{"total":17,"rows":[{"id":"2301.00805","title":"Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation","created":"2023-01-02","cited_by_count":28,"area":null},{"id":"2210.03416","title":"Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding","created":"2022-10-07","cited_by_count":26,"area":null},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2301.03160","title":"Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network","created":"2023-01-09","cited_by_count":13,"area":null},{"id":"2402.02555","title":"High-Quality Entity Segmentation and Grounding","created":"2024-02-04","cited_by_count":13,"area":null},{"id":"2208.05647","title":"PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding","created":"2022-08-11","cited_by_count":12,"area":null},{"id":"2310.10975","title":"NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning","created":"2023-10-17","cited_by_count":8,"area":null},{"id":"2311.01091","title":"Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding","created":"2023-11-02","cited_by_count":6,"area":null},{"id":"2310.16616","title":"Context Does Matter: End-to-end Panoptic Narrative Grounding with Deformable Attention Refined Matching Network","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2402.05917","title":"Point-VOS: Pointing Up Video Object Segmentation","created":"2024-02-08","cited_by_count":5,"area":null},{"id":"2310.18142","title":"Semi-Supervised Panoptic Narrative Grounding","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2502.13898","title":"GroundCap: A Visually Grounded Image Captioning Dataset","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2501.04184","title":"MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2201.05026","title":"Fantastic Data and How to Query Them","created":"2022-01-13","cited_by_count":1,"area":null},{"id":"2603.02896","title":"3D-DRES: Detailed 3D Referring Expression Segmentation","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2609.19143","title":"PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}