{"total":28,"rows":[{"id":"2601.05244","title":"GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation","created":"2026-01-08","cited_by_count":6,"area":null},{"id":"2605.18018","title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.20110","title":"SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction","created":"2026-05-19","cited_by_count":2,"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":"2603.14022","title":"A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2603.23126","title":"3rd Place of MeViS-Audio Track of the 5th PVUW: VIRST-Audio","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.00404","title":"The 1st Winner for 5th PVUW MeViS-Text Challenge: Strong MLLMs Meet SAM3 for Referring Video Object Segmentation","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.23935","title":"2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2604.26031","title":"Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2601.12076","title":"CroBIM-V: Memory-Quality Controlled Remote Sensing Referring Video Object Segmentation","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2603.13904","title":"Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.23788","title":"Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.27241","title":"SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.02860","title":"A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.22836","title":"AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.22837","title":"OAMVOS:2nd Report for 5th PVUW MOSE Track","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.17584","title":"VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.27339","title":"SAM2Matting: Generalized Image and Video Matting","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.02497","title":"Seek to Segment: Active Perception for Panoramic Referring Segmentation","created":"2026-07-02","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":"2608.09475","title":"Agreement-Based Audio-Visual Segmentation:Champion Report for the MeViS-Audio Track in the 8th LSVOS Challenge","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.12721","title":"VOS-Agent: The 1st Place Solution for the 8th LSVOS Challenge (MOSEv2 Track)","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.17279","title":"Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS Challenge","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.22337","title":"Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.06078","title":"Report of the 8th LSVOS Challenge: Complex and Multimodal Video Object Segmentation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.19451","title":"Efficient Unified Multimodal Understanding (EUMU): Winning Solution for the MUMU Track at the 8th LSVOS Challenge","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.23067","title":"LD-RSVIS: A Large-Scale and Diverse Benchmark for Referring Surgical Video Instrument Segmentation","created":"2026-09-19","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}],"next_cursor":null}