{"total":37,"rows":[{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97,"area":null},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97,"area":null},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2407.13761","title":"SegPoint: Segment Any Point Cloud via Large Language Model","created":"2024-07-18","cited_by_count":35,"area":null},{"id":"2407.12435","title":"F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions","created":"2024-07-17","cited_by_count":24,"area":null},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2410.05963","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","created":"2024-10-08","cited_by_count":16,"area":null},{"id":"2410.09909","title":"UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation","created":"2024-10-13","cited_by_count":14,"area":null},{"id":"2507.20025","title":"Region-based Cluster Discrimination for Visual Representation Learning","created":"2025-07-26","cited_by_count":13,"area":null},{"id":"2502.20678","title":"STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2504.13621","title":"Visual Intention Grounding for Egocentric Assistants","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2508.00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","created":"2025-08-01","cited_by_count":11,"area":null},{"id":"2506.23088","title":"Where, What, Why: Towards Explainable Driver Attention Prediction","created":"2025-06-29","cited_by_count":10,"area":null},{"id":"2411.18671","title":"TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video","created":"2024-11-27","cited_by_count":8,"area":null},{"id":"2512.05941","title":"Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding","created":"2025-12-05","cited_by_count":8,"area":null},{"id":"2502.20104","title":"New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2404.06212","title":"OmniFusion Technical Report","created":"2024-04-09","cited_by_count":6,"area":null},{"id":"2505.18986","title":"VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion","created":"2025-05-25","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2411.16196","title":"Learn from Foundation Model: Fruit Detection Model without Manual Annotation","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2503.10781","title":"Large-scale Pre-training for Grounded Video Caption Generation","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2504.02876","title":"Multimodal Reference Visual Grounding","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2507.14899","title":"InsightX Agent: An LMM-based Agentic Framework with Integrated Tools for Reliable X-ray NDT Analysis","created":"2025-07-20","cited_by_count":3,"area":null},{"id":"2510.14904","title":"CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2510.26781","title":"ChartAB: A Benchmark for Chart Grounding & Dense Alignment","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2603.26646","title":"Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2408.02336","title":"Infusing Environmental Captions for Long-Form Video Language Grounding","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2411.07584","title":"Grounded Video Caption Generation","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2603.14012","title":"Multi-Grained Vision-Language Alignment for Domain Generalized Person Re-Identification","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.16931","title":"Script-to-Slide Grounding: Grounding Script Sentences to Slide Objects for Automatic Instructional Video Generation","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.23173","title":"One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2607.08267","title":"UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagery","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.21543","title":"presto: Efficient, Training-free, and Open-world Object Placement via Imaginary Search","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.19143","title":"PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.39601","title":"GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}