolution Network for Point Cloud Classification and Segmentation

S. Qiu, S. Anwar, and N. Barnes

IEEE Winter Conference on Applications of Computer Vision (WACV), 2021

Official PDF Supplementary arXiv Video Slides Code

@InProceedings{QIU2021DRNET,
    author    = {Qiu, Shi and Anwar, Saeed and Barnes, Nick},
    title     = {Dense-Resolution Network for Point Cloud Classification and Segmentation},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
    month     = {January},
    year      = {2021},
    pages     = {3813-3822}
}

2020

Densely Residual Laplacian Super-Resolution

S. Anwar and N. Barnes

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020

Official PDF Supplementary arXiv Code

@article{Anwar2020DRLN,
  author = {Anwar, Saeed and Barnes, Nick},
  title = {Densely Residual Laplacian Super-Resolution},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2020}
}

Diving Deeper into Underwater image enhancement: A survey

S. Anwar and C. Li

Signal Processing: Image Communication (SPIC), 2020

Official PDF arXiv Code

@article{Anwar2020UWESurvey,
  title = "Diving deeper into underwater image enhancement: A survey",
  journal = "Signal Processing: Image Communication",
  volume = "89",
  pages = "115978",
  year = "2020",
  issn = "0923-5965",
  doi = "https://doi.org/10.1016/j.image.2020.115978",
  url = "http://www.sciencedirect.com/science/article/pii/S0923596520301478",
  author = "Saeed Anwar and Chongyi Li",
}

Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable

Y. Liu, Z. Qin, S. Anwar, S. Caldwell, and T. Gedeon

International Conference on Neural Information Processing (ICONIP), 2020Oral

Official PDF Code

@inproceedings{Yang2020Glow,
  author = {Liu, Yang and Qin, Zhenyue and Anwar, Saeed  and Caldwell, Sabrina  and Gedeon, Tom },
  title = {Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable},
  booktitle={International Conference on Neural Information Processing},
  year = {2020}
}

OfGAN: Realistic Rendition of Synthetic Colonoscopy Videos

J. Xu, S. Anwar, N. Barnes, F. Grimpen, O. Salvado, S. Anderson, and M. A. Armin

Medical Image Computing and Computer Assisted Intervention (MICCAI), 2020Oral

Official PDF

@InProceedings{Xu2020OfGAN,
 author="Xu, Jiabo and Anwar, Saeed and Barnes, Nick and Grimpen, Florian and Salvado, Olivier and Anderson, Stuart and Armin, Mohammad Ali",
 title="OfGAN: Realistic Rendition of Synthetic Colonoscopy Videos",
 booktitle="Medical Image Computing and Computer Assisted Intervention (MICCAI)",
 year="2020",
 publisher="Springer International Publishing",
 address="Cham",
 pages="732--741",
 isbn="978-3-030-59716-0"
}

A Deep Journey into Super-resolution: A survey

S. Anwar, S. Khan, and N. Barnes

ACM Computing Surveys (CSUR), 2020

Official PDF arXiv Code

@article{Anwar2020Survey,
  author = {Anwar, Saeed and Khan, Salman and Barnes, Nick},
    title = {A Deep Journey into Super-resolution: A survey},
    journal={ACM Computing Surveys (CSUR)},
    year={2020},
    publisher={ACM New York, NY, USA}
}

UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

J. Zhang, D.P. Fan, Y. Dai, S. Anwar, F.S. Saleh, T. Zhang, and N. Barnes

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020OralBest Paper nominated in CVPR

Official PDF Code

@InProceedings{Jing2020UCNET,
author = {Zhang, Jing and Fan, Deng-Ping and Dai, Yuchao and Anwar, Saeed and Saleh, Fatemeh Sadat and Zhang, Tong and Barnes, Nick},
title = {UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

From Depth What Can You See? Depth Completion via Auxiliary Image Reconstruction

K. Lu, N. Barnes, S. Anwar, and L. Zheng

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Official PDF Video

@InProceedings{Kaiyue2020Depth,
author = {Lu, Kaiyue and Barnes, Nick and Anwar, Saeed and Zheng, Liang},
title = {From Depth What Can You See? Depth Completion via Auxiliary Image Reconstruction},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

Identity Enhanced Image Denoising

S. Anwar, C. P. Huynh, and F. Porikli

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020Workshop

Official PDF arXiv Supplementary Code

@InProceedings{Anwar2020IERD,
    author = {Anwar, Saeed and Phuoc Huynh, Cong and Porikli, Fatih},
    title = {Identity Enhanced Residual Image Denoising},
    booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month = {June},
    year = {2020}
}

GradNet Image Denoising

Y. Liu, S. Anwar, and L. Zheng

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020Workshop

Official PDF Supplementary Code

@InProceedings{Yang2020GradNet,
    author = {Liu, Yang and Anwar, Saeed and Zheng, Liang and Tian, Qi},
    title = {GradNet Image Denoising},
    booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month = {June},
    year = {2020}
}

Mosaic Super-resolution via Sequential Feature Pyramid Networks

M. Shoeiby, M. A. Armin, S. Aliakbarian, S. Anwar, and L. petersson

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020OralWorkshop

Official PDF arXiv

@InProceedings{Mehrdad2019SR,
     author = {Shoeiby, Mehrdad and Armin, Ali and Aliakbarian, Sadegh and Anwar, Saeed and Petersson, Lars},
     title = {Mosaic Super-Resolution via Sequential Feature Pyramid Networks},
     booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
     month = {June},
     year = {2020}
}

Earlier

2009–2019

Real Image Denoising with Feature Attention

S. Anwar and N. Barnes

IEEE International Conference on Computer Vision (ICCV), 2019Oral

Official PDF Supplementary Code

@InProceedings{Anwar2019RIDNET,
author = {Anwar, Saeed and Barnes, Nick},
title = {Real Image Denoising With Feature Attention},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}

Underwater Scene Prior Inspired Deep Underwater Image and Video Enhancement

S. Anwar, C. Li, and F. Porikli

Pattern Recognition (PR), 2019ESI Highly CitedBest Paper Honorable Mention

Official PDF arXiv Code

@article{Anwar2019UWE,
  title={Underwater Scene Prior Inspired Deep Underwater Image and Video Enhancement},
  author={Li, Chongyi and Anwar, Saeed},
  journal={Pattern Recognition},
  pages={107038},
  year={2019},
  publisher={Elsevier}
}

Image Deblurring with a Class-Specific Prior

S. Anwar, C. P. Huynh, and F. Porikli

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018

Official PDF Supplementary Code

@article{Anwar2018PAMI,
  author = {Anwar, Saeed and Huynh, Cong P. and Porikli, Fatih },
  title = {Image Deblurring with a Class-Specific Prior},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2018}
}

Category-Specific Object Image Denoising

S. Anwar, F. Porikli, and C. P. Huynh

IEEE Transactions on Image Processing (TIP), 2017

Official PDF Code

@article{Anwar2017category,
	title	={Category-specific object image denoising},
	author	={Anwar, Saeed and Porikli, Fatih and Huynh, Cong Phuoc},
	journal	={IEEE Transactions on Image Processing},
	volume	={26},
	number	={11},
	pages	={5506--5518},
	year	={2017},
	publisher={IEEE}
}

Combined Internal and External Category-Specific Image Denoising

S. Anwar, C. P. Huynh, and F. Porikli

British Machine Vision Conference (BMVC), 2017

Official PDF Code

@inproceedings{Anwar2017internalnoise,
  author = {Anwar, Saeed and Huynh, Cong P. and Porikli, Fatih },
  title = {Combined Internal and External Category-Specific Image Denoising},
  booktitle = {British Machine Vision Conference},
  year = {2017}
}

Depth Estimation and Blur Removal from a Single Out-of-focus Image

S. Anwar, Z Hayder, and F. Porikli

British Machine Vision Conference (BMVC), 2017Oral

Official PDF Code

@inproceedings{Anwar2017depth,
  author = {Anwar, Saeed and Hayder, Zeeshan and Porikli, Fatih },
  title = {Depth Estimation and Blur Removal from a Single Out-of-focus Image},
  booktitle = {British Machine Vision Conference},
  year = {2017}
}

Class-specific image deblurring

S. Anwar, C. P. Huynh, and F. Porikli

IEEE International Conference on Computer Vision (ICCV), 2015

Official PDF Code

@inproceedings{anwar2015class,
  title={Class-specific image deblurring},
  author={Anwar, Saeed and Phuoc Huynh, Cong and Porikli, Fatih},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={495--503},
  year={2015}
}

Fast mean shift and particle filtering based visual human tracking

M. Farooq, S. Anwar, and S. Khan

IEEE Multitopic Conference (INMIC), 2009

PDF

@inproceedings{farooq2009fast,
  title={Fast mean shift and particle filtering based visual human tracking},
  author={Farooq, Muhammad and Anwar, Saeed and Khan, Sharif},
  booktitle={Multitopic Conference, INMIC 2009. IEEE 13th International},
  pages={1--5},
  year={2009}
}

Thesis

Data-Driven Image Restoration

S. Anwar

PhD thesis, The Australian National University

PDF

@phdthesis{anwarthesis,
  title={Data-Driven Image Restoration},
  author={Anwar, Saeed},
  school={The Australian National University (Australia) },
  year={2018}
}