@inproceedings{bb223000,
AUTHOR = "Yuan, Y.C. and Wang, Y.F. and Wang, L.J. and Zhao, X.Q. and Lu, H.C. and Wang, Y. and Su, W.B. and Zhang, L.",
TITLE = "Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "966-976",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218103"}
@article{bb223001,
AUTHOR = "Yang, Z.X. and Miao, J.X. and Wei, Y.C. and Wang, W.G. and Wang, X.H. and Yang, Y.",
TITLE = "Scalable Video Object Segmentation With Identification Mechanism",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "9",
MONTH = "September",
PAGES = "6247-6262",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218104"}
@article{bb223002,
AUTHOR = "Lu, Y.W. and Zhang, J. and Sun, S. and Guo, Q.Y. and Cao, Z.W. and Fei, S.L. and Yang, B. and Chen, Y.J.V.",
TITLE = "Label-Efficient Video Object Segmentation With Motion Clues",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "8",
MONTH = "August",
PAGES = "6710-6721",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218105"}
@article{bb223003,
AUTHOR = "Hou, Z.Q. and Li, F.C. and Dong, J. and Dai, N. and Ma, S. and Fan, J.",
TITLE = "Video object segmentation based on dynamic perception update and
feature fusion",
JOURNAL = IVC,
VOLUME = "150",
YEAR = "2024",
PAGES = "105156",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218106"}
@article{bb223004,
AUTHOR = "Hou, Z.Q. and Dong, J. and Wang, C.X. and Ma, S. and Yu, W.S. and Wang, Y.C.",
TITLE = "Video object segmentation based on feature compression and attention
correction",
JOURNAL = SP:IC,
VOLUME = "142",
YEAR = "2026",
PAGES = "117456",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218107"}
@article{bb223005,
AUTHOR = "Fan, J.Q. and Hu, S.L. and Wang, L. and Zhang, K. and Liu, B.",
TITLE = "Dual temporal memory network with high-order spatio-temporal graph
learning for video object segmentation",
JOURNAL = IVC,
VOLUME = "150",
YEAR = "2024",
PAGES = "105208",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218108"}
@inproceedings{bb223006,
AUTHOR = "Xie, F. and Yang, W.K. and Zhang, K. and Liu, B. and Wang, G.T. and Zuo, W.M.",
TITLE = "Learning Spatio-Appearance Memory Network for High-Performance Visual
Tracking",
BOOKTITLE = VOT21,
YEAR = "2021",
PAGES = "2678-2687",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218109"}
@article{bb223007,
AUTHOR = "Xu, S. and Wei, S.K. and Ruan, T. and Liao, L.X. and Zhao, Y.",
TITLE = "Each Performs Its Functions: Task Decomposition and Feature
Assignment for Audio-Visual Segmentation",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "9489-9498",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218110"}
@article{bb223008,
AUTHOR = "Duan, L. and Yang, R.F. and Yue, K. and Sun, Z.B. and Yuan, G.W.",
TITLE = "Video object detection via space-time feature aggregation and result
reuse",
JOURNAL = IET-IPR,
VOLUME = "18",
YEAR = "2024",
NUMBER = "12",
PAGES = "3356-3367",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218111"}
@article{bb223009,
AUTHOR = "Li, W. and Fan, J. and Guo, P. and Hong, L. and Zhang, W.",
TITLE = "HFVOS: History-Future Integrated Dynamic Memory for Video Object
Segmentation",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "10",
MONTH = "October",
PAGES = "10208-10222",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218112"}
@article{bb223010,
AUTHOR = "Miao, B. and Bennamoun, M. and Gao, Y.S. and Shah, M. and Mian, A.",
TITLE = "Temporally Consistent Referring Video Object Segmentation With Hybrid
Memory",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "11",
MONTH = "November",
PAGES = "11373-11385",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218113"}
@article{bb223011,
AUTHOR = "Zhang, F. and Ji, H.B. and Zhang, Y.Q. and Zhu, Z.G.",
TITLE = "Joint Spatial and Temporal Feature Enhancement Network for Disturbed
Object Detection",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "12258-12273",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218114"}
@article{bb223012,
AUTHOR = "Li, X.J. and Zong, Y. and Zheng, W.M.",
TITLE = "Adaptive Multi-Scale Iterative Optimized Video Object Segmentation
Based on Correlation Enhancement",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "13099-13112",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218115"}
@article{bb223013,
AUTHOR = "Qi, Q. and Qiu, Z.Y. and Yan, Y. and Lu, Y. and Wang, H.Z.",
TITLE = "IMC-Det: Intra-Inter Modality Contrastive Learning for Video Object
Detection",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "2",
MONTH = "February",
PAGES = "890-909",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218116"}
@article{bb223014,
AUTHOR = "Li, X.M. and Wang, Q.H. and Li, D.Z. and Ge, M.M. and Jia, X. and He, Y. and Lu, H.C.",
TITLE = "MoBox: Enhancing Video Object Segmentation With Motion-Augmented Box
Supervision",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "405-417",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218117"}
@article{bb223015,
AUTHOR = "Guo, P.X. and Zhang, W. and Li, X.Q. and Fan, J.P. and Zhang, W.Q.",
TITLE = "Self-supervised video object segmentation via pseudo label
rectification",
JOURNAL = PR,
VOLUME = "163",
YEAR = "2025",
PAGES = "111428",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218118"}
@article{bb223016,
AUTHOR = "Liu, Y. and Yu, R. and Yin, F. and Zhao, X.Y. and Zhao, W. and Xia, W.H. and Wang, J.H. and Wang, Y.T. and Tang, Y.S. and Yang, Y.",
TITLE = "Learning High-Quality Dynamic Memory for Video Object Segmentation",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "3452-3468",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218119"}
@inproceedings{bb223017,
AUTHOR = "Liu, Y. and Yu, R. and Yin, F. and Zhao, X.Y. and Zhao, W. and Xia, W.H. and Yang, Y.",
TITLE = "Learning Quality-aware Dynamic Memory for Video Object Segmentation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:468-486",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218120"}
@article{bb223018,
AUTHOR = "Qi, Q. and Wang, H.Z. and Yan, Y. and Li, X.L.",
TITLE = "DGC-Net: Dynamic Graph Contrastive Network for Video Object Detection",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "2269-2284",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218121"}
@inproceedings{bb223019,
AUTHOR = "Qiu, Z.Y. and Qi, Q. and Yan, Y. and Wang, H.Z.",
TITLE = "DF-Net: Diversity-Focused Network for Video Object Detection",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "2105-2109",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218122"}
@article{bb223020,
AUTHOR = "Gao, X.Y. and Li, Z. and Shi, H.L. and Chen, Z.Y. and Zhao, P.L.",
TITLE = "Scribble-Supervised Video Object Segmentation via Scribble
Enhancement",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "2999-3012",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218123"}
@article{bb223021,
AUTHOR = "Cho, E. and Kim, J.U. and Kim, S.T.",
TITLE = "Spatial Mask-Based Adaptive Robust Training for Video Object
Segmentation With Noisy Labels",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "4976-4990",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218124"}
@article{bb223022,
AUTHOR = "Yang, J.X. and Zhang, L. and Lu, H.C.",
TITLE = "Semantics Alternating Enhancement and Bidirectional Aggregation for
Referring Video Object Segmentation",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "2987-2998",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218125"}
@article{bb223023,
AUTHOR = "Siam, M.",
TITLE = "Temporal Transductive Inference for Few-Shot Video Object Segmentation",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "4465-4482",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218126"}
@article{bb223024,
AUTHOR = "Zhang, J.M. and Cui, Y.T. and Wu, G.S. and Wang, L.M.",
TITLE = "JointFormer: A Unified Framework with Joint Modeling for Video Object
Segmentation",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "6039-6054",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218127"}
@article{bb223025,
AUTHOR = "Yu, J.H. and Chen, Y.F. and Wang, X. and Chen, L. and Chen, H. and Zhou, D. and Xu, Y.K. and Ju, Z.J.",
TITLE = "Video Object Detection Considering Dynamic Neighborhood Feature
Multiplexing",
JOURNAL = SMCS,
VOLUME = "55",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "5451-5463",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218128"}
@article{bb223026,
AUTHOR = "Liu, H. and Li, G.H. and Gao, M.Q. and Zhen, X.T. and Zheng, F. and Wang, Y.",
TITLE = "Few-Shot Referring Video Single- and Multi-Object Segmentation Via
Cross-Modal Affinity with Instance Sequence Matching",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "5610-5628",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218129"}
@inproceedings{bb223027,
AUTHOR = "Li, G.H. and Gao, M.Q. and Liu, H. and Zhen, X.T. and Zheng, F.",
TITLE = "Learning Cross-Modal Affinity for Referring Video Object Segmentation
Targeting Limited Samples",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2684-2693",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218130"}
@article{bb223028,
AUTHOR = "Ding, H.H. and Liu, C. and He, S.T. and Ying, K.N. and Jiang, X.D. and Loy, C.C. and Jiang, Y.G.",
TITLE = "MeViS: A Multi-Modal Dataset for Referring Motion Expression Video
Segmentation",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "12",
MONTH = "December",
PAGES = "11400-11416",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218131"}
@article{bb223029,
AUTHOR = "Hong, L.Y. and Liu, Z.Y. and Chen, W.C. and Tan, C.Z. and Feng, Y. and Zhou, X.Y. and Guo, P. and Li, J.L. and Chen, Z.Y. and Gao, S. and Zhang, W. and Zhang, W.Q.",
TITLE = "LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "946-961",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218132"}
@inproceedings{bb223030,
AUTHOR = "Hong, L.Y. and Chen, W.C. and Liu, Z.Y. and Zhang, W. and Guo, P. and Chen, Z.Y. and Zhang, W.Q.",
TITLE = "LVOS: A Benchmark for Long-term Video Object Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13434-13446",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218133"}
@article{bb223031,
AUTHOR = "Chen, Z.Y. and Zhu, J. and Zhang, L. and Hu, P. and Zhuge, Y.Z. and Lu, H.C. and He, Y.",
TITLE = "RVMamba: Selective Text-Vision Mamba for Referring Video Object
Segmentation",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "4349-4353",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218134"}
@article{bb223032,
AUTHOR = "Liu, Y. and Luo, Z.Y. and Xiao, Y.C. and Wang, Y.T. and Li, S.Y. and Li, X. and Yang, Y.J. and Tang, Y.S.",
TITLE = "Semantic-Assisted Object Clustering for Multi-Modal Referring Video
Segmentation",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "572-590",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218135"}
@inproceedings{bb223033,
AUTHOR = "Liu, Y. and Yu, R. and Wang, J.H. and Zhao, X.Y. and Wang, Y.T. and Tang, Y.S. and Yang, Y.J.",
TITLE = "Global Spectral Filter Memory Network for Video Object Segmentation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:648-665",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218136"}
@article{bb223034,
AUTHOR = "Sun, B. and Ma, X.Z. and Wang, N. and Wang, Z.H. and Wang, Z.Y.",
TITLE = "Referring Video Object Segmentation With Cross-Modality Proxy Queries",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "9659-9669",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218137"}
@article{bb223035,
AUTHOR = "Wang, Y.H. and Sun, B. and Ma, X.Z. and Ge, H.W. and Fan, J. and Li, H.J.",
TITLE = "P^2M: Progressive Perspective Mining for Referring Video Object
Segmentation",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "9749-9760",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218138"}
@article{bb223036,
AUTHOR = "Wei, B.N. and Maraval, J. and Outtas, M. and Kpalma, K. and Ramin, N. and Zhang, L.",
TITLE = "MUVOD: A Novel Multi-View Video Object Segmentation Dataset and a
Benchmark for 3D Segmentation",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "726-741",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218139"}
@article{bb223037,
AUTHOR = "Shi, Y.H. and Zhang, T. and Guo, X.J.",
TITLE = "Practical Video Object Detection via Feature Selection and Aggregation",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "95",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218140"}
@article{bb223038,
AUTHOR = "Plou, C. and Mur Labadia, L. and Guerrero, J.J. and Martinez Cantin, R. and Murillo, A.C.",
TITLE = "Temporal video segmentation with natural language using text-video
cross attention and Bayesian order-priors",
JOURNAL = CVIU,
VOLUME = "264",
YEAR = "2026",
PAGES = "104622",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218141"}
@article{bb223039,
AUTHOR = "Dang, J.S. and Zheng, H.C. and Chen, Z.X. and Li, Z. and Guo, Y.L. and Chua, T.S.",
TITLE = "Fast Track Anything With Sparse Spatio-Temporal Propagation for
Unified Video Segmentation",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "955-969",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218142"}
@article{bb223040,
AUTHOR = "Guo, P. and Hong, L.Y. and Zhou, X.Y. and Gao, S.Y. and Li, W. and Li, J.L. and Chen, Z.Y. and Li, X.Q. and Zhang, W. and Zhang, W.Q.",
TITLE = "ClickVOS: Click Video Object Segmentation",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "320-334",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218143"}
@article{bb223041,
AUTHOR = "Yang, W.J. and Kao, Y.Y. and Liu, T. and Yu, Y. and Huang, K.Q.",
TITLE = "COSOS-1k: A Benchmark Dataset and Occlusion-Aware Uncertainty
Learning for Multi-View Video Object Detection",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "599-614",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218144"}
@article{bb223042,
AUTHOR = "Li, G.Q. and Yuan, H. and Chen, S. and Hu, Q. and Wang, J. and Jiang, K.M.",
TITLE = "MFT: Memory-Aware Fine-Tuning of SAM2 for Efficient Long-Sequence
Video Object Segmentation",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "943-947",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218145"}
@inproceedings{bb223043,
AUTHOR = "Jeon, I. and Cho, S. and Lee, M. and Lee, S. and Kang, M. and Lee, J. and Park, C. and Kim, D. and Lee, S.Y.",
TITLE = "CMTM: Cross-Modal Token Modulation for Unsupervised Video Object
Segmentation",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "1390-1395",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218146"}
@inproceedings{bb223044,
AUTHOR = "Li, K.H. and Chen, F. and Zeng, X.X. and Liu, W. and Chen, H.Y.",
TITLE = "Task-Specific Spatiotemporal Context-Aware Decoupling for Occluded
Video Object Detection",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "701-706",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218147"}
@inproceedings{bb223045,
AUTHOR = "Yasarla, R. and Han, S.Z. and Cai, H. and Porikli, F.M.",
TITLE = "DySS: Dynamic Queries and State-Space Learning for Efficient 3D
Object Detection from Multi-Camera Videos",
BOOKTITLE = WAD25,
YEAR = "2025",
PAGES = "2501-2510",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218148"}
@inproceedings{bb223046,
AUTHOR = "Delatolas, T. and Kalogeiton, V. and Papadopoulos, D.P.",
TITLE = "Studying Image Diffusion Features for Zero-Shot Video Object
Segmentation",
BOOKTITLE = PVUW25,
YEAR = "2025",
PAGES = "01-12",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218149"}
@inproceedings{bb223047,
AUTHOR = "Liu, Q. and Wang, J.F. and Yang, Z.Y. and Li, L.J. and Lin, K. and Niethammer, M. and Wang, L.J.",
TITLE = "LiVOS: Light Video Object Segmentation with Gated Linear Matching",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8668-8678",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218150"}
@inproceedings{bb223048,
AUTHOR = "Mei, H.Y. and Zhang, P.Y. and Shou, M.Z.",
TITLE = "SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with
Less than 0.2% Training Cost",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3417-3426",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218151"}
@inproceedings{bb223049,
AUTHOR = "Chen, Z.X. and Li, J.X. and Liang, J. and Tan, L.M. and Guo, Y. and Lu, C. and Li, Y.L.",
TITLE = "M3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object
Segmentation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29193-29202",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218152"}
@inproceedings{bb223050,
AUTHOR = "Huang, N. and Zheng, W.Z. and Xu, C.F. and Keutzer, K. and Zhang, S.H. and Kanazawa, A. and Wang, Q.Q.",
TITLE = "Segment Any Motion in Videos",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3406-3416",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218153"}
@inproceedings{bb223051,
AUTHOR = "Gong, S. and Zhuge, Y.Z. and Zhang, L. and Yang, Z.X. and Zhang, P.P. and Lu, H.C.",
TITLE = "The Devil is in Temporal Token: High Quality Video Reasoning
Segmentation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29183-29192",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218154"}
@inproceedings{bb223052,
AUTHOR = "Yuan, Y.Q. and Zhang, H. and Li, W. and Cheng, Z. and Zhang, B.Q. and Li, L. and Li, X. and Zhao, D.L. and Zhang, W.Q. and Zhuang, Y.T. and Zhu, J. and Bing, L.",
TITLE = "VideoRefer Suite: Advancing Spatial-Temporal Object Understanding
with Video LLM",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18970-18980",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218155"}
@inproceedings{bb223053,
AUTHOR = "Lin, L. and Yu, X.Y. and Pang, Z.Q. and Wang, Y.X.",
TITLE = "GLUS: Global-Local Reasoning Unified into A Single Large Language
Model for Video Segmentation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8658-8667",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218156"}
@inproceedings{bb223054,
AUTHOR = "Deng, A.D. and Chen, T.J. and Yu, S. and Yang, T. and Spencer, L. and Tian, Y.P. and Mian, A.S. and Bansal, M. and Chen, C.",
TITLE = "Motion-Grounded Video Reasoning:
Understanding and Perceiving Motion at Pixel Level",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8625-8636",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218157"}
@inproceedings{bb223055,
AUTHOR = "Sarkar, S. and Datta, G. and Kundu, S. and Zheng, K. and Bhattacharyya, C. and Beerel, P.A.",
TITLE = "MaskVD: Region Masking for Efficient Video Object Detection",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "1955-1964",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218158"}
@inproceedings{bb223056,
AUTHOR = "Hashmi, K.A. and Sheikh, T.U. and Stricker, D. and Afzal, M.Z.",
TITLE = "Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for
Video Object Detection",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8122-8133",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218159"}
@inproceedings{bb223057,
AUTHOR = "Shaker, A. and Talal, S. and Danelljan, M. and Khan, S. and Yang, M.H. and Khan, F.S.",
TITLE = "Efficient Video Object Segmentation via Modulated Cross-Attention
Memory",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8681-8690",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218160"}
@inproceedings{bb223058,
AUTHOR = "Ouyang, L.Y. and Liu, R.C. and Huang, Y.F. and Furuta, R. and Sato, Y.",
TITLE = "Actionvos: Actions as Prompts for Video Object Segmentation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "X: 216-235",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218161"}
@inproceedings{bb223059,
AUTHOR = "Ding, S. and Qian, R. and Xu, H.H. and Lin, D. and Xiong, H.K.",
TITLE = "Betrayed by Attention: A Simple yet Effective Approach for
Self-supervised Video Object Segmentation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLV: 215-233",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218162"}
@inproceedings{bb223060,
AUTHOR = "Li, W. and Guo, P. and Zhou, X.Y. and Hong, L. and He, Y.J. and Zheng, X.Y. and Zhang, W. and Zhang, W.Q.",
TITLE = "Onevos: Unifying Video Object Segmentation with All-in-one Transformer
Framework",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVIII: 20-40",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218163"}
@inproceedings{bb223061,
AUTHOR = "Chen, M. and Li, L. and Wang, W.G. and Quan, R.J. and Yang, Y.",
TITLE = "General and Task-oriented Video Segmentation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VII: 72-92",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218164"}
@inproceedings{bb223062,
AUTHOR = "Zhou, Y.K. and Zhang, T. and Ji, S.P. and Yan, S.C. and Li, X.T.",
TITLE = "Improving Video Segmentation via Dynamic Anchor Queries",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "L: 446-463",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218165"}
@inproceedings{bb223063,
AUTHOR = "Yan, S.L. and Xu, X.H. and Zhang, R.R. and Hong, L.Y. and Chen, W.C. and Zhang, W.Q. and Zhang, W.",
TITLE = "Panovos: Bridging Non-panoramic and Panoramic Views with Transformer
for Video Segmentation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "IX: 346-365",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218166"}
@inproceedings{bb223064,
AUTHOR = "Tekchandani, R. and Maheshwari, R. and Hambarde, P. and Tazi, S.N. and Vipparthi, S.K. and Murala, S.",
TITLE = "Luminate: Linguistic Understanding and Multi-Granularity Interaction
for Video Object Segmentation",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "4028-4034",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218167"}
@inproceedings{bb223065,
AUTHOR = "Zhao, Q. and Wu, S.Y. and Zhang, Y.Y. and Sun, X.Y.",
TITLE = "Semantic-Enhanced Point-Box Joint Prompting for Video Object
Segmentation",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "2334-2340",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218168"}
@inproceedings{bb223066,
AUTHOR = "Osman, I. and Shehata, M.S.",
TITLE = "Learn by an Example Transformer for Domain Generalization in Video
Object Segmentation",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "4014-4020",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218169"}
@inproceedings{bb223067,
AUTHOR = "Li, M.H. and Li, S. and Zhang, X.D. and Zhang, L.",
TITLE = "UniVS: Unified and Universal Video Segmentation with Prompts as
Queries",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "3227-3238",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218170"}
@inproceedings{bb223068,
AUTHOR = "He, S.T. and Ding, H.H.",
TITLE = "Decoupling Static and Hierarchical Motion Perception for Referring
Video Segmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13332-13341",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218171"}
@inproceedings{bb223069,
AUTHOR = "Zhou, J. and Pang, Z.Q. and Wang, Y.X.",
TITLE = "RMem: Restricted Memory Banks Improve Video Object Segmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18602-18611",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218172"}
@inproceedings{bb223070,
AUTHOR = "Li, H. and Wang, J. and Yuan, J.H. and Li, Y. and Weng, W.M. and Peng, Y.S. and Zhang, Y.Y. and Xiong, Z.W. and Sun, X.Y.",
TITLE = "Event-Assisted Low-Light Video Object Segmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "3250-3259",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218173"}
@inproceedings{bb223071,
AUTHOR = "Cheng, H.K. and Oh, S.W. and Price, B. and Lee, J.Y. and Schwing, A.",
TITLE = "Putting the Object Back into Video Object Segmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "3151-3161",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218174"}
@inproceedings{bb223072,
AUTHOR = "Wu, Z.W. and Zheng, J. and Ren, X.X. and Vasluianu, F.A. and Ma, C. and Paudel, D.P. and Van Gool, L.J. and Timofte, R.",
TITLE = "Single-Model and Any-Modality for Video Object Tracking",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "19156-19166",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218175"}
@inproceedings{bb223073,
AUTHOR = "Liu, W. and Shen, X. and Li, H. and Bi, X.L. and Liu, B. and Pun, C.M. and Cun, X.D.",
TITLE = "Depth-Aware Test-Time Training for Zero-Shot Video Object
Segmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "19218-19227",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218176"}
@inproceedings{bb223074,
AUTHOR = "Bompani, L. and Rusci, M. and Palossi, D. and Conti, F. and Benini, L.",
TITLE = "Multi-resolution Rescored ByteTrack for Video Object Detection on
Ultra-low-power Embedded Systems",
BOOKTITLE = ECVW24,
YEAR = "2024",
PAGES = "2182-2190",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218177"}
@inproceedings{bb223075,
AUTHOR = "Zhang, X.G. and Chou, C.H.",
TITLE = "Source-free Domain Adaptation for Video Object Detection Under
Adverse Image Conditions",
BOOKTITLE = DEF-AI-MIA24,
YEAR = "2024",
PAGES = "5010-5019",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218178"}
@inproceedings{bb223076,
AUTHOR = "Hu, X. and Hampiholi, B. and Neumann, H. and Lang, J.",
TITLE = "Temporal Context Enhanced Referring Video Object Segmentation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5562-5571",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218179"}
@inproceedings{bb223077,
AUTHOR = "Delatolas, T. and Kalogeiton, V. and Papadopoulos, D.P.",
TITLE = "Learning the What and How of Annotation in Video Object Segmentation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6936-6946",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218180"}
@inproceedings{bb223078,
AUTHOR = "Fedynyak, V. and Romanus, Y. and Hlovatskyi, B. and Sydor, B. and Dobosevych, O. and Babin, I. and Riazantsev, R.",
TITLE = "DeVOS: Flow-Guided Deformable Transformer for Video Object
Segmentation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "239-248",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218181"}
@inproceedings{bb223079,
AUTHOR = "Dang, L.F. and Yang, M. and Yi, K. and Si, B.",
TITLE = "A Moving Object Detection Technology for Intelligent Police Based on
ViBe Algorithm",
BOOKTITLE = CVIDL23,
YEAR = "2023",
PAGES = "667-671",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218182"}
@inproceedings{bb223080,
AUTHOR = "Wu, J.Z.J. and Zhang, D.J. and Hsu, W. and Zhang, M. and Shou, M.Z.",
TITLE = "Label-Efficient Online Continual Object Detection in Streaming Video",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "19189-19198",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218183"}
@inproceedings{bb223081,
AUTHOR = "Li, X. and Wang, J.L. and Xu, X.H. and Li, X. and Raj, B. and Lu, Y.",
TITLE = "Robust Referring Video Object Segmentation with Cyclic Structural
Consensus",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22179-22188",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218184"}
@inproceedings{bb223082,
AUTHOR = "Yoo, J.S. and Lee, H. and Jung, S.W.",
TITLE = "Hierarchical Spatiotemporal Transformers for Video Object
Segmentation",
BOOKTITLE = NIVT23,
YEAR = "2023",
PAGES = "795-805",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218185"}
@inproceedings{bb223083,
AUTHOR = "Liu, N. and Nan, K. and Zhao, W.B. and Liu, Y.W. and Yao, X. and Khan, S. and Cholakkal, H. and Anwer, R.M. and Han, J.W. and Khan, F.S.",
TITLE = "Multi-grained Temporal Prototype Learning for Few-shot Video Object
Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "18816-18825",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218186"}
@inproceedings{bb223084,
AUTHOR = "Tang, J.J. and Zheng, G. and Yang, S.",
TITLE = "Temporal Collection and Distribution for Referring Video Object
Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15420-15430",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218187"}
@inproceedings{bb223085,
AUTHOR = "Wu, Q.Q. and Yang, T.Y. and Wu, W. and Chan, A.B.",
TITLE = "Scalable Video Object Segmentation with Simplified Framework",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13833-13843",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218188"}
@inproceedings{bb223086,
AUTHOR = "Deng, C.R. and Chen, D. and Wu, Q.",
TITLE = "Identity-Consistent Aggregation for Video Object Detection",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13388-13398",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218189"}
@inproceedings{bb223087,
AUTHOR = "Yoo, J.S. and Lee, H. and Jung, S.W.",
TITLE = "Video Object Segmentation-aware Video Frame Interpolation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "12288-12299",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218190"}
@inproceedings{bb223088,
AUTHOR = "Liu, X. and Nejadasl, F.K. and van Gemert, J.C. and Booij, O. and Pintea, S.L.",
TITLE = "Objects do not disappear: Video object detection by single-frame
object location anticipation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "6927-6938",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218191"}
@inproceedings{bb223089,
AUTHOR = "Wu, D.M. and Wang, T. and Zhang, Y. and Zhang, X.Y. and Shen, J.B.",
TITLE = "OnlineRefer: A Simple Online Baseline for Referring Video Object
Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2749-2758",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218192"}
@inproceedings{bb223090,
AUTHOR = "Sun, R. and Wang, Y. and Mai, H.Y. and Zhang, T.Z. and Wu, F.",
TITLE = "Alignment Before Aggregation: Trajectory Memory Retrieval Network for
Video Object Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "1218-1228",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218193"}
@inproceedings{bb223091,
AUTHOR = "Miao, B. and Bennamoun, M. and Gao, Y.S. and Mian, A.",
TITLE = "Spectrum-guided Multi-granularity Referring Video Object Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "920-930",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218194"}
@inproceedings{bb223092,
AUTHOR = "Han, M.F. and Wang, Y. and Li, Z.H. and Yao, L. and Chang, X.J. and Qiao, Y.",
TITLE = "HTML: Hybrid Temporal-scale Multimodal Learning Framework for
Referring Video Object Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13368-13377",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218195"}
@inproceedings{bb223093,
AUTHOR = "Dubuisson, I. and Muselet, D. and Ducottet, C. and Lang, J.",
TITLE = "Fast Context Adaptation for Video Object Segmentation",
BOOKTITLE = CAIP23,
YEAR = "2023",
PAGES = "I:273-283",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218196"}
@inproceedings{bb223094,
AUTHOR = "Skartados, E. and Georgiadis, K. and Yucel, M.K. and Ioannis, K. and Domi, A. and Drosou, A. and Manganelli, B. and Saa Garriga, A.",
TITLE = "TRICKVOS: A Bag of Tricks for Video Object Segmentation",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "2430-2434",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218197"}
@inproceedings{bb223095,
AUTHOR = "Jo, J. and Wee, D.Y. and Cho, N.I.",
TITLE = "OCVOS: Object-Centric Representation for Video Object Segmentation",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1655-1659",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218198"}
@inproceedings{bb223096,
AUTHOR = "Gao, Q.Q. and Zhong, W. and Li, J. and Zhao, T.J.",
TITLE = "Leveraging Visual Prompts To Guide Language Modeling for Referring
Video Object Segmentation",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "685-689",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218199"}
@inproceedings{bb223097,
AUTHOR = "Zhang, Y.S. and Robinson, A. and Magnusson, M. and Felsberg, M.",
TITLE = "Leveraging Optical Flow Features for Higher Generalization Power in
Video Object Segmentation",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "326-330",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218200"}
@inproceedings{bb223098,
AUTHOR = "Li, L. and Wang, W.G. and Zhou, T.F. and Li, J. and Yang, Y.",
TITLE = "Unified Mask Embedding and Correspondence Learning for
Self-Supervised Video Segmentation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18706-18716",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218201"}
@inproceedings{bb223099,
AUTHOR = "Athar, A. and Hermans, A. and Luiten, J. and Ramanan, D. and Leibe, B.",
TITLE = "TarViS: A Unified Approach for Target-Based Video Segmentation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18738-18748",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-i762vose4.html#TT218202"}
Last update:Mar 28, 2026 at 17:09:41