@article{sam, title={Segment anything}, author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C and Lo, Wan-Yen and others}, journal={arXiv preprint arXiv:2304.02643}, year={2023} } @inproceedings{xmem, author = {Ho Kei Cheng and Alexander G. Schwing}, title = {XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model}, booktitle = {{ECCV} {(28)}}, series = {Lecture Notes in Computer Science}, volume = {13688}, pages = {640--658}, publisher = {Springer}, year = {2022} } %related @article{vos, author = {Mingqi Gao and Feng Zheng and James J. Q. Yu and Caifeng Shan and Guiguang Ding and Jungong Han}, title = {Deep learning for video object segmentation: a review}, journal = {Artif. Intell. Rev.}, volume = {56}, number = {1}, pages = {457--531}, year = {2023} } @inproceedings{vot9, title={The ninth visual object tracking vot2021 challenge results}, author={Kristan, Matej and Matas, Ji{\v{r}}{\'\i} and Leonardis, Ale{\v{s}} and Felsberg, Michael and Pflugfelder, Roman and K{\"a}m{\"a}r{\"a}inen, Joni-Kristian and Chang, Hyung Jin and Danelljan, Martin and Cehovin, Luka and Luke{\v{z}}i{\v{c}}, Alan and others}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={2711--2738}, year={2021} } @inproceedings{vot10, title={The Tenth Visual Object Tracking VOT2022 Challenge Results}, author={Kristan, Matej and Leonardis, Ale{\v{s}} and Matas, Ji{\v{r}}{\'\i} and Felsberg, Michael and Pflugfelder, Roman and K{\"a}m{\"a}r{\"a}inen, Joni-Kristian and Chang, Hyung Jin and Danelljan, Martin and Zajc, Luka {\v{C}}ehovin and Luke{\v{z}}i{\v{c}}, Alan and others}, booktitle={Computer Vision--ECCV 2022 Workshops: Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part VIII}, pages={431--460}, year={2023}, organization={Springer} } @inproceedings{vot8, title={The eighth visual object tracking VOT2020 challenge results}, author={Kristan, Matej and Leonardis, Ale{\v{s}} and Matas, Ji{\v{r}}{\'\i} and Felsberg, Michael and Pflugfelder, Roman and K{\"a}m{\"a}r{\"a}inen, Joni-Kristian and Danelljan, Martin and Zajc, Luka {\v{C}}ehovin and Luke{\v{z}}i{\v{c}}, Alan and Drbohlav, Ondrej and others}, booktitle={European Conference on Computer Vision}, pages={547--601}, year={2020}, organization={Springer} } @inproceedings{vot7, title={The seventh visual object tracking vot2019 challenge results}, author={Kristan, Matej and Matas, Jiri and Leonardis, Ales and Felsberg, Michael and Pflugfelder, Roman and Kamarainen, Joni-Kristian and ˇCehovin Zajc, Luka and Drbohlav, Ondrej and Lukezic, Alan and Berg, Amanda and others}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops}, pages={0--0}, year={2019} } @inproceedings{vot6, title={The sixth visual object tracking vot2018 challenge results}, author={Kristan, Matej and Leonardis, Ales and Matas, Jiri and Felsberg, Michael and Pflugfelder, Roman and ˇCehovin Zajc, Luka and Vojir, Tomas and Bhat, Goutam and Lukezic, Alan and Eldesokey, Abdelrahman and others}, booktitle={Proceedings of the European Conference on Computer Vision (ECCV) Workshops}, pages={0--0}, year={2018} } @inproceedings{vit, author = {Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby}, title = {An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale}, booktitle = {{ICLR}}, publisher = {OpenReview.net}, year = {2021} } @inproceedings{stm, author = {Seoung Wug Oh and Joon{-}Young Lee and Ning Xu and Seon Joo Kim}, title = {Video Object Segmentation Using Space-Time Memory Networks}, booktitle = {{ICCV}}, pages = {9225--9234}, publisher = {{IEEE}}, year = {2019} } @inproceedings{siammask, author = {Qiang Wang and Li Zhang and Luca Bertinetto and Weiming Hu and Philip H. S. Torr}, title = {Fast Online Object Tracking and Segmentation: {A} Unifying Approach}, booktitle = {{CVPR}}, pages = {1328--1338}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2019} } @inproceedings{mivos, author = {Ho Kei Cheng and Yu{-}Wing Tai and Chi{-}Keung Tang}, title = {Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion}, booktitle = {{CVPR}}, pages = {5559--5568}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2021} } @article{davis, author = {Jordi Pont{-}Tuset and Federico Perazzi and Sergi Caelles and Pablo Arbelaez and Alexander Sorkine{-}Hornung and Luc Van Gool}, title = {The 2017 {DAVIS} Challenge on Video Object Segmentation}, journal = {CoRR}, volume = {abs/1704.00675}, year = {2017} } @inproceedings{aot, author = {Zongxin Yang and Yunchao Wei and Yi Yang}, title = {Associating Objects with Transformers for Video Object Segmentation}, booktitle = {NeurIPS}, pages = {2491--2502}, year = {2021} } @inproceedings{icip, author = {St{\'{e}}phane Vujasinovic and Sebastian Bullinger and Stefan Becker and Norbert Scherer{-}Negenborn and Michael Arens and Rainer Stiefelhagen}, title = {Revisiting Click-Based Interactive Video Object Segmentation}, booktitle = {{ICIP}}, pages = {2756--2760}, publisher = {{IEEE}}, year = {2022} } @inproceedings{e2fgvi, author = {Zhen Li and Chengze Lu and Jianhua Qin and Chun{-}Le Guo and Ming{-}Ming Cheng}, title = {Towards An End-to-End Framework for Flow-Guided Video Inpainting}, booktitle = {{CVPR}}, pages = {17541--17550}, publisher = {{IEEE}}, year = {2022} }