{"total":156,"rows":[{"id":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105,"area":null},{"id":"2104.00194","title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","created":"2021-04-01","cited_by_count":93,"area":null},{"id":"2106.06345","title":"Proximal Optimal Transport Modeling of Population Dynamics","created":"2021-06-11","cited_by_count":93,"area":null},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2103.07351","title":"Monocular Quasi-Dense 3D Object Tracking","created":"2021-03-12","cited_by_count":81,"area":null},{"id":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80,"area":null},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"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":"2205.00158","title":"AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild","created":"2022-04-30","cited_by_count":37,"area":null},{"id":"2207.05518","title":"Tracking Objects as Pixel-wise Distributions","created":"2022-07-12","cited_by_count":37,"area":null},{"id":"2308.11894","title":"Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack","created":"2023-08-23","cited_by_count":37,"area":null},{"id":"2111.15157","title":"MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark","created":"2021-11-30","cited_by_count":29,"area":null},{"id":"2210.16204","title":"TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM","created":"2022-10-28","cited_by_count":26,"area":null},{"id":"2104.09441","title":"One More Check: Making \"Fake Background\" Be Tracked Again","created":"2021-04-19","cited_by_count":25,"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":"2203.05314","title":"SoK: On the Semantic AI Security in Autonomous Driving","created":"2022-03-10","cited_by_count":22,"area":null},{"id":"2403.11186","title":"NetTrack: Tracking Highly Dynamic Objects with a Net","created":"2024-03-17","cited_by_count":22,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2308.11157","title":"TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes","created":"2023-08-22","cited_by_count":21,"area":null},{"id":"2410.01806","title":"Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2111.12960","title":"Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark","created":"2021-11-25","cited_by_count":18,"area":null},{"id":"2203.12335","title":"DR.VIC: Decomposition and Reasoning for Video Individual Counting","created":"2022-03-23","cited_by_count":18,"area":null},{"id":"2204.01784","title":"Object Permanence Emerges in a Random Walk along Memory","created":"2022-04-04","cited_by_count":18,"area":null},{"id":"2307.05721","title":"HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding","created":"2023-07-09","cited_by_count":18,"area":null},{"id":"2110.03267","title":"Propagating State Uncertainty Through Trajectory Forecasting","created":"2021-10-07","cited_by_count":17,"area":null},{"id":"2305.03052","title":"Tracking through Containers and Occluders in the Wild","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2308.07207","title":"FOLT: Fast Multiple Object Tracking from UAV-captured Videos Based on Optical Flow","created":"2023-08-14","cited_by_count":15,"area":null},{"id":"2210.12733","title":"Self-supervised Amodal Video Object Segmentation","created":"2022-10-23","cited_by_count":14,"area":null},{"id":"2405.15700","title":"Trackastra: Transformer-based cell tracking for live-cell microscopy","created":"2024-05-24","cited_by_count":14,"area":null},{"id":"2301.01882","title":"InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation","created":"2023-01-05","cited_by_count":13,"area":null},{"id":"2105.13351","title":"Tracking Without Re-recognition in Humans and Machines","created":"2021-05-27","cited_by_count":12,"area":null},{"id":"2208.14542","title":"TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos","created":"2022-08-30","cited_by_count":12,"area":null},{"id":"2209.04796","title":"In Pursuit of Many: A Review of Modern Multiple Object Tracking Systems","created":"2022-09-11","cited_by_count":12,"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":"2307.16517","title":"Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception","created":"2023-07-31","cited_by_count":12,"area":null},{"id":"2108.10175","title":"Towards Balanced Learning for Instance Recognition","created":"2021-08-23","cited_by_count":9,"area":null},{"id":"2211.11925","title":"Multimodal Data Augmentation for Visual-Infrared Person ReID with Corrupted Data","created":"2022-11-22","cited_by_count":9,"area":null},{"id":"2405.17903","title":"Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion","created":"2024-05-28","cited_by_count":9,"area":null},{"id":"2410.19872","title":"Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey","created":"2024-10-24","cited_by_count":9,"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":"2408.15503","title":"RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments","created":"2024-08-28","cited_by_count":8,"area":null},{"id":"2208.06461","title":"Real-Time Accident Detection in Traffic Surveillance Using Deep Learning","created":"2022-08-12","cited_by_count":7,"area":null},{"id":"2210.13827","title":"End-to-end Transformer for Compressed Video Quality Enhancement","created":"2022-10-25","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":"2303.09044","title":"CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2110.10428","title":"Reconstruction of Fragmented Trajectories of Collective Motion using Hadamard Deep Autoencoders","created":"2021-10-20","cited_by_count":6,"area":null},{"id":"2209.14965","title":"DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment","created":"2022-09-29","cited_by_count":6,"area":null},{"id":"2402.00163","title":"Improving Object Detection Quality in Football Through Super-Resolution Techniques","created":"2024-01-31","cited_by_count":6,"area":null},{"id":"2404.19417","title":"Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World","created":"2024-04-30","cited_by_count":6,"area":null},{"id":"2406.05810","title":"ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Driving","created":"2024-06-09","cited_by_count":6,"area":null},{"id":"2309.07268","title":"So you think you can track?","created":"2023-09-13","cited_by_count":5,"area":null},{"id":"2403.16003","title":"Diverse Representation Embedding for Lifelong Person Re-Identification","created":"2024-03-24","cited_by_count":5,"area":null},{"id":"2407.08049","title":"Deep Learning-Based Robust Multi-Object Tracking via Fusion of mmWave Radar and Camera Sensors","created":"2024-07-10","cited_by_count":5,"area":null},{"id":"2108.10543","title":"Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting","created":"2021-08-24","cited_by_count":4,"area":null},{"id":"2309.15411","title":"3D Multiple Object Tracking on Autonomous Driving: A Literature Review","created":"2023-09-27","cited_by_count":4,"area":null},{"id":"2312.06136","title":"BACTrack: Building Appearance Collection for Aerial Tracking","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2401.08147","title":"Machine Learning on Dynamic Graphs: A Survey on Applications","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2412.00348","title":"Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey","created":"2024-11-30","cited_by_count":4,"area":null},{"id":"2412.05548","title":"Street Gaussians without 3D Object Tracker","created":"2024-12-07","cited_by_count":4,"area":null},{"id":"2504.09361","title":"PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking","created":"2025-04-12","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":"2303.09731","title":"Exorcising ''Wraith'': Protecting LiDAR-based Object Detector in Automated Driving System from Appearing Attacks","created":"2023-03-17","cited_by_count":3,"area":null},{"id":"2406.05800","title":"SlowPerception: Physical-World Latency Attack against Visual Perception in Autonomous Driving","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2407.17272","title":"DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy","created":"2024-07-24","cited_by_count":3,"area":null},{"id":"2205.15495","title":"Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2206.02116","title":"Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos","created":"2022-06-05","cited_by_count":2,"area":null},{"id":"2207.10031","title":"MOTCOM: The Multi-Object Tracking Dataset Complexity Metric","created":"2022-07-20","cited_by_count":2,"area":null},{"id":"2304.10765","title":"BPJDet: Extended Object Representation for Generic Body-Part Joint Detection","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2306.16890","title":"Trajectory Poisson multi-Bernoulli mixture filter for traffic monitoring using a drone","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2307.14591","title":"The detection and rectification for identity-switch based on unfalsified control","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2308.12116","title":"The TYC Dataset for Understanding Instance-Level Semantics and Motions of Cells in Microstructures","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2308.15795","title":"Occlusion-Aware Detection and Re-ID Calibrated Network for Multi-Object Tracking","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2310.00783","title":"Propagating Semantic Labels in Video Data","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2312.10922","title":"NTrack: A Multiple-Object Tracker and Dataset for Infield Cotton Boll Counting","created":"2023-12-18","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":"2407.06018","title":"Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2407.15199","title":"Multiple Object Detection and Tracking in Panoramic Videos for Cycling Safety Analysis","created":"2024-07-21","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":"2410.04817","title":"Resource-Efficient Multiview Perception: Integrating Semantic Masking with Masked Autoencoders","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2505.08126","title":"Asynchronous Multi-Object Tracking with an Event Camera","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2508.13000","title":"Omni Survey for Multimodality Analysis in Visual Object Tracking","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2510.12753","title":"E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2601.10819","title":"A Unified 3D Object Perception Framework for Real-Time Outside-In Multi-Camera Systems","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2111.08954","title":"Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers","created":"2021-11-17","cited_by_count":1,"area":null},{"id":"2112.07159","title":"Birds Eye View Social Distancing Analysis System","created":"2021-12-14","cited_by_count":1,"area":null},{"id":"2207.08556","title":"A Certifiable Security Patch for Object Tracking in Self-Driving Systems via Historical Deviation Modeling","created":"2022-07-18","cited_by_count":1,"area":null},{"id":"2210.13570","title":"Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representations","created":"2022-10-24","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":"2310.19413","title":"CARPE-ID: Continuously Adaptable Re-identification for Personalized Robot Assistance","created":"2023-10-30","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":"2401.12480","title":"IDPro: Flexible Interactive Video Object Segmentation by ID-queried Concurrent Propagation","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2404.02562","title":"Representation Alignment Contrastive Regularization for Multi-Object Tracking","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2404.03110","title":"Ego-Motion Aware Target Prediction Module for Robust Multi-Object Tracking","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2406.01380","title":"Convolutional Unscented Kalman Filter for Multi-Object Tracking with Outliers","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2407.06000","title":"Bounding Boxes and Probabilistic Graphical Models: Video Anomaly Detection Simplified","created":"2024-07-08","cited_by_count":1,"area":null},{"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":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2508.20892","title":"To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.09962","title":"An HMM-based framework for identity-aware long-term multi-object tracking from sparse and uncertain identification: use case on long-term tracking in livestock","created":"2025-09-12","cited_by_count":1,"area":null}],"next_cursor":"100"}