{"total":94,"rows":[{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864,"area":"wm"},{"id":"2507.01925","title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","created":"2025-07-02","cited_by_count":96,"area":"vla"},{"id":"2411.17576","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","created":"2024-11-26","cited_by_count":66,"area":null},{"id":"2508.05630","title":"MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes","created":"2025-08-07","cited_by_count":62,"area":null},{"id":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61,"area":null},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"area":null},{"id":"2501.02341","title":"UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility","created":"2025-01-04","cited_by_count":49,"area":"agents"},{"id":"2504.07962","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","created":"2025-04-10","cited_by_count":34,"area":"lr"},{"id":"2505.05800","title":"3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks","created":"2025-05-09","cited_by_count":31,"area":"vla"},{"id":"2503.07098","title":"OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation","created":"2025-03-10","cited_by_count":28,"area":null},{"id":"2507.15852","title":"Advancing Complex Video Object Segmentation via Progressive Concept Construction","created":"2025-07-21","cited_by_count":26,"area":null},{"id":"2601.01528","title":"DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving","created":"2026-01-04","cited_by_count":21,"area":"wm"},{"id":"2504.04519","title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","created":"2025-04-06","cited_by_count":17,"area":null},{"id":"2508.13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts","created":"2025-08-18","cited_by_count":15,"area":null},{"id":"2503.12781","title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","created":"2025-03-17","cited_by_count":13,"area":null},{"id":"2505.18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2512.05905","title":"SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations","created":"2025-12-05","cited_by_count":13,"area":null},{"id":"2506.15368","title":"Open-World Object Counting in Videos","created":"2025-06-18","cited_by_count":11,"area":null},{"id":"2502.11594","title":"iMOVE: Instance-Motion-Aware Video Understanding","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2503.06700","title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","created":"2025-03-09","cited_by_count":10,"area":null},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2602.03595","title":"Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation","created":"2026-02-03","cited_by_count":9,"area":"lr"},{"id":"2503.22204","title":"Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting","created":"2025-03-28","cited_by_count":8,"area":null},{"id":"2604.03305","title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","created":"2026-03-31","cited_by_count":7,"area":null},{"id":"2507.07603","title":"HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Tracking","created":"2025-07-10","cited_by_count":6,"area":null},{"id":"2505.00739","title":"MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2507.21732","title":"SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2601.07290","title":"VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2509.12047","title":"A Computer Vision Pipeline for Individual-Level Behavior Analysis: Benchmarking on the Edinburgh Pig Dataset","created":"2025-09-15","cited_by_count":4,"area":null},{"id":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2505.07071","title":"Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution","created":"2025-05-11","cited_by_count":3,"area":"diffusion"},{"id":"2507.08548","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","created":"2025-07-11","cited_by_count":3,"area":"deeprl"},{"id":"2511.04678","title":"Tracking and Understanding Object Transformations","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2511.13715","title":"Segment Anything Across Shots: A Method and Benchmark","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2507.14613","title":"Depthwise-Dilated Convolutional Adapters for Medical Object Tracking and Segmentation Using the Segment Anything Model 2","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2509.00385","title":"HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization","created":"2025-08-30","cited_by_count":2,"area":null},{"id":"2509.13864","title":"Distractor-Aware Memory-Based Visual Object Tracking","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2602.03137","title":"FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.08224","title":"Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2603.10125","title":"4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2605.02638","title":"ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2605.22538","title":"Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2507.16015","title":"Is Tracking really more challenging in First Person Egocentric Vision?","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2508.11531","title":"Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2510.11417","title":"Robust Ego-Exo Correspondence with Long-Term Memory","created":"2025-10-13","cited_by_count":1,"area":"moe"},{"id":"2510.18822","title":"SAM 2++: Tracking Anything at Any Granularity","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2511.16618","title":"SurgSLOT: Segment Anything in Surgical Videos via Semantic Long-term Tracking","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2511.22950","title":"RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2512.22624","title":"Rethinking Memory Design in SAM-Based Visual Object Tracking","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2601.04798","title":"Detector-Augmented SAMURAI for Long-Duration Drone Tracking","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.09699","title":"SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM3","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2602.11183","title":"Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.19380","title":"Detector-in-the-Loop Tracking: Active Memory Rectification for Stable Glottic Opening Localization","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2603.26929","title":"Live Interactive Training for Video Segmentation","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2606.15320","title":"Conditional Multi-Event Temporal Grounding in Long-Form Video","created":"2026-06-13","cited_by_count":1,"area":"mllm"},{"id":"2412.01119","title":"Object Tracking in a $360^o$ View: A Novel Perspective on Bridging the Gap to Biomedical Advancements","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2503.00042","title":"An Analysis of Data Transformation Effects on Segment Anything 2","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.01907","title":"Technical Report for ReID-SAM on SkiTB Visual Tracking Challenge 2025","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2505.18111","title":"Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.06748","title":"THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2506.07850","title":"SAM2Auto: Auto Annotation Using FLASH","created":"2025-06-09","cited_by_count":0,"area":"mllm"},{"id":"2508.01752","title":"Vision transformer-based multi-camera multi-object tracking framework for dairy cow monitoring","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2508.19705","title":"FreeVPS: Repurposing Training-Free SAM2 for Generalizable Video Polyp Segmentation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.04735","title":"Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2509.17500","title":"SAMSON: 3rd Place Solution of LSVOS 2025 VOS Challenge","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2509.19183","title":"The 1st Solution for MOSEv2 Challenge 2025: Long-term and Concept-aware Video Segmentation via SeC","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2509.23838","title":"2nd Place Report of MOSEv2 Challenge 2025: Concept Guided Video Object Segmentation via SeC","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2511.02591","title":"Zero-Shot Multi-Animal Tracking in the Wild","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2511.18264","title":"SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.08467","title":"Team-Aware Football Player Tracking with SAM: An Appearance-Based Approach to Occlusion Recovery","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.09633","title":"Benchmarking SAM2-based Trackers on FMOX","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.16880","title":"ReMeDI: Refined Memory for Disambiguation of Identities with SAM3 in Surgical Segmentation","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.18006","title":"MUOT_3M: A 3 Million Frame Multimodal Underwater Benchmark and the MUTrack Tracking Method","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.05463","title":"EdgeDAM: Real-time Object Tracking for Mobile Devices","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.14300","title":"Show Me When and Where: Towards Referring Video Object Segmentation in the Wild","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.15415","title":"AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.20887","title":"Scene Graph-guided SegCaptioning Transformer with Fine-grained Alignment for Controllable Video Segmentation and Captioning","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2603.21387","title":"Knowledge Priors for Identity-Disentangled Open-Set Privacy-Preserving Video FER","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.01974","title":"Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.03426","title":"Automated Segmentation and Tracking of Group Housed Pigs Using Foundation Models","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.04016","title":"HOIGS: Human-Object Interaction Gaussian Splatting","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.06671","title":"4D Vessel Reconstruction for Benchtop Thrombectomy Analysis","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2606.27655","title":"Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.29861","title":"SUMO: Segment and Track Any Motion with Nonlinear State Space Models","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.08688","title":"SAM-MT: Real-Time Interactive Multi-Target Video Segmentation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.19743","title":"Efficient Tracking and Understanding Object Transformations","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.19811","title":"Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.03912","title":"StreamDAM: Presence-Aware Memory for Real-Time Streaming Video Object Segmentation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.18640","title":"SAM2Dual: Training-Free, Dual Memory for Long-Term Video Object Segmentation","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.03756","title":"ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.06221","title":"RefGuard: Identity-Aware Language-Guided Robot Manipulation via Joint Target-Anchor-Frame Grounding","created":"2026-09-05","cited_by_count":0,"area":"vla"},{"id":"2609.28078","title":"LiAM-SAM: Lifecycle-Aware Memory for Robust SAM2-Based MOT","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.02946","title":"When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.15929","title":"When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}