{"total":343,"rows":[{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2512.03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework","created":"2025-12-02","cited_by_count":36,"area":null},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28,"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":"2509.25134","title":"LayerD: Decomposing Raster Graphic Designs into Layers","created":"2025-09-29","cited_by_count":21,"area":null},{"id":"2506.05163","title":"FRED: The Florence RGB-Event Drone Dataset","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2506.07848","title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2501.01855","title":"UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery","created":"2025-01-03","cited_by_count":15,"area":null},{"id":"2501.13400","title":"YOLOv8 to YOLO11: A Comprehensive Architecture In-depth Comparative Review","created":"2025-01-23","cited_by_count":15,"area":null},{"id":"2505.13948","title":"Memory-Centric Embodied Question Answering","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2603.14473","title":"AI Can Learn Scientific Taste","created":"2026-03-15","cited_by_count":11,"area":null},{"id":"2508.04564","title":"Drone Detection with Event Cameras","created":"2025-08-06","cited_by_count":9,"area":null},{"id":"2503.23359","title":"VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion","created":"2025-03-30","cited_by_count":8,"area":null},{"id":"2506.06301","title":"Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2509.15237","title":"MICA: Multi-Agent Industrial Coordination Assistant","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2508.13401","title":"AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report","created":"2025-08-18","cited_by_count":7,"area":null},{"id":"2601.14706","title":"LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval","created":"2026-01-21","cited_by_count":7,"area":null},{"id":"2502.05540","title":"Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2504.10979","title":"Deep Learning in Concealed Dense Prediction","created":"2025-04-15","cited_by_count":6,"area":null},{"id":"2506.17119","title":"RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2508.10704","title":"Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios","created":"2025-08-14","cited_by_count":6,"area":null},{"id":"2509.20745","title":"Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2512.20479","title":"UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images","created":"2025-12-23","cited_by_count":6,"area":null},{"id":"2602.14276","title":"ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2411.14137","title":"VAGUE: Visual Contexts Clarify Ambiguous Expressions","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2502.11304","title":"Leveraging Multimodal-LLMs Assisted by Instance Segmentation for Intelligent Traffic Monitoring","created":"2025-02-16","cited_by_count":5,"area":null},{"id":"2504.02534","title":"Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery","created":"2025-04-03","cited_by_count":5,"area":null},{"id":"2504.10165","title":"WildLive: Near Real-time Visual Wildlife Tracking onboard UAVs","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2507.14505","title":"DCHM: Depth-Consistent Human Modeling for Multiview Detection","created":"2025-07-19","cited_by_count":5,"area":null},{"id":"2511.16937","title":"OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2604.05271","title":"Toward Unified Fine-Grained Vehicle Classification and Automatic License Plate Recognition","created":"2026-04-07","cited_by_count":5,"area":null},{"id":"2605.23271","title":"EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation","created":"2026-05-22","cited_by_count":5,"area":null},{"id":"2412.14790","title":"YOLOv11 Optimization for Efficient Resource Utilization","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2502.13134","title":"RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2506.16737","title":"Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detection","created":"2025-06-20","cited_by_count":4,"area":null},{"id":"2507.11279","title":"Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2507.13373","title":"Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection","created":"2025-07-12","cited_by_count":4,"area":null},{"id":"2507.22481","title":"Towards Blind Bitstream-corrupted Video Recovery via a Visual Foundation Model-driven Framework","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2508.19182","title":"SoccerNet 2025 Challenges Results","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2509.11772","title":"Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation","created":"2025-09-15","cited_by_count":4,"area":null},{"id":"2510.06858","title":"Explaining raw data complexity to improve satellite onboard processing","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2510.14876","title":"BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2510.25140","title":"DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2602.00153","title":"See Without Decoding: Motion-Vector-Based Tracking in Compressed Video","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2605.04569","title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2504.13469","title":"HMPE:HeatMap Embedding for Efficient Transformer-Based Small Object Detection","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2505.04917","title":"A Simple Detector with Frame Dynamics is a Strong Tracker","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2506.14696","title":"YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Framework","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2507.08729","title":"RoundaboutHD: High-Resolution Real-World Urban Environment Benchmark for Multi-Camera Vehicle Tracking","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2508.00438","title":"Diffusion-Based User-Guided Data Augmentation for Coronary Stenosis Detection","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2510.20820","title":"CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2511.20620","title":"Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2604.12807","title":"Rethinking Satellite Image Restoration for Onboard AI: A Lightweight Learning-Based Approach","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2604.15065","title":"Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2411.18871","title":"Comprehensive Performance Evaluation of YOLOv11, YOLOv10, YOLOv9, YOLOv8 and YOLOv5 on Object Detection of Power Equipment","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2503.06743","title":"X-GAN: A Generative AI-Powered Unsupervised Model for Main Vessel Segmentation of Glaucoma Screening","created":"2025-03-09","cited_by_count":2,"area":null},{"id":"2504.04835","title":"Inland Waterway Object Detection in Multi-environment: Dataset and Approach","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2506.02535","title":"Video Anomaly Detection with Semantics-Aware Information Bottleneck","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.21625","title":"Doc2SAR: A Synergistic Framework for High-Fidelity Extraction of Structure-Activity Relationships from Scientific Documents","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2506.22866","title":"Region-Aware CAM: High-Resolution Weakly-Supervised Defect Segmentation via Salient Region Perception","created":"2025-06-28","cited_by_count":2,"area":null},{"id":"2507.04323","title":"DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2507.12123","title":"Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2507.15094","title":"BleedOrigin: Dynamic Bleeding Source Localization in Endoscopic Submucosal Dissection via Dual-Stage Detection and Tracking","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2507.18763","title":"Diffusion-FS: Multimodal Free-Space Prediction via Diffusion for Autonomous Driving","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2508.16140","title":"High-Precision Mixed Feature Fusion Network Using Hypergraph Computation for Cervical Abnormal Cell Detection","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2509.08818","title":"GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2510.05662","title":"DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulation","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.27224","title":"Mask-to-Height: A YOLOv11-Based Architecture for Joint Building Instance Segmentation and Height Classification from Satellite Imagery","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2512.18046","title":"YolovN-CBi: A Lightweight and Efficient Architecture for Real-Time Detection of Small UAVs","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2602.01740","title":"MACD: Model-Aware Contrastive Decoding via Counterfactual Data","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2604.26520","title":"3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2607.27898","title":"CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2411.10068","title":"Diachronic Document Dataset for Semantic Layout Analysis","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2412.16478","title":"Enhancing Nighttime Vehicle Detection with Day-to-Night Style Transfer and Labeling-Free Augmentation","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2503.01605","title":"A Leaf-Level Dataset for Soybean-Cotton Detection and Segmentation","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2503.06317","title":"Accurate and Efficient Two-Stage Gun Detection in Video","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2503.10109","title":"Dream-IF: Dynamic Relative EnhAnceMent for Image Fusion","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2503.16579","title":"World Knowledge from AI Image Generation for Robot Control","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2503.19658","title":"BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2504.18136","title":"MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2504.20682","title":"OG-HFYOLO :Orientation gradient guidance and heterogeneous feature fusion for deformation table cell instance segmentation","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2505.04095","title":"Scalable Aerial GNSS Localization for Marine Robots","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2505.06980","title":"VALISENS: A Validated Innovative Multi-Sensor System for Cooperative Automated Driving","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2505.12045","title":"FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2505.13633","title":"IPENS:Interactive Unsupervised Framework for Rapid Plant Phenotyping Extraction via NeRF-SAM2 Fusion","created":"2025-05-19","cited_by_count":1,"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":"2506.02845","title":"Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.07637","title":"HieraEdgeNet: A Multi-Scale Edge-Enhanced Framework for Automated Pollen Recognition","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2506.18689","title":"NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2506.22517","title":"Container damage detection using advanced computer vision model Yolov12 vs Yolov11 vs RF-DETR A comparative analysis","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2507.00825","title":"High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2507.10864","title":"A Lightweight and Robust Framework for Real-Time Colorectal Polyp Detection Using LOF-Based Preprocessing and YOLO-v11n","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2507.19780","title":"JDATT: A Joint Distillation Framework for Atmospheric Turbulence Mitigation and Target Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2507.19807","title":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2508.03235","title":"Zero-shot Shape Classification of Nanoparticles in SEM Images using Vision Foundation Models","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.07803","title":"MambaTrans: Multimodal Fusion Image Translation via Large Language Model Priors for Downstream Visual Tasks","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2508.10445","title":"DOD-SA: Infrared-Visible Decoupled Object Detection with Single-Modality Annotations","created":"2025-08-14","cited_by_count":1,"area":null}],"next_cursor":"100"}