{"total":353,"rows":[{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2505.05071","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","created":"2025-05-08","cited_by_count":81,"area":null},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75,"area":null},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2506.03147","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","created":"2025-06-03","cited_by_count":66,"area":null},{"id":"2501.18954","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","created":"2025-01-31","cited_by_count":57,"area":null},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2410.13860","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2503.07465","title":"YOLOE: Real-Time Seeing Anything","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2503.13139","title":"Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding","created":"2025-03-17","cited_by_count":34,"area":null},{"id":"2406.02548","title":"Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation","created":"2024-06-04","cited_by_count":30,"area":null},{"id":"2501.14607","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","created":"2025-01-24","cited_by_count":30,"area":null},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"area":null},{"id":"2407.07844","title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","created":"2024-07-10","cited_by_count":28,"area":null},{"id":"2408.06627","title":"WorldScribe: Towards Context-Aware Live Visual Descriptions","created":"2024-08-13","cited_by_count":27,"area":null},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24,"area":null},{"id":"2502.12231","title":"PUGS: Zero-shot Physical Understanding with Gaussian Splatting","created":"2025-02-17","cited_by_count":24,"area":null},{"id":"2411.16833","title":"Open Vocabulary Monocular 3D Object Detection","created":"2024-11-25","cited_by_count":23,"area":null},{"id":"2503.07909","title":"FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction","created":"2025-03-10","cited_by_count":23,"area":null},{"id":"2412.00171","title":"RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World","created":"2024-11-29","cited_by_count":22,"area":null},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21,"area":null},{"id":"2403.06892","title":"Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head","created":"2024-03-11","cited_by_count":20,"area":null},{"id":"2411.16198","title":"Interpreting Object-level Foundation Models via Visual Precision Search","created":"2024-11-25","cited_by_count":20,"area":null},{"id":"2405.17859","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","created":"2024-05-28","cited_by_count":17,"area":null},{"id":"2411.16072","title":"Language Driven Occupancy Prediction","created":"2024-11-25","cited_by_count":17,"area":null},{"id":"2411.16310","title":"Functionality understanding and segmentation in 3D scenes","created":"2024-11-25","cited_by_count":17,"area":null},{"id":"2404.09432","title":"The 8th AI City Challenge","created":"2024-04-15","cited_by_count":16,"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":"2403.12415","title":"VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation","created":"2024-03-19","cited_by_count":14,"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":"2404.03539","title":"Is CLIP the main roadblock for fine-grained open-world perception?","created":"2024-04-04","cited_by_count":13,"area":null},{"id":"2406.02395","title":"GrootVL: Tree Topology is All You Need in State Space Model","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2409.11764","title":"One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2509.11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding","created":"2025-09-15","cited_by_count":13,"area":null},{"id":"2510.10921","title":"FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model","created":"2025-10-13","cited_by_count":13,"area":null},{"id":"2511.10376","title":"MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation","created":"2025-11-13","cited_by_count":13,"area":null},{"id":"2503.01646","title":"OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2411.16934","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2507.23567","title":"3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection","created":"2025-07-31","cited_by_count":11,"area":null},{"id":"2501.17053","title":"Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding","created":"2025-01-28","cited_by_count":10,"area":null},{"id":"2503.09447","title":"Online Language Splatting","created":"2025-03-12","cited_by_count":10,"area":null},{"id":"2508.00728","title":"YOLO-Count: Differentiable Object Counting for Text-to-Image Generation","created":"2025-08-01","cited_by_count":10,"area":null},{"id":"2512.02790","title":"UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits","created":"2025-12-01","cited_by_count":10,"area":null},{"id":"2407.04230","title":"A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation","created":"2024-07-05","cited_by_count":9,"area":null},{"id":"2411.18289","title":"Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy","created":"2024-11-27","cited_by_count":9,"area":null},{"id":"2412.20645","title":"YOLO-UniOW: Efficient Universal Open-World Object Detection","created":"2024-12-30","cited_by_count":9,"area":null},{"id":"2503.06146","title":"OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images","created":"2025-03-08","cited_by_count":9,"area":null},{"id":"2407.11906","title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2409.04847","title":"Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation","created":"2024-09-07","cited_by_count":8,"area":null},{"id":"2505.15818","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","created":"2025-05-21","cited_by_count":8,"area":null},{"id":"2603.11106","title":"RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation","created":"2026-03-11","cited_by_count":8,"area":null},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2408.09332","title":"YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems","created":"2024-08-18","cited_by_count":7,"area":null},{"id":"2409.06135","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","created":"2024-09-10","cited_by_count":7,"area":null},{"id":"2410.08530","title":"Ego3DT: Tracking Every 3D Object in Ego-centric Videos","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2412.00622","title":"Visual Modality Prompt for Adapting Vision-Language Object Detectors","created":"2024-12-01","cited_by_count":7,"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":"2604.10096","title":"ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents","created":"2026-04-11","cited_by_count":7,"area":null},{"id":"2606.11670","title":"ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation","created":"2026-06-10","cited_by_count":7,"area":null},{"id":"2405.11478","title":"Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancement","created":"2024-05-19","cited_by_count":6,"area":null},{"id":"2407.11211","title":"Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2408.10499","title":"ProgramAlly: Creating Custom Visual Access Programs via Multi-Modal End-User Programming","created":"2024-08-20","cited_by_count":6,"area":null},{"id":"2410.13305","title":"Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2503.08512","title":"SAS: Segment Any 3D Scene with Integrated 2D Priors","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2504.01515","title":"Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis","created":"2025-04-02","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":"2506.01950","title":"DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2507.17664","title":"Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras","created":"2025-07-23","cited_by_count":6,"area":null},{"id":"2511.12389","title":"Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation","created":"2025-11-15","cited_by_count":6,"area":null},{"id":"2607.14189","title":"MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation","created":"2026-07-15","cited_by_count":6,"area":null},{"id":"2403.16188","title":"Cross-domain Multi-modal Few-shot Object Detection via Rich Text","created":"2024-03-24","cited_by_count":5,"area":null},{"id":"2408.09333","title":"SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama","created":"2024-08-18","cited_by_count":5,"area":null},{"id":"2408.11221","title":"On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2410.05650","title":"SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection","created":"2024-10-08","cited_by_count":5,"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":"2412.03118","title":"ObjectFinder: An Open-Vocabulary Assistive System for Interactive Object Search by Blind People","created":"2024-12-04","cited_by_count":5,"area":null},{"id":"2412.04434","title":"Towards Real-Time Open-Vocabulary Video Instance Segmentation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2504.07252","title":"Few-Shot Adaptation of Grounding DINO for Agricultural Domain","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2508.06146","title":"Text-guided Visual Prompt DINO for Generic Segmentation","created":"2025-08-08","cited_by_count":5,"area":null},{"id":"2509.24966","title":"Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2510.05051","title":"SegMASt3R: Geometry Grounded Segment Matching","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2510.15018","title":"UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos","created":"2025-10-16","cited_by_count":5,"area":null},{"id":"2405.14874","title":"Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2408.03695","title":"Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling","created":"2024-08-07","cited_by_count":4,"area":null},{"id":"2409.11681","title":"Gradient-Driven 3D Segmentation and Affordance Transfer in Gaussian Splatting Using 2D Masks","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2409.17702","title":"Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2409.18372","title":"You Only Speak Once to See","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2411.01850","title":"ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2411.02057","title":"Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2501.13338","title":"CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2505.20639","title":"Open-Det: An Efficient Learning Framework for Open-Ended Detection","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.23607","title":"PGOV3D: Open-Vocabulary 3D Semantic Segmentation with Partial-to-Global Curriculum","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2507.01938","title":"CI-VID: A Coherent Interleaved Text-Video Dataset","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2603.00586","title":"WildActor: Unconstrained Identity-Preserving Video Generation","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2603.26541","title":"OVI-MAP:Open-Vocabulary Instance-Semantic Mapping","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2606.19383","title":"3D Scene Graphs: Open Challenges and Future Directions","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2407.10655","title":"OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2407.10754","title":"An Autonomous Drone Swarm for Detecting and Tracking Anomalies among Dense Vegetation","created":"2024-07-15","cited_by_count":3,"area":null}],"next_cursor":"100"}