{"list":"other","total":72,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"1703.05884","title":"Need for Speed: A Benchmark for Higher Frame Rate Object Tracking","created":"2017-03-17","cited_by_count":137},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125},{"id":"2411.11922","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","created":"2024-11-18","cited_by_count":94},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93},{"id":"2303.16580","title":"Generalized Relation Modeling for Transformer Tracking","created":"2023-03-29","cited_by_count":93},{"id":"1811.05804","title":"Creatures great and SMAL: Recovering the shape and motion of animals from video","created":"2018-11-14","cited_by_count":84},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81},{"id":"2308.05140","title":"Robust Object Modeling for Visual Tracking","created":"2023-08-09","cited_by_count":80},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80},{"id":"2410.16268","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","created":"2024-10-21","cited_by_count":80},{"id":"2211.10181","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","created":"2022-11-18","cited_by_count":77},{"id":"2311.02072","title":"HIPTrack: Visual Tracking with Historical Prompts","created":"2023-11-03","cited_by_count":71},{"id":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66},{"id":"2411.17576","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","created":"2024-11-26","cited_by_count":66},{"id":"2107.02156","title":"Do Different Tracking Tasks Require Different Appearance Models?","created":"2021-07-05","cited_by_count":62},{"id":"2312.17133","title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","created":"2023-12-28","cited_by_count":59},{"id":"2211.09808","title":"Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks","created":"2022-11-17","cited_by_count":57},{"id":"2412.19138","title":"SUTrack: Towards Simple and Unified Single Object Tracking","created":"2024-12-26","cited_by_count":52},{"id":"2212.06200","title":"Breaking the \"Object\" in Video Object Segmentation","created":"2022-12-12","cited_by_count":49},{"id":"2403.13042","title":"TAPTR: Tracking Any Point with Transformers as Detection","created":"2024-03-19","cited_by_count":45},{"id":"2404.19326","title":"LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation","created":"2024-04-30","cited_by_count":44},{"id":"2411.17646","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","created":"2024-11-26","cited_by_count":44},{"id":"2503.22268","title":"Segment Any Motion in Videos","created":"2025-03-28","cited_by_count":35},{"id":"2402.03631","title":"CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model","created":"2024-02-06","cited_by_count":27},{"id":"2403.03493","title":"VastTrack: Vast Category Visual Object Tracking","created":"2024-03-06","cited_by_count":26},{"id":"1506.03011","title":"Learning to Linearize Under Uncertainty","created":"2015-06-09","cited_by_count":25},{"id":"2411.18933","title":"Efficient Track Anything","created":"2024-11-28","cited_by_count":21},{"id":"2501.07256","title":"EdgeTAM: On-Device Track Anything Model","created":"2025-01-13","cited_by_count":21},{"id":"2501.18487","title":"Track-On: Transformer-based Online Point Tracking with Memory","created":"2025-01-30","cited_by_count":21},{"id":"2502.06756","title":"SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement","created":"2025-02-10","cited_by_count":20},{"id":"2303.12079","title":"OmniTracker: Unifying Object Tracking by Tracking-with-Detection","created":"2023-03-21","cited_by_count":19},{"id":"2408.15876","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation","created":"2024-08-28","cited_by_count":19},{"id":"2403.08682","title":"OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework","created":"2024-03-13","cited_by_count":6},{"id":"2308.13266","title":"Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation","created":"2023-08-25","cited_by_count":5}],"next_cursor":null}