{"total":107,"rows":[{"id":"2211.10581","title":"Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion","created":"2022-11-19","cited_by_count":162,"area":null},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60,"area":null},{"id":"2102.02267","title":"DEFT: Detection Embeddings for Tracking","created":"2021-02-03","cited_by_count":56,"area":null},{"id":"2105.04322","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","created":"2021-05-10","cited_by_count":52,"area":null},{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46,"area":null},{"id":"2103.07889","title":"Learning a Proposal Classifier for Multiple Object Tracking","created":"2021-03-14","cited_by_count":42,"area":null},{"id":"2103.13516","title":"Tracking Pedestrian Heads in Dense Crowd","created":"2021-03-24","cited_by_count":42,"area":null},{"id":"2205.00158","title":"AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild","created":"2022-04-30","cited_by_count":37,"area":null},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36,"area":null},{"id":"2305.07348","title":"A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects","created":"2023-05-12","cited_by_count":30,"area":null},{"id":"2204.13349","title":"Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor","created":"2022-04-28","cited_by_count":27,"area":null},{"id":"2103.13933","title":"Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark","created":"2021-03-25","cited_by_count":25,"area":null},{"id":"2103.15632","title":"Regular Polytope Networks","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2103.17001","title":"Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Cameras","created":"2021-03-31","cited_by_count":24,"area":null},{"id":"2207.09295","title":"The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting","created":"2022-07-19","cited_by_count":24,"area":null},{"id":"2309.09737","title":"RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud","created":"2023-09-18","cited_by_count":21,"area":null},{"id":"2202.13073","title":"Global Instance Tracking: Locating Target More Like Humans","created":"2022-02-26","cited_by_count":18,"area":null},{"id":"2312.14229","title":"Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2204.10713","title":"EmbedTrack -- Simultaneous Cell Segmentation and Tracking Through Learning Offsets and Clustering Bandwidths","created":"2022-04-22","cited_by_count":16,"area":null},{"id":"2112.04477","title":"Tracking People by Predicting 3D Appearance, Location & Pose","created":"2021-12-08","cited_by_count":15,"area":null},{"id":"2205.15730","title":"Transformers for Multi-Object Tracking on Point Clouds","created":"2022-05-31","cited_by_count":14,"area":null},{"id":"2306.17602","title":"S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations","created":"2023-06-30","cited_by_count":12,"area":null},{"id":"2211.01671","title":"Visual Adversarial Attacks and Defenses in the Physical World: A Survey","created":"2022-11-03","cited_by_count":11,"area":null},{"id":"2204.07414","title":"SOTVerse: A User-defined Task Space of Single Object Tracking","created":"2022-04-15","cited_by_count":10,"area":null},{"id":"2302.11867","title":"Transformers in Single Object Tracking: An Experimental Survey","created":"2023-02-23","cited_by_count":10,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2204.08584","title":"A Region-Based Deep Learning Approach to Automated Retail Checkout","created":"2022-04-18","cited_by_count":9,"area":null},{"id":"2310.15098","title":"Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2102.04091","title":"Online Clustering-based Multi-Camera Vehicle Tracking in Scenarios with overlapping FOVs","created":"2021-02-08","cited_by_count":8,"area":null},{"id":"2204.07482","title":"Towards PAC Multi-Object Detection and Tracking","created":"2022-04-15","cited_by_count":8,"area":null},{"id":"2205.10766","title":"Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2107.05150","title":"CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking","created":"2021-07-11","cited_by_count":7,"area":null},{"id":"2211.15751","title":"Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques","created":"2022-11-28","cited_by_count":7,"area":null},{"id":"2212.00266","title":"Multi-view Tracking, Re-ID, and Social Network Analysis of a Flock of Visually Similar Birds in an Outdoor Aviary","created":"2022-12-01","cited_by_count":7,"area":null},{"id":"2308.04770","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2506.06026","title":"O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2104.00734","title":"Next Generation Multitarget Trackers: Random Finite Set Methods vs Transformer-based Deep Learning","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2208.08041","title":"InterTrack: Interaction Transformer for 3D Multi-Object Tracking","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2309.16987","title":"SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2108.01495","title":"Cross-Modal Analysis of Human Detection for Robotics: An Industrial Case Study","created":"2021-08-03","cited_by_count":5,"area":null},{"id":"2109.14737","title":"Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2202.07909","title":"Can Deep Learning be Applied to Model-Based Multi-Object Tracking?","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2503.05962","title":"OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cooking","created":"2025-03-07","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":"2407.00738","title":"Engineering an Efficient Object Tracker for Non-Linear Motion","created":"2024-06-30","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":"2204.04143","title":"Optical tracking in team sports","created":"2022-04-08","cited_by_count":3,"area":null},{"id":"2303.00337","title":"TAU: A Framework for Video-Based Traffic Analytics Leveraging Artificial Intelligence and Unmanned Aerial Systems","created":"2023-03-01","cited_by_count":3,"area":null},{"id":"2306.05089","title":"A review of UAV Visual Detection and Tracking Methods","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2306.14753","title":"The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theory","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2312.17261","title":"Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing","created":"2023-12-22","cited_by_count":3,"area":null},{"id":"2501.13710","title":"YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2106.13064","title":"Advancing biological super-resolution microscopy through deep learning: a brief review","created":"2021-06-24","cited_by_count":2,"area":null},{"id":"2304.00950","title":"Semi-Automated Computer Vision based Tracking of Multiple Industrial Entities -- A Framework and Dataset Creation Approach","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2307.11904","title":"Model Compression Methods for YOLOv5: A Review","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2312.07723","title":"Automated Behavioral Analysis Using Instance Segmentation","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2401.11110","title":"VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE","created":"2024-01-20","cited_by_count":2,"area":null},{"id":"2406.04844","title":"Multi-Granularity Language-Guided Training for Multi-Object Tracking","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2507.08494","title":"One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2507.12832","title":"MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2508.07968","title":"TrackOR: Towards Personalized Intelligent Operating Rooms Through Robust Tracking","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2107.13273","title":"Rank-based verification for long-term face tracking in crowded scenes","created":"2021-07-28","cited_by_count":1,"area":null},{"id":"2110.05102","title":"Multiple Object Trackers in OpenCV: A Benchmark","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2112.14159","title":"Skin feature point tracking using deep feature encodings","created":"2021-12-28","cited_by_count":1,"area":null},{"id":"2201.04235","title":"SmartDet: Context-Aware Dynamic Control of Edge Task Offloading for Mobile Object Detection","created":"2022-01-11","cited_by_count":1,"area":null},{"id":"2204.04416","title":"E^2TAD: An Energy-Efficient Tracking-based Action Detector","created":"2022-04-09","cited_by_count":1,"area":null},{"id":"2208.10662","title":"How to Track and Segment Fish without Human Annotations: A Self-Supervised Deep Learning Approach","created":"2022-08-23","cited_by_count":1,"area":null},{"id":"2212.05861","title":"Joint Counting, Detection and Re-Identification for Multi-Object Tracking","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2309.02975","title":"FishMOT: A Simple and Effective Method for Fish Tracking Based on IoU Matching","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2312.04167","title":"Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation","created":"2023-12-07","cited_by_count":1,"area":null},{"id":"2405.07272","title":"MAML MOT: Multiple Object Tracking based on Meta-Learning","created":"2024-05-12","cited_by_count":1,"area":null},{"id":"2409.01148","title":"FMRFT: Fusion Mamba and DETR for Query Time Sequence Intersection Fish Tracking","created":"2024-09-02","cited_by_count":1,"area":"ssm"},{"id":"2409.04187","title":"LITE: A Paradigm Shift in Multi-Object Tracking with Efficient ReID Feature Integration","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2411.15447","title":"Gotta Hear Them All: Towards Sound Source Aware Audio Generation","created":"2024-11-23","cited_by_count":1,"area":null},{"id":"2502.21242","title":"Towards long-term player tracking with graph hierarchies and domain-specific features","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2504.00161","title":"SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2507.07883","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2511.16532","title":"Enhancing Multi-Camera Gymnast Tracking Through Domain Knowledge Integration","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2607.22731","title":"Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2103.00053","title":"PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation","created":"2021-02-26","cited_by_count":0,"area":"distill"},{"id":"2103.13428","title":"TagMe: GPS-Assisted Automatic Object Annotation in Videos","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2109.01235","title":"DeepTracks: Geopositioning Maritime Vehicles in Video Acquired from a Moving Platform","created":"2021-09-02","cited_by_count":0,"area":null},{"id":"2110.02044","title":"Multi-Object Tracking with Deep Learning Ensemble for Unmanned Aerial System Applications","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2110.15674","title":"Multi-target tracking for video surveillance using deep affinity network: a brief review","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2112.08345","title":"Reliable Multi-Object Tracking in the Presence of Unreliable Detections","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2202.04966","title":"Real-Time Siamese Multiple Object Tracker with Enhanced Proposals","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2202.09315","title":"Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencoder","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2202.13958","title":"CQELS 2.0: Towards A Unified Framework for Semantic Stream Fusion","created":"2022-02-15","cited_by_count":0,"area":null},{"id":"2204.00891","title":"A Free Lunch to Person Re-identification: Learning from Automatically Generated Noisy Tracklets","created":"2022-04-02","cited_by_count":0,"area":null},{"id":"2302.05425","title":"Deep Learning Based Object Tracking in Walking Droplet and Granular Intruder Experiments","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2302.08052","title":"Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection","created":"2023-02-16","cited_by_count":0,"area":null},{"id":"2305.09981","title":"S$^3$Track: Self-supervised Tracking with Soft Assignment Flow","created":"2023-05-17","cited_by_count":0,"area":null},{"id":"2311.17109","title":"Neural Texture Puppeteer: A Framework for Neural Geometry and Texture Rendering of Articulated Shapes, Enabling Re-Identification at Interactive Speed","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2404.17865","title":"Vision-based Discovery of Nonlinear Dynamics for 3D Moving Target","created":"2024-04-27","cited_by_count":0,"area":null},{"id":"2405.04943","title":"Unsupervised Skin Feature Tracking with Deep Neural Networks","created":"2024-05-08","cited_by_count":0,"area":null},{"id":"2406.13060","title":"Scale-Translation Equivariant Network for Oceanic Internal Solitary Wave Localization","created":"2024-06-18","cited_by_count":0,"area":null},{"id":"2503.04500","title":"ReynoldsFlow: Physics-Inspired Spatiotemporal Flow Representation for Video Understanding","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2503.09807","title":"How good are deep learning methods for automated road safety analysis using video data? An experimental study","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.00599","title":"Visual Trajectory Prediction of Vessels for Inland Navigation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2508.05172","title":"Multi-tracklet Tracking for Generic Targets with Adaptive Detection Clustering","created":"2025-08-07","cited_by_count":0,"area":null}],"next_cursor":"100"}