Description: “Visual storytelling refers to the manner of describing a set of images rather than a single image, also known as multi-image captioning. Visual Storytelling Task (VST) takes a set of images as input and aims to generate a coherent story relevant to the input images. The image sets are collected manually from publicly available videos in three domains: documentaries, lifestyle, and movies, and then annotated manually using Amazon Mechanical Turk. In summary, SSID dataset is comprised of 17,365 images, which resulted in a total of 3,473 unique sets of five images. Each set of images is associated with four ground truths, resulting in a total of 13,892 unique ground truths (i.e., written stories). And each ground truth is composed of five connected sentences written in the form of a story. ”
[Dataset] [BibTeX] [PDF]
@article{Malakan2023SSID,
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}
}
Description: “A large-scale outdoor point cloud dataset captured with LiDAR sensor and annotated manually for semantic segmentation, instance segmentation and object detection.”
[Dataset] [BibTeX] [PDF]
@article{Ibrahim2023SWAN,
author={Ibrahim, Muhammad and Akhtar, Naveed and Anwar, Saeed and Mian, Ajmal},
journal={IEEE Transactions on Intelligent Transportation Systems},
title={SAT3D: Slot Attention Transformer for 3D Point Cloud Semantic Segmentation},
year={2023},
pages={1-11},
}
Description: “LiDAR 3D point cloud map of Perth, Western Australia is provided with ground truth locations and orientations.”
[Dataset] [BibTeX] [PDF]
@article{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},
journal={IEEE International Conference on Robotics and Automation (ICRA)},
year={2023}
}
Description: “FGBR contains two species, butterfly and reef fish. The butterfly dataset has 50 species, consisting of 2613 images, most of which are ecological. The reef fish also has 50 species. Most of the 3825 images in the reef fish dataset are ecological.”
[Dataset] [BibTeX] [PDF]
@article{Anwar2022FGBR,
title={Towards Low-Cost Classification for Novel Fine-Grained Datasets},
author={Anwar, Abbas and Anwar, Hafeez and Anwar, Saeed},
journal={Electronics},
year={2022}
}
Description: “ANUBIS is a large-scale human skeleton dataset containing 80 actions. Compared with previously collected datasets, ANUBIS is advantageous in the following four aspects: (1) employing more recently released sensors; (2) containing novel back view; (3) encouraging high enthusiasm of subjects; (4) including actions of the COVID pandemic era.”
[Dataset] [BibTeX] [PDF]
@article{Qin2022ANUBIS,
title={ANUBIS: Skeleton Action Recognition Dataset, Review, and Benchmark},
author={Qin, Zhenyue and Liu, Yang and Perera, Madhawa and Gedeon, Tom and Ji, Pan and Kim, Dongwoo and Anwar, Saeed},
journal={arXiv preprint arXiv:2205.02071},
year={2022}
}
Description: “We collect a novel dataset that has 10k images of Pakistani vehicles. These vehicles are trucks, buses, vans, carry vans, and cars. There are two sub-classes of trucks called type1 trucks having a single axle and type2 trucks with double axles. After dataset collection, the pre-processing steps and ground truth generation are performed to train and test the CNN models.”
[Dataset] [BibTeX] [PDF]
@InProceedings{Usama2022VTLPR,
title={Vehicle and License Plate Recognition with Novel Dataset for Toll Collection},
author={Muhammad Usama and Hafeez Anwar and Muhammad Muaz Shahid and Abbas Anwar and Saeed Anwar and Helmuth Hlavacs},
year={2022},
eprint={2202.05631},
archivePrefix={arXiv},
primaryClass={eess.IV}
}
Description: “Heron Island Coral Reef Dataset (HICRD) contains 6003 low-quality images, 3673 good-quality images, and 2000 restored images. We use low-quality images and restored images as the unpaired training set (trainA + trainB). In contrast, the paired training set contains good-quality (trainA_paired) images and corresponding restored images (trainB_paired). The test set contains 300 good-quality images (testA) as well as 300 paired restored images (testB) as ground truth. All images are in 1842 x 980 resolution. The copyright belongs to CSIRO (Commonwealth Scientific and Industrial Research Organisation).”
[Dataset] [BibTeX] [arXiv]
@article{Han2021CWR,
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},
year={2021},
eprint={2106.10718},
archivePrefix={arXiv},
primaryClass={eess.IV}
}
Description: “Based on Crawford’s work, we collect the most diverse and extensive image dataset of the reverse sides. For most of the Roman Republic coin classes, the ob- verse side depicts more discriminative information than the observe side. Our dataset has 228 motif classes, including 100 classes that are the main classes for training and testing, which we call the main dataset RRCD-Main. The images of the additional 128 classes constitute the disjoint test set, RRCD-Disjoint, which we allocate to assess the generalization ability of our models.,”
[Dataset] [BibTeX] [PDF] [arXiv]
@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},
}
Description: “The Natural-Color Dataset (NCD) is an image colorization dataset where images are true to their colors. For example, a carrot will have an orange color in most images. Bananas will be either greenish or yellowish. It contains 723 images from the internet distributed in 20 categories. Each image has an object and a white background.”
[Dataset (GrayScale Images)] [Dataset (Color GroundTruth)] [BibTeX] [PDF]
@article{Anwar2020ColorSurvey,
title={Image Colorization: A Survey and Dataset},
author={Anwar, Saeed and Tahir, Muhammad and Li, Chongyi and Mian, Ajmal and Khan, Fahad Shahbaz and Muzaffar, Abdul Wahab},
journal={arXiv preprint arXiv:2008.10774},
year={2020}
}
Description: “To synthesize underwater image degradation datasets, we use the attenuation coefficients described in Table 1 for the different water types of oceanic and coastal classes (i.e., I, IA, IB, II, and III for open ocean waters, and 1, 3, 5, 7, and 9 for coastal waters). Type-I is the clearest and Type-III is the most turbid open ocean water. Similarly, for coastal waters, Type-1 is the clearest and Type-9 is the most turbid. We apply Eqs (1) and (2) (please check the paper) to build ten types of underwater image datasets by using the RGB-D NYU-v2 indoor dataset which consists of 1449 images. To improve the quality of datasets, we crop the original size (480x640) of NYU-v2 to 460x620. This dataset is for non-commercial use only. The size of each dataset is 1.2GB”
[Dataset] [BibTeX] [PR Version] [PDF]
@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}
}
Description: “ Synthetic Monocular Depth generation code,”
[BibTeX] [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}
}