{"total":533,"rows":[{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"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":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229,"area":"mllm"},{"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":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87,"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":"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":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2307.09220","title":"A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future","created":"2023-07-18","cited_by_count":61,"area":null},{"id":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60,"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":"2601.21957","title":"PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing","created":"2026-01-29","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":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2405.13675","title":"Context and Geometry Aware Voxel Transformer for Semantic Scene Completion","created":"2024-05-22","cited_by_count":50,"area":null},{"id":"2512.02498","title":"dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model","created":"2025-12-02","cited_by_count":47,"area":"mllm"},{"id":"2305.05813","title":"Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review","created":"2023-05-09","cited_by_count":41,"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":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2408.09869","title":"Docling Technical Report","created":"2024-08-19","cited_by_count":34,"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":"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":"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":"2406.06843","title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","created":"2024-06-10","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":"2509.20787","title":"Real-Time Object Detection Meets DINOv3","created":"2025-09-25","cited_by_count":27,"area":null},{"id":"2503.17213","title":"PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction","created":"2025-03-21","cited_by_count":26,"area":null},{"id":"2407.06937","title":"HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance","created":"2024-07-09","cited_by_count":25,"area":"diffusion"},{"id":"2412.06647","title":"Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset","created":"2024-12-09","cited_by_count":25,"area":"moe"},{"id":"2406.08249","title":"Dataset Enhancement with Instance-Level Augmentations","created":"2024-06-12","cited_by_count":23,"area":"diffusion"},{"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":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"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":"2501.04336","title":"Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs","created":"2025-01-08","cited_by_count":19,"area":"mllm"},{"id":"2501.06553","title":"VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification","created":"2025-01-11","cited_by_count":17,"area":"mllm"},{"id":"2506.05163","title":"FRED: The Florence RGB-Event Drone Dataset","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2405.12070","title":"AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements","created":"2024-05-20","cited_by_count":15,"area":null},{"id":"2409.19833","title":"HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes","created":"2024-09-30","cited_by_count":15,"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":"2405.12930","title":"Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservation","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14,"area":"mllm"},{"id":"2405.00587","title":"GraCo: Granularity-Controllable Interactive Segmentation","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2506.04623","title":"VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2511.10390","title":"MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns","created":"2025-11-13","cited_by_count":13,"area":"rag"},{"id":"2504.13099","title":"RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity","created":"2025-04-17","cited_by_count":12,"area":null},{"id":"2409.04758","title":"SGSeg: Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance","created":"2024-09-07","cited_by_count":11,"area":null},{"id":"2411.02136","title":"Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery","created":"2024-11-04","cited_by_count":11,"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":"2505.04594","title":"Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection","created":"2025-05-07","cited_by_count":10,"area":null},{"id":"2507.18300","title":"LMM-Det: Make Large Multimodal Models Excel in Object Detection","created":"2025-07-24","cited_by_count":10,"area":"mllm"},{"id":"2507.19993","title":"FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images","created":"2025-07-26","cited_by_count":10,"area":null},{"id":"2412.02890","title":"EvRT-DETR: Latent Space Adaptation of Image Detectors for Event-based Vision","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2503.01463","title":"MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2503.17122","title":"R-LiViT: A LiDAR-Visual-Thermal Dataset Enabling Vulnerable Road User Focused Roadside Perception","created":"2025-03-21","cited_by_count":9,"area":null},{"id":"2508.04564","title":"Drone Detection with Event Cameras","created":"2025-08-06","cited_by_count":9,"area":null},{"id":"2306.07265","title":"detrex: Benchmarking Detection Transformers","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2411.02799","title":"ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing","created":"2024-11-05","cited_by_count":8,"area":null},{"id":"2402.13575","title":"Flexible Physical Camouflage Generation Based on a Differential Approach","created":"2024-02-21","cited_by_count":7,"area":null},{"id":"2407.18487","title":"SMPISD-MTPNet: Scene Semantic Prior-Assisted Infrared Ship Detection Using Multi-Task Perception Networks","created":"2024-07-26","cited_by_count":7,"area":null},{"id":"2407.21308","title":"Enhanced Self-Checkout System for Retail Based on Improved YOLOv10","created":"2024-07-31","cited_by_count":7,"area":null},{"id":"2412.13490","title":"Comparative Analysis of YOLOv9, YOLOv10 and RT-DETR for Real-Time Weed Detection","created":"2024-12-18","cited_by_count":7,"area":null},{"id":"2503.14012","title":"LEGNet: A Lightweight Edge-Gaussian Network for Low-Quality Remote Sensing Image Object Detection","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2402.16370","title":"DEYO: DETR with YOLO for End-to-End Object Detection","created":"2024-02-26","cited_by_count":6,"area":null},{"id":"2405.10148","title":"SpecDETR: A transformer-based hyperspectral point object detection network","created":"2024-05-16","cited_by_count":6,"area":null},{"id":"2502.13023","title":"Detection and Geographic Localization of Natural Objects in the Wild: A Case Study on Palms","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2509.19875","title":"Adaptive Guidance Semantically Enhanced via Multimodal LLM for Edge-Cloud Object Detection","created":"2025-09-24","cited_by_count":6,"area":"mllm"},{"id":"2510.03701","title":"Referring Expression Comprehension for Small Objects","created":"2025-10-04","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":"2305.00675","title":"End-to-End Lane detection with One-to-Several Transformer","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2307.13901","title":"YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems","created":"2023-07-26","cited_by_count":5,"area":null},{"id":"2404.08081","title":"Real-Time Detection and Analysis of Vehicles and Pedestrians using Deep Learning","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2408.06123","title":"DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detection","created":"2024-08-12","cited_by_count":5,"area":null},{"id":"2409.07284","title":"TLD-READY: Traffic Light Detection -- Relevance Estimation and Deployment Analysis","created":"2024-09-11","cited_by_count":5,"area":null},{"id":"2410.11124","title":"Real-Time Localization and Bimodal Point Pattern Analysis of Palms Using UAV Imagery","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2411.03403","title":"Enhancing Maritime Situational Awareness through End-to-End Onboard Raw Data Analysis","created":"2024-11-05","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":"2501.17387","title":"Assessing the Capability of YOLO- and Transformer-based Object Detectors for Real-time Weed Detection","created":"2025-01-29","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":"2509.17993","title":"StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models","created":"2025-09-22","cited_by_count":5,"area":"diffusion"},{"id":"2509.23700","title":"INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2603.28130","title":"MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2402.00350","title":"On the Challenges of Fuzzing Techniques via Large Language Models","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2403.17726","title":"Tiny Models are the Computational Saver for Large Models","created":"2024-03-26","cited_by_count":4,"area":"inference"},{"id":"2406.06230","title":"UEMM-Air: Make Unmanned Aerial Vehicles Perform More Multi-modal Tasks","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2407.12773","title":"OMG-Net: A Deep Learning Framework Deploying Segment Anything to Detect Pan-Cancer Mitotic Figures from Haematoxylin and Eosin-Stained Slides","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2407.18245","title":"VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2409.05466","title":"Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2410.12143","title":"Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmark","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2412.01440","title":"BadPatch: Diffusion-Based Generation of Physical Adversarial Patches","created":"2024-12-02","cited_by_count":4,"area":"diffusion"},{"id":"2504.05583","title":"Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification","created":"2025-04-08","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":"2506.13457","title":"Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art","created":"2025-06-16","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":"2507.15911","title":"Local Dense Logit Relations for Enhanced Knowledge Distillation","created":"2025-07-21","cited_by_count":4,"area":"distill"},{"id":"2509.11772","title":"Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation","created":"2025-09-15","cited_by_count":4,"area":null},{"id":"2510.11090","title":"Source-Free Object Detection with Detection Transformer","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2511.00510","title":"OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback","created":"2025-11-01","cited_by_count":4,"area":null}],"next_cursor":"100"}