{"total":24,"rows":[{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2411.15539","title":"Large Language Model with Region-guided Referring and Grounding for CT Report Generation","created":"2024-11-23","cited_by_count":28,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"area":null},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22,"area":null},{"id":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2512.20013","title":"SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images","created":"2025-12-23","cited_by_count":10,"area":null},{"id":"2505.02830","title":"AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation","created":"2025-05-05","cited_by_count":8,"area":null},{"id":"2411.11507","title":"SignEye: Traffic Sign Interpretation from Vehicle First-Person View","created":"2024-11-18","cited_by_count":5,"area":null},{"id":"2405.16071","title":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2510.02898","title":"One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2602.02220","title":"LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation","created":"2026-02-02","cited_by_count":2,"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":"2505.24466","title":"SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2509.01209","title":"Measuring Image-Relation Alignment: Reference-Free Evaluation of VLMs and Synthetic Pre-training for Open-Vocabulary Scene Graph Generation","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2606.29531","title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2507.16623","title":"Automatic Fine-grained Segmentation-assisted Report Generation","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2509.06335","title":"Harnessing Object Grounding for Time-Sensitive Video Understanding","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2510.07319","title":"Temporal Prompting Matters: Rethinking Referring Video Object Segmentation","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2603.01603","title":"Sparse View Distractor-Free Gaussian Splatting","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2605.12074","title":"BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.25445","title":"C3-Bench: A Context-Aware Change Captioning Benchmark","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.02025","title":"Evaluating Vision-Language Models as a Zero-Shot Learning Alternative to You Only Look Once and Optical Character Recognition for Nigerian License Plate Recognition","created":"2026-07-02","cited_by_count":0,"area":null}],"next_cursor":null}