{"total":94,"rows":[{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"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":"2108.09518","title":"MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?","created":"2021-08-21","cited_by_count":69,"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":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50,"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":"2104.11487","title":"Skip-Convolutions for Efficient Video Processing","created":"2021-04-23","cited_by_count":32,"area":null},{"id":"2210.07681","title":"Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?","created":"2022-10-14","cited_by_count":29,"area":null},{"id":"2108.06029","title":"Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking","created":"2021-08-13","cited_by_count":26,"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":"2303.09757","title":"Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior","created":"2023-03-17","cited_by_count":22,"area":null},{"id":"2210.10046","title":"A Tri-Layer Plugin to Improve Occluded Detection","created":"2022-10-18","cited_by_count":21,"area":null},{"id":"2306.02585","title":"MotionTrack: Learning Motion Predictor for Multiple Object Tracking","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2304.10893","title":"FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval system","created":"2023-04-21","cited_by_count":15,"area":null},{"id":"2203.10939","title":"Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2204.02397","title":"SALISA: Saliency-based Input Sampling for Efficient Video Object Detection","created":"2022-04-05","cited_by_count":12,"area":null},{"id":"2309.08382","title":"Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation Surveillance","created":"2023-09-15","cited_by_count":12,"area":null},{"id":"2306.15333","title":"Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning","created":"2023-06-27","cited_by_count":11,"area":null},{"id":"2404.13868","title":"TeamTrack: A Dataset for Multi-Sport Multi-Object Tracking in Full-pitch Videos","created":"2024-04-22","cited_by_count":11,"area":null},{"id":"2110.07790","title":"DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception","created":"2021-10-15","cited_by_count":10,"area":null},{"id":"2410.20371","title":"Open-Vocabulary Object Detection via Language Hierarchy","created":"2024-10-27","cited_by_count":10,"area":null},{"id":"2207.13050","title":"Efficient High-Resolution Deep Learning: A Survey","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2311.00987","title":"CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2106.10950","title":"Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation","created":"2021-06-21","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":"2111.12301","title":"Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction","created":"2021-11-24","cited_by_count":7,"area":null},{"id":"2207.00172","title":"Turbo: Opportunistic Enhancement for Edge Video Analytics","created":"2022-06-29","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":"2305.17648","title":"Z-GMOT: Zero-shot Generic Multiple Object Tracking","created":"2023-05-28","cited_by_count":7,"area":null},{"id":"2404.06997","title":"Agent-driven Generative Semantic Communication with Cross-Modality and Prediction","created":"2024-04-10","cited_by_count":7,"area":null},{"id":"2110.05561","title":"UrbanNet: Leveraging Urban Maps for Long Range 3D Object Detection","created":"2021-10-11","cited_by_count":6,"area":null},{"id":"2403.13803","title":"Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2103.12511","title":"Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking","created":"2021-03-23","cited_by_count":5,"area":null},{"id":"2109.09165","title":"Traffic-Net: 3D Traffic Monitoring Using a Single Camera","created":"2021-09-19","cited_by_count":5,"area":null},{"id":"2309.07268","title":"So you think you can track?","created":"2023-09-13","cited_by_count":5,"area":null},{"id":"2309.13610","title":"VisionKG: Unleashing the Power of Visual Datasets via Knowledge Graph","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2303.06202","title":"A POV-based Highway Vehicle Trajectory Dataset and Prediction Architecture","created":"2023-03-10","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":"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":"2102.02625","title":"Safety Case Templates for Autonomous Systems","created":"2021-01-29","cited_by_count":3,"area":null},{"id":"2105.14993","title":"Urban Traffic Surveillance (UTS): A fully probabilistic 3D tracking approach based on 2D detections","created":"2021-05-31","cited_by_count":3,"area":null},{"id":"2308.14833","title":"The Interstate-24 3D Dataset: a new benchmark for 3D multi-camera vehicle tracking","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2403.18908","title":"Enhancing Multiple Object Tracking Accuracy via Quantum Annealing","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2408.13031","title":"VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models","created":"2024-08-23","cited_by_count":3,"area":null},{"id":"2503.23249","title":"Context in object detection: a systematic literature review","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2507.08729","title":"RoundaboutHD: High-Resolution Real-World Urban Environment Benchmark for Multi-Camera Vehicle Tracking","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2507.16254","title":"Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2109.07298","title":"FFAVOD: Feature Fusion Architecture for Video Object Detection","created":"2021-09-15","cited_by_count":2,"area":null},{"id":"2302.09429","title":"NU-AIR -- A Neuromorphic Urban Aerial Dataset for Detection and Localization of Pedestrians and Vehicles","created":"2023-02-18","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":"2602.05414","title":"TSBOW -- Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2605.11508","title":"LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2106.09932","title":"A Framework for Real-time Traffic Trajectory Tracking, Speed Estimation, and Driver Behavior Calibration at Urban Intersections Using Virtual Traffic Lanes","created":"2021-06-18","cited_by_count":1,"area":null},{"id":"2109.12414","title":"Vehicle Detection and Tracking From Surveillance Cameras in Urban Scenes","created":"2021-09-25","cited_by_count":1,"area":null},{"id":"2204.07442","title":"Scalable and Real-time Multi-Camera Vehicle Detection, Re-Identification, and Tracking","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2208.03571","title":"Transformer-based assignment decision network for multiple object tracking","created":"2022-08-06","cited_by_count":1,"area":null},{"id":"2308.08717","title":"EdgeMA: Model Adaptation System for Real-Time Video Analytics on Edge Devices","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2404.11226","title":"Simple In-place Data Augmentation for Surveillance Object Detection","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2506.22562","title":"Improving Token-based Object Detection with Video","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2507.06513","title":"What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2507.08375","title":"Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2510.24374","title":"Decoupling What to Count and Where to See for Referring Expression Counting","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.12342","title":"Ground Plane Projection for Improved Traffic Analytics at Intersections","created":"2025-11-15","cited_by_count":1,"area":null},{"id":"2601.09531","title":"Bipartite Mode Matching for Vision Training Set Search from a Hierarchical Data Server","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2602.18394","title":"Self-Aware Object Detection via Degradation Manifolds","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2104.05823","title":"Localization-Based Tracking","created":"2021-04-12","cited_by_count":0,"area":null},{"id":"2105.08416","title":"Improved detection of small objects in road network sequences","created":"2021-05-18","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":"2201.06824","title":"STURE: Spatial-Temporal Mutual Representation Learning for Robust Data Association in Online Multi-Object Tracking","created":"2022-01-18","cited_by_count":0,"area":null},{"id":"2301.00393","title":"A principled distributional approach to trajectory similarity measurement","created":"2023-01-01","cited_by_count":0,"area":null},{"id":"2309.14468","title":"FARSEC: A Reproducible Framework for Automatic Real-Time Vehicle Speed Estimation Using Traffic Cameras","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2310.14294","title":"Deep MDP: A Modular Framework for Multi-Object Tracking","created":"2023-10-22","cited_by_count":0,"area":null},{"id":"2311.07928","title":"Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2406.10469","title":"Object-Attribute-Relation Representation Based Video Semantic Communication","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2506.02765","title":"A Dynamic Transformer Network for Vehicle Detection","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2507.03564","title":"2.5D Object Detection for Intelligent Roadside Infrastructure","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2508.04868","title":"Dual-Stream Attention with Multi-Modal Queries for Object Detection in Transportation Applications","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2508.12082","title":"Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2508.19864","title":"Self-supervised structured object representation learning","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2601.14568","title":"Breaking the accuracy-resource dilemma: a lightweight adaptive video inference enhancement","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.05970","title":"Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.20708","title":"High-Quality and Efficient Turbulence Mitigation with Events","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2604.09681","title":"R2E-VID: Two-Stage Robust Routing via Temporal Gating for Elastic Edge-Cloud Video Inference","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.12470","title":"Intelligent ROI-Based Vehicle Counting Framework for Automated Traffic Monitoring","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.16783","title":"EdgeVTP: Exploration of Latency-efficient Trajectory Prediction for Edge-based Embedded Vision Applications","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2604.24419","title":"BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Cities","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.15423","title":"MR2-ByteTrack: CNN and Transformer-based Video Object Detection for AI-augmented Embedded Vision Sensor Nodes","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.08541","title":"VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.10949","title":"Unsupervised Detection of Entry and Exit Regions from Vehicle Trajectories for Camera-Agnostic Turning Movement Counts","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.19911","title":"LoRFT: Benchmarking Long-Range Vehicle Trajectory Reconstruction from Fixed Highway Cameras","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.16632","title":"DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detection","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.34142","title":"Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01282","title":"Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}