{"list":"other","total":52,"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","created":"2024-03-14","cited_by_count":328},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"2411.16537","title":"RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics","created":"2024-11-25","cited_by_count":136},{"id":"2012.00726","title":"RAFT-3D: Scene Flow using Rigid-Motion Embeddings","created":"2020-12-01","cited_by_count":122},{"id":"2504.13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins","created":"2025-04-17","cited_by_count":121},{"id":"1604.03670","title":"Interactive Perception: Leveraging Action in Perception and Perception in Action","created":"2016-04-13","cited_by_count":78},{"id":"2007.15157","title":"Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation","created":"2020-07-30","cited_by_count":64},{"id":"2207.02206","title":"Segmenting Moving Objects via an Object-Centric Layered Representation","created":"2022-07-05","cited_by_count":63},{"id":"2404.04808","title":"MemFlow: Optical Flow Estimation and Prediction with Memory","created":"2024-04-07","cited_by_count":55},{"id":"2503.03734","title":"OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction","created":"2025-03-05","cited_by_count":54},{"id":"1902.03715","title":"Towards Segmenting Anything That Moves","created":"2019-02-11","cited_by_count":51},{"id":"2508.19958","title":"Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation","created":"2025-08-27","cited_by_count":48},{"id":"2101.06605","title":"MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization","created":"2021-01-17","cited_by_count":46},{"id":"2503.07135","title":"VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation","created":"2025-03-10","cited_by_count":46},{"id":"2503.07465","title":"YOLOE: Real-Time Seeing Anything","created":"2025-03-10","cited_by_count":36},{"id":"2503.22268","title":"Segment Any Motion in Videos","created":"2025-03-28","cited_by_count":35},{"id":"2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","created":"2025-05-26","cited_by_count":33},{"id":"1812.02772","title":"Object Discovery in Videos as Foreground Motion Clustering","created":"2018-12-06","cited_by_count":32},{"id":"2508.04655","title":"X-SAM: From Segment Anything to Any Segmentation","created":"2025-08-06","cited_by_count":30},{"id":"2504.08541","title":"Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset","created":"2025-04-11","cited_by_count":29},{"id":"1804.05195","title":"Motion-based Object Segmentation based on Dense RGB-D Scene Flow","created":"2018-04-14","cited_by_count":18},{"id":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11},{"id":"2509.21986","title":"Developing Vision-Language-Action Model from Egocentric Videos","created":"2025-09-26","cited_by_count":11},{"id":"2302.03793","title":"Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction","created":"2023-02-07","cited_by_count":10},{"id":"2306.05584","title":"Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation","created":"2023-06-08","cited_by_count":7},{"id":"2506.22718","title":"Part Segmentation and Motion Estimation for Articulated Objects with Dynamic 3D Gaussians","created":"2025-06-28","cited_by_count":5},{"id":"2403.01731","title":"RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features","created":"2024-03-04","cited_by_count":4},{"id":"2507.10776","title":"rt-RISeg: Real-Time Model-Free Robot Interactive Segmentation for Active Instance-Level Object Understanding","created":"2025-07-14","cited_by_count":1},{"id":"2509.02807","title":"PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?","created":"2025-09-02","cited_by_count":1}],"next_cursor":null}