{"total":188,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863,"area":null},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315,"area":"lr"},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277,"area":null},{"id":"2501.04001","title":"Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos","created":"2025-01-07","cited_by_count":159,"area":"mllm"},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2502.20900","title":"DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping","created":"2025-02-28","cited_by_count":89,"area":"vla"},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"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,"area":null},{"id":"2410.11792","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","created":"2024-10-15","cited_by_count":67,"area":null},{"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":"2405.20321","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","created":"2024-05-30","cited_by_count":50,"area":null},{"id":"2408.07931","title":"Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning","created":"2024-08-15","cited_by_count":47,"area":null},{"id":"2408.00756","title":"Segment anything model 2: an application to 2D and 3D medical images","created":"2024-08-01","cited_by_count":28,"area":null},{"id":"2402.18115","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","created":"2024-02-28","cited_by_count":27,"area":null},{"id":"2504.17788","title":"Dynamic Camera Poses and Where to Find Them","created":"2025-04-24","cited_by_count":27,"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":"2501.14677","title":"MatAnyone: Stable Video Matting with Consistent Memory Propagation","created":"2025-01-24","cited_by_count":24,"area":null},{"id":"2312.15715","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","created":"2023-12-25","cited_by_count":22,"area":null},{"id":"2406.08476","title":"RMem: Restricted Memory Banks Improve Video Object Segmentation","created":"2024-06-12","cited_by_count":22,"area":null},{"id":"2411.18933","title":"Efficient Track Anything","created":"2024-11-28","cited_by_count":21,"area":null},{"id":"2501.07256","title":"EdgeTAM: On-Device Track Anything Model","created":"2025-01-13","cited_by_count":21,"area":null},{"id":"2511.16661","title":"Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations","created":"2025-11-20","cited_by_count":19,"area":null},{"id":"2412.09754","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","created":"2024-12-12","cited_by_count":17,"area":"mllm"},{"id":"2508.05506","title":"MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips","created":"2025-08-07","cited_by_count":17,"area":"diffusion"},{"id":"2407.00451","title":"Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulation","created":"2024-06-29","cited_by_count":14,"area":"diffusion"},{"id":"2412.00155","title":"T-3DGS: Removing Transient Objects for 3D Scene Reconstruction","created":"2024-11-29","cited_by_count":13,"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":"2406.17005","title":"PVUW 2024 Challenge on Complex Video Understanding: Methods and Results","created":"2024-06-24","cited_by_count":12,"area":null},{"id":"2411.11002","title":"Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation","created":"2024-11-17","cited_by_count":12,"area":null},{"id":"2411.11409","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2406.10078","title":"D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2501.16443","title":"Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"wm"},{"id":"2512.22519","title":"Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding","created":"2025-12-27","cited_by_count":10,"area":"mllm"},{"id":"2412.09122","title":"LVMark: Robust Watermark for Latent Video Diffusion Models","created":"2024-12-12","cited_by_count":9,"area":"diffusion"},{"id":"2505.18561","title":"CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2409.05847","title":"LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation","created":"2024-09-09","cited_by_count":8,"area":null},{"id":"2410.00231","title":"Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2501.05439","title":"From Simple to Complex Skills: The Case of In-Hand Object Reorientation","created":"2025-01-09","cited_by_count":8,"area":null},{"id":"2506.01304","title":"SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2512.08406","title":"SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2407.07760","title":"Learning Spatial-Semantic Features for Robust Video Object Segmentation","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2411.02818","title":"LiVOS: Light Video Object Segmentation with Gated Linear Matching","created":"2024-11-05","cited_by_count":7,"area":null},{"id":"2501.13667","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","created":"2025-01-23","cited_by_count":7,"area":null},{"id":"2505.23617","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2510.10524","title":"Unified Open-World Segmentation with Multi-Modal Prompts","created":"2025-10-12","cited_by_count":7,"area":null},{"id":"2403.04924","title":"$\\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2412.01410","title":"CellSeg1: Robust Cell Segmentation with One Training Image","created":"2024-12-02","cited_by_count":6,"area":null},{"id":"2506.01373","title":"No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and Beyond","created":"2025-06-02","cited_by_count":6,"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":"2507.22061","title":"MOVE: Motion-Guided Few-Shot Video Object Segmentation","created":"2025-07-29","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":"2505.01854","title":"Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2","created":"2025-05-03","cited_by_count":5,"area":null},{"id":"2511.16937","title":"OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2312.08514","title":"TAM-VT: Transformation-Aware Multi-scale Video Transformer for Segmentation and Tracking","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2408.00169","title":"Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation","created":"2024-07-31","cited_by_count":4,"area":null},{"id":"2504.05468","title":"Studying Image Diffusion Features for Zero-Shot Video Object Segmentation","created":"2025-04-07","cited_by_count":4,"area":"diffusion"},{"id":"2510.14902","title":"VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation","created":"2025-10-16","cited_by_count":4,"area":"vla"},{"id":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2408.10125","title":"Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2408.10129","title":"UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2410.00386","title":"Seamless Augmented Reality Integration in Arthroscopy: A Pipeline for Articular Reconstruction and Guidance","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2503.03492","title":"Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2503.06471","title":"Online Dense Point Tracking with Streaming Memory","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2504.05178","title":"The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation","created":"2025-04-07","cited_by_count":3,"area":"mllm"},{"id":"2508.21809","title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2509.25594","title":"K-Prism: A Knowledge-Guided and Prompt Integrated Universal Medical Image Segmentation Model","created":"2025-09-29","cited_by_count":3,"area":"moe"},{"id":"2511.04678","title":"Tracking and Understanding Object Transformations","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2512.21333","title":"Fast SAM2 with Text-Driven Token Pruning","created":"2025-12-24","cited_by_count":3,"area":"inference"},{"id":"2604.22238","title":"CodeGraphVLP: Code-as-Planner Meets Semantic-Graph State for Non-Markovian Vision-Language-Action Models","created":"2026-04-24","cited_by_count":3,"area":"vla"},{"id":"2312.00778","title":"MorpheuS: Neural Dynamic 360{\\deg} Surface Reconstruction from Monocular RGB-D Video","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2406.07043","title":"1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2408.10469","title":"LSVOS Challenge 3rd Place Report: SAM2 and Cutie based VOS","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2410.12214","title":"Order-aware Interactive Segmentation","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2410.23191","title":"Continuous Spatio-Temporal Memory Networks for 4D Cardiac Cine MRI Segmentation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2412.16742","title":"EasyVis2: A Real Time Multi-view 3D Visualization System for Laparoscopic Surgery Training Enhanced by a Deep Neural Network YOLOv8-Pose","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2503.00695","title":"MoSFormer: Augmenting Temporal Context with Memory of Surgery for Surgical Phase Recognition","created":"2025-03-02","cited_by_count":2,"area":null},{"id":"2506.05543","title":"FRAME: Pre-Training Video Feature Representations via Anticipation and Memory","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2506.13552","title":"A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2508.07066","title":"Membership Inference Attacks with False Discovery Rate Control","created":"2025-08-09","cited_by_count":2,"area":"safety"},{"id":"2508.08612","title":"Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation","created":"2025-08-12","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":"2509.24804","title":"DyMoDreamer: World Modeling with Dynamic Modulation","created":"2025-09-29","cited_by_count":2,"area":"wm"},{"id":"2511.01427","title":"UniSOT: A Unified Framework for Multi-Modality Single Object Tracking","created":"2025-11-03","cited_by_count":2,"area":null},{"id":"2602.13197","title":"Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos","created":"2026-02-13","cited_by_count":2,"area":null},{"id":"2609.05416","title":"WorldSculpt: Generating Compositional Worlds from Grounded Videos","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2403.18690","title":"Annolid: Annotate, Segment, and Track Anything You Need","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2406.03668","title":"3rd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2406.04600","title":"1st Place Solution for MOSE Track in CVPR 2024 PVUW Workshop: Complex Video Object Segmentation","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2406.08192","title":"2nd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2408.16431","title":"Discriminative Spatial-Semantic VOS Solution: 1st Place Solution for 6th LSVOS","created":"2024-08-29","cited_by_count":1,"area":null},{"id":"2409.14220","title":"Temporally Propagated Masks and Bounding Boxes: Combining the Best of Both Worlds for Multi-Object Tracking","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2410.22451","title":"Addressing Issues with Working Memory in Video Object Segmentation","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2411.02482","title":"NeRF-Aug: Data Augmentation for Robotics with Neural Radiance Fields","created":"2024-11-04","cited_by_count":1,"area":null},{"id":"2503.23509","title":"ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025","created":"2025-03-30","cited_by_count":1,"area":null},{"id":"2504.03041","title":"VIP: Video Inpainting Pipeline for Real World Human Removal","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2505.00295","title":"Fine-grained spatial-temporal perception for gas leak segmentation","created":"2025-05-01","cited_by_count":1,"area":null},{"id":"2507.00339","title":"Training for X-Ray Vision: Amodal Segmentation, Amodal Content Completion, and View-Invariant Object Representation from Multi-Camera Video","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2507.07838","title":"3D-ADAM: A Dataset for 3D Anomaly Detection in Additive Manufacturing","created":"2025-07-10","cited_by_count":1,"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}],"next_cursor":"100"}