{"total":982,"rows":[{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"area":null},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425,"area":null},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290,"area":null},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275,"area":null},{"id":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205,"area":"mllm"},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2306.05427","title":"Grounded Text-to-Image Synthesis with Attention Refocusing","created":"2023-06-08","cited_by_count":164,"area":"diffusion"},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163,"area":"diffusion"},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106,"area":null},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83,"area":null},{"id":"2509.25164","title":"YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection","created":"2025-09-29","cited_by_count":79,"area":null},{"id":"2306.00973","title":"Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models","created":"2023-06-01","cited_by_count":77,"area":"diffusion"},{"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":"2410.13842","title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","created":"2024-10-17","cited_by_count":74,"area":"distill"},{"id":"2407.06322","title":"MagMax: Leveraging Model Merging for Seamless Continual Learning","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2301.05586","title":"YOLOv6 v3.0: A Full-Scale Reloading","created":"2023-01-13","cited_by_count":58,"area":null},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58,"area":null},{"id":"2506.17733","title":"YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception","created":"2025-06-21","cited_by_count":58,"area":null},{"id":"2305.15072","title":"PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology","created":"2023-05-24","cited_by_count":57,"area":"mllm"},{"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":"2311.17663","title":"Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications","created":"2023-11-29","cited_by_count":52,"area":"wm"},{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2307.10784","title":"SMURF: Spatial Multi-Representation Fusion for 3D Object Detection with 4D Imaging Radar","created":"2023-07-20","cited_by_count":49,"area":null},{"id":"2306.05238","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46,"area":null},{"id":"2303.14488","title":"Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images","created":"2023-03-25","cited_by_count":41,"area":null},{"id":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41,"area":null},{"id":"2304.01159","title":"DribbleBot: Dynamic Legged Manipulation in the Wild","created":"2023-04-03","cited_by_count":40,"area":null},{"id":"2305.11618","title":"DAP: A Dynamic Adversarial Patch for Evading Person Detectors","created":"2023-05-19","cited_by_count":40,"area":null},{"id":"2404.00722","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","created":"2024-03-31","cited_by_count":40,"area":null},{"id":"2302.02367","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","created":"2023-02-05","cited_by_count":39,"area":null},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38,"area":null},{"id":"2307.09781","title":"Text2Layer: Layered Image Generation using Latent Diffusion Model","created":"2023-07-19","cited_by_count":37,"area":"diffusion"},{"id":"2310.14729","title":"MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion","created":"2023-10-23","cited_by_count":37,"area":"diffusion"},{"id":"2303.07335","title":"Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR","created":"2023-03-13","cited_by_count":36,"area":null},{"id":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","cited_by_count":36,"area":null},{"id":"2503.07465","title":"YOLOE: Real-Time Seeing Anything","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2401.03989","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","created":"2024-01-08","cited_by_count":35,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2402.16936","title":"Disentangled 3D Scene Generation with Layout Learning","created":"2024-02-26","cited_by_count":33,"area":null},{"id":"2409.08475","title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","created":"2024-09-13","cited_by_count":32,"area":null},{"id":"2305.13500","title":"Learning Emotion Representations from Verbal and Nonverbal Communication","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2306.04557","title":"PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain","created":"2023-06-07","cited_by_count":31,"area":null},{"id":"2308.07009","title":"ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion","created":"2023-08-14","cited_by_count":31,"area":null},{"id":"2301.10051","title":"Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism","created":"2023-01-24","cited_by_count":30,"area":null},{"id":"2404.01294","title":"CosmicMan: A Text-to-Image Foundation Model for Humans","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2408.04804","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","created":"2024-08-09","cited_by_count":29,"area":null},{"id":"2403.00326","title":"DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion","created":"2024-03-01","cited_by_count":28,"area":null},{"id":"2307.07859","title":"Unified Adversarial Patch for Cross-modal Attacks in the Physical World","created":"2023-07-15","cited_by_count":27,"area":null},{"id":"2208.11434","title":"YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception","created":"2022-08-24","cited_by_count":26,"area":null},{"id":"2211.13523","title":"Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark","created":"2022-11-24","cited_by_count":26,"area":null},{"id":"2305.00314","title":"InfraDet3D: Multi-Modal 3D Object Detection based on Roadside Infrastructure Camera and LiDAR Sensors","created":"2023-04-29","cited_by_count":25,"area":null},{"id":"2405.09365","title":"SARATR-X: Toward Building A Foundation Model for SAR Target Recognition","created":"2024-05-15","cited_by_count":25,"area":null},{"id":"2305.00434","title":"EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction","created":"2023-04-30","cited_by_count":24,"area":null},{"id":"2401.00027","title":"Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring","created":"2023-12-29","cited_by_count":24,"area":null},{"id":"2210.04435","title":"Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning","created":"2022-10-10","cited_by_count":23,"area":null},{"id":"2312.02219","title":"Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models","created":"2023-12-03","cited_by_count":23,"area":null},{"id":"2212.01593","title":"Make RepVGG Greater Again: A Quantization-aware Approach","created":"2022-12-03","cited_by_count":22,"area":null},{"id":"2303.06442","title":"Fine-grained Visual Classification with High-temperature Refinement and Background Suppression","created":"2023-03-11","cited_by_count":22,"area":null},{"id":"2305.17449","title":"FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection","created":"2023-05-27","cited_by_count":22,"area":null},{"id":"2401.08206","title":"Generative Multi-Modal Knowledge Retrieval with Large Language Models","created":"2024-01-16","cited_by_count":22,"area":null},{"id":"2411.17030","title":"g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks","created":"2024-11-26","cited_by_count":22,"area":null},{"id":"2307.14682","title":"Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World","created":"2023-07-27","cited_by_count":21,"area":null},{"id":"2412.13126","title":"Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis","created":"2024-12-17","cited_by_count":21,"area":"mllm"},{"id":"2303.15334","title":"ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box","created":"2023-03-27","cited_by_count":20,"area":null},{"id":"2308.06173","title":"Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook","created":"2023-08-11","cited_by_count":20,"area":null},{"id":"2311.00537","title":"Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial","created":"2023-11-01","cited_by_count":20,"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":"2406.05835","title":"Mamba YOLO: A Simple Baseline for Object Detection with State Space Model","created":"2024-06-09","cited_by_count":19,"area":"ssm"},{"id":"2312.04548","title":"Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?","created":"2023-12-07","cited_by_count":18,"area":null},{"id":"2402.15853","title":"RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation","created":"2024-02-24","cited_by_count":18,"area":null},{"id":"2411.00201","title":"YOLO Evolution: A Comprehensive Benchmark and Architectural Review of YOLOv12, YOLO11, and Their Previous Versions","created":"2024-10-31","cited_by_count":18,"area":null},{"id":"2510.09653","title":"Ultralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition","created":"2025-10-06","cited_by_count":18,"area":null},{"id":"2302.07577","title":"Efficient Teacher: Semi-Supervised Object Detection for YOLOv5","created":"2023-02-15","cited_by_count":17,"area":null},{"id":"2306.15988","title":"AFPN: Asymptotic Feature Pyramid Network for Object Detection","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2309.14976","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","created":"2023-09-26","cited_by_count":17,"area":"moe"},{"id":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17,"area":null},{"id":"2403.04173","title":"Image Coding for Machines with Edge Information Learning Using Segment Anything","created":"2024-03-07","cited_by_count":17,"area":null},{"id":"2405.15199","title":"ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models","created":"2024-05-24","cited_by_count":17,"area":"diffusion"},{"id":"2408.08827","title":"RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba","created":"2024-08-16","cited_by_count":17,"area":"ssm"},{"id":"2307.07102","title":"Achelous: A Fast Unified Water-surface Panoptic Perception Framework based on Fusion of Monocular Camera and 4D mmWave Radar","created":"2023-07-14","cited_by_count":16,"area":null},{"id":"2311.00436","title":"Enhancing Traffic Object Detection in Variable Illumination with RGB-Event Fusion","created":"2023-11-01","cited_by_count":16,"area":null},{"id":"2404.09432","title":"The 8th AI City Challenge","created":"2024-04-15","cited_by_count":16,"area":null},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2304.05552","title":"DynamicDet: A Unified Dynamic Architecture for Object Detection","created":"2023-04-12","cited_by_count":15,"area":null},{"id":"2307.02733","title":"MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection","created":"2023-07-06","cited_by_count":15,"area":null},{"id":"2307.14723","title":"EFLNet: Enhancing Feature Learning for Infrared Small Target Detection","created":"2023-07-27","cited_by_count":15,"area":null},{"id":"2309.04902","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","created":"2023-09-10","cited_by_count":15,"area":null},{"id":"2311.01057","title":"Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO","created":"2023-11-02","cited_by_count":15,"area":null},{"id":"2409.13366","title":"RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning","created":"2024-09-20","cited_by_count":15,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2305.00201","title":"Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT","created":"2023-04-29","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2310.01641","title":"You Only Look at Once for Real-time and Generic Multi-Task","created":"2023-10-02","cited_by_count":14,"area":null}],"next_cursor":"100"}