{"total":33,"rows":[{"id":"2512.07826","title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","created":"2025-12-08","cited_by_count":53,"area":null},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"area":null},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2511.21025","title":"CaptionQA: Is Your Caption as Useful as the Image Itself?","created":"2025-11-26","cited_by_count":15,"area":null},{"id":"2512.12309","title":"WeDetect: Fast Open-Vocabulary Object Detection as Retrieval","created":"2025-12-13","cited_by_count":14,"area":null},{"id":"2507.19599","title":"Object-centric Video Question Answering with Visual Grounding and Referring","created":"2025-07-25","cited_by_count":13,"area":null},{"id":"2505.05517","title":"Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2505.15877","title":"Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2507.13861","title":"PositionIC: Unified Position and Identity Consistency for Image Customization","created":"2025-07-18","cited_by_count":4,"area":null},{"id":"2510.27680","title":"PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting","created":"2025-10-31","cited_by_count":4,"area":null},{"id":"2602.23543","title":"Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2606.08277","title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2509.26604","title":"Video Object Segmentation-Aware Audio Generation","created":"2025-09-30","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":"2509.17022","title":"VAInpaint: Zero-Shot Video-Audio inpainting framework with LLMs-driven Module","created":"2025-09-21","cited_by_count":1,"area":null},{"id":"2510.12126","title":"MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2603.12533","title":"Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2603.13397","title":"TennisExpert: Towards Expert-Level Analytical Sports Video Understanding","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.21343","title":"OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2607.13245","title":"Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2506.05673","title":"Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2512.00489","title":"Learning What Helps: Task-Aligned Context Selection for Vision Tasks","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2602.01753","title":"ObjEmbed: Towards Universal Multimodal Object Embeddings","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.06474","title":"LAB-Det: Language as a Domain-Invariant Bridge for Training-Free One-Shot Domain Generalization in Object Detection","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2604.01907","title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.16903","title":"WOW-Seg: A Word-free Open World Segmentation Model","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.29879","title":"DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.02805","title":"A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.30584","title":"Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.21400","title":"A Scene Language Model for Open-Vocabulary Scene Mapping","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.28184","title":"VLMs Can Describe, But Not Measure: Object-Centric Scene Understanding for Robotic Manipulation","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}