{"total":113,"rows":[{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","cited_by_count":98,"area":null},{"id":"2305.09972","title":"Real-Time Flying Object Detection with YOLOv8","created":"2023-05-17","cited_by_count":94,"area":null},{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2103.17202","title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","created":"2021-03-31","cited_by_count":66,"area":null},{"id":"2108.05888","title":"Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)","created":"2021-08-12","cited_by_count":45,"area":null},{"id":"2308.04047","title":"SODFormer: Streaming Object Detection with Transformer Using Events and Frames","created":"2023-08-08","cited_by_count":39,"area":null},{"id":"2104.11747","title":"Learnable Online Graph Representations for 3D Multi-Object Tracking","created":"2021-04-23","cited_by_count":38,"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":"2405.08909","title":"ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association","created":"2024-05-14","cited_by_count":33,"area":null},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31,"area":null},{"id":"2312.00425","title":"Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware","created":"2023-12-01","cited_by_count":27,"area":null},{"id":"2308.07313","title":"Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation","created":"2023-08-14","cited_by_count":26,"area":null},{"id":"2403.07304","title":"Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models","created":"2024-03-12","cited_by_count":24,"area":"mllm"},{"id":"2506.21710","title":"FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering","created":"2025-06-26","cited_by_count":20,"area":"lr"},{"id":"2401.10227","title":"A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting","created":"2024-01-18","cited_by_count":18,"area":"diffusion"},{"id":"2109.10948","title":"T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression","created":"2021-09-22","cited_by_count":16,"area":null},{"id":"2407.11840","title":"MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densification","created":"2024-07-16","cited_by_count":16,"area":null},{"id":"2308.16187","title":"Boosting Detection in Crowd Analysis via Underutilized Output Features","created":"2023-08-30","cited_by_count":14,"area":null},{"id":"2304.06354","title":"ODAM: Gradient-based instance-specific visual explanations for object detection","created":"2023-04-13","cited_by_count":12,"area":null},{"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":"2310.09776","title":"CBARF: Cascaded Bundle-Adjusting Neural Radiance Fields from Imperfect Camera Poses","created":"2023-10-15","cited_by_count":11,"area":null},{"id":"2104.12389","title":"Variational Pedestrian Detection","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2108.10175","title":"Towards Balanced Learning for Instance Recognition","created":"2021-08-23","cited_by_count":9,"area":null},{"id":"2412.01857","title":"Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation","created":"2024-11-30","cited_by_count":8,"area":null},{"id":"2205.03562","title":"Graph Fusion Network for Multi-Oriented Object Detection","created":"2022-05-07","cited_by_count":7,"area":null},{"id":"2207.03912","title":"A Mask Attention Interaction and Scale Enhancement Network for SAR Ship Instance Segmentation","created":"2022-07-08","cited_by_count":7,"area":null},{"id":"2401.15785","title":"Real-time object detection and robotic manipulation for agriculture using a YOLO-based learning approach","created":"2024-01-28","cited_by_count":7,"area":null},{"id":"2407.15451","title":"Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions","created":"2024-07-22","cited_by_count":7,"area":null},{"id":"2104.03888","title":"Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2307.12239","title":"Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation","created":"2023-07-23","cited_by_count":6,"area":null},{"id":"2404.03789","title":"Quantifying Uncertainty in Motion Prediction with Variational Bayesian Mixture","created":"2024-04-04","cited_by_count":6,"area":null},{"id":"2502.10683","title":"CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs","created":"2025-02-15","cited_by_count":6,"area":"distill"},{"id":"2204.10803","title":"Pay \"Attention\" to Adverse Weather: Weather-aware Attention-based Object Detection","created":"2022-04-22","cited_by_count":5,"area":null},{"id":"2211.13859","title":"DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection","created":"2022-11-25","cited_by_count":4,"area":null},{"id":"2305.16332","title":"Continual Learning through Human-Robot Interaction: Human Perceptions of a Continual Learning Robot in Repeated Interactions","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2306.05772","title":"A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challenge","created":"2023-06-09","cited_by_count":4,"area":null},{"id":"2405.04971","title":"End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents","created":"2024-05-08","cited_by_count":4,"area":null},{"id":"2407.08460","title":"Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer","created":"2024-07-11","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":"2411.16129","title":"Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2505.01385","title":"Global Collinearity-aware Polygonizer for Polygonal Building Mapping in Remote Sensing","created":"2025-05-02","cited_by_count":4,"area":null},{"id":"2204.13971","title":"Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach","created":"2022-04-29","cited_by_count":3,"area":null},{"id":"2307.11550","title":"YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimation","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2412.02171","title":"Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2503.08019","title":"Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models","created":"2025-03-11","cited_by_count":3,"area":"mllm"},{"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":"2505.07040","title":"Differentiable NMS via Sinkhorn Matching for End-to-End Fabric Defect Detection","created":"2025-05-11","cited_by_count":3,"area":null},{"id":"2505.24038","title":"Conformal Object Detection by Sequential Risk Control","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2507.22438","title":"From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras","created":"2025-07-30","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":"2105.05636","title":"VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching","created":"2021-05-12","cited_by_count":2,"area":null},{"id":"2106.14195","title":"Learning to solve geometric construction problems from images","created":"2021-06-27","cited_by_count":2,"area":null},{"id":"2110.11829","title":"CNN-based Omnidirectional Object Detection for HermesBot Autonomous Delivery Robot with Preliminary Frame Classification","created":"2021-10-22","cited_by_count":2,"area":null},{"id":"2405.03318","title":"Enhancing DETRs Variants through Improved Content Query and Similar Query Aggregation","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2409.20520","title":"Accelerating Non-Maximum Suppression: A Graph Theory Perspective","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2505.00534","title":"A Robust Deep Networks based Multi-Object MultiCamera Tracking System for City Scale Traffic","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2508.12605","title":"ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images","created":"2025-08-18","cited_by_count":2,"area":"mllm"},{"id":"2509.06165","title":"UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2603.15497","title":"Real-Time Oriented Object Detection Transformer in Remote Sensing Images","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2203.02940","title":"Detection of Parasitic Eggs from Microscopy Images and the emergence of a new dataset","created":"2022-03-06","cited_by_count":1,"area":null},{"id":"2302.14166","title":"GLOW: Global Layout Aware Attacks on Object Detection","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2303.04253","title":"TMHOI: Translational Model for Human-Object Interaction Detection","created":"2023-03-07","cited_by_count":1,"area":null},{"id":"2309.02159","title":"The Adversarial Implications of Variable-Time Inference","created":"2023-09-05","cited_by_count":1,"area":null},{"id":"2310.19936","title":"Towards Few-Annotation Learning for Object Detection: Are Transformer-based Models More Efficient ?","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2411.01499","title":"Polar R-CNN: End-to-End Lane Detection with Fewer Anchors","created":"2024-11-03","cited_by_count":1,"area":null},{"id":"2412.06268","title":"Open-Vocabulary High-Resolution 3D (OVHR3D) Data Segmentation and Annotation Framework","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2412.10453","title":"Analysis of Object Detection Models for Tiny Object in Satellite Imagery: A Dataset-Centric Approach","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2502.00535","title":"Work-Efficient Parallel Non-Maximum Suppression Kernels","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2504.09819","title":"Density-based Object Detection in Crowded Scenes","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2511.13344","title":"YOLO Meets Mixture-of-Experts: Adaptive Expert Routing for Robust Object Detection","created":"2025-11-17","cited_by_count":1,"area":"moe"},{"id":"2512.01315","title":"FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detection","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2603.07985","title":"On the Feasibility and Opportunity of Autoregressive 3D Object Detection","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2102.04582","title":"RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2107.13233","title":"C^3Net: End-to-End deep learning for efficient real-time visual active camera control","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2109.04698","title":"Face-NMS: A Core-set Selection Approach for Efficient Face Recognition","created":"2021-09-10","cited_by_count":0,"area":null},{"id":"2112.00342","title":"Confidence Propagation Cluster: Unleash Full Potential of Object Detectors","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2211.14716","title":"Fingerprint Pore Detection: A Survey","created":"2022-11-27","cited_by_count":0,"area":null},{"id":"2302.05541","title":"Semi-supervised Large-scale Fiber Detection in Material Images with Synthetic Data","created":"2023-02-10","cited_by_count":0,"area":null},{"id":"2312.08268","title":"Efficient Multi-Object Pose Estimation using Multi-Resolution Deformable Attention and Query Aggregation","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2402.08251","title":"Object Detection in Thermal Images Using Deep Learning for Unmanned Aerial Vehicles","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2403.10981","title":"Automatic Spatial Calibration of Near-Field MIMO Radar With Respect to Optical Depth Sensors","created":"2024-03-16","cited_by_count":0,"area":null},{"id":"2502.10118","title":"Image Embedding Sampling Method for Diverse Captioning","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2505.08835","title":"Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2505.21544","title":"Vision Meets Language: A RAG-Augmented YOLOv8 Framework for Coffee Disease Diagnosis and Farmer Assistance","created":"2025-05-24","cited_by_count":0,"area":"rag"},{"id":"2506.20522","title":"AI-assisted radiographic analysis in detecting alveolar bone-loss severity and patterns","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2509.05604","title":"Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2509.10779","title":"Group Evidence Matters: Tiling-based Semantic Gating for Dense Object Detection","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2510.10108","title":"Uncertainty-Aware Post-Detection Framework for Enhanced Fire and Smoke Detection in Compact Deep Learning Models","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2510.27179","title":"SilhouetteTell: Practical Video Identification Leveraging Blurred Recordings of Video Subtitles","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2512.05579","title":"A Comprehensive Framework for Automated Quality Control in the Automotive Industry","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2602.05730","title":"Depth as Prior Knowledge for Object Detection","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.23290","title":"LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.00605","title":"Fluently Lying: Adversarial Robustness Can Be Substrate-Dependent","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.27928","title":"Training-Free Tunnel Defect Inspection and Engineering Interpretation via Visual Recalibration and Entity Reconstruction","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.15088","title":"Learned Suppression for 3D Keypoint Detection with a Graph-Transformer Backbone","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.24831","title":"YOLO26 vs. YOLOv8: A Comprehensive Architectural Benchmark of Next-Generation Real-Time Object Detection Models","created":"2026-05-24","cited_by_count":0,"area":null}],"next_cursor":"100"}