{"list":"other","total":103,"rows":[{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"1701.07717","title":"Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro","created":"2017-01-26","cited_by_count":281},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1904.07223","title":"Joint Discriminative and Generative Learning for Person Re-identification","created":"2019-04-15","cited_by_count":213},{"id":"2211.13977","title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","created":"2022-11-25","cited_by_count":181},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"1903.09254","title":"CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification","created":"2019-03-21","cited_by_count":119},{"id":"2107.12666","title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","created":"2021-07-27","cited_by_count":110},{"id":"1703.07475","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","created":"2017-03-22","cited_by_count":101},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"2012.03753","title":"Unsupervised Pre-training for Person Re-identification","created":"2020-12-07","cited_by_count":95},{"id":"2205.00613","title":"MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries","created":"2022-05-02","cited_by_count":91},{"id":"1803.10859","title":"Features for Multi-Target Multi-Camera Tracking and Re-Identification","created":"2018-03-28","cited_by_count":88},{"id":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80},{"id":"2007.07247","title":"Multiview Detection with Feature Perspective Transformation","created":"2020-07-14","cited_by_count":71},{"id":"1912.00535","title":"Deep Learning for Visual Tracking: A Comprehensive Survey","created":"2019-12-02","cited_by_count":61},{"id":"2111.09571","title":"Person Re-identification Method Based on Color Attack and Joint Defence","created":"2021-11-18","cited_by_count":56},{"id":"2103.04337","title":"Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification","created":"2021-03-07","cited_by_count":45},{"id":"1704.05775","title":"Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection","created":"2017-04-19","cited_by_count":42},{"id":"2304.04617","title":"VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views","created":"2023-04-10","cited_by_count":38},{"id":"1702.04593","title":"Deep Multi-camera People Detection","created":"2017-02-15","cited_by_count":37},{"id":"2108.09039","title":"Video-based Person Re-identification with Spatial and Temporal Memory Networks","created":"2021-08-20","cited_by_count":35},{"id":"2308.03322","title":"Part-Aware Transformer for Generalizable Person Re-identification","created":"2023-08-07","cited_by_count":35},{"id":"2111.11892","title":"LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking","created":"2021-11-23","cited_by_count":34},{"id":"1711.08766","title":"Region-based Quality Estimation Network for Large-scale Person Re-identification","created":"2017-11-23","cited_by_count":33},{"id":"2203.14208","title":"Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking","created":"2022-03-27","cited_by_count":33},{"id":"2310.13350","title":"EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View","created":"2023-10-20","cited_by_count":33},{"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},{"id":"2106.06856","title":"DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking","created":"2021-06-12","cited_by_count":31},{"id":"2111.15157","title":"MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark","created":"2021-11-30","cited_by_count":29},{"id":"2104.01745","title":"A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification","created":"2021-04-05","cited_by_count":28},{"id":"2401.06825","title":"Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification","created":"2024-01-12","cited_by_count":27},{"id":"2403.12573","title":"Lifting Multi-View Detection and Tracking to the Bird's Eye View","created":"2024-03-19","cited_by_count":25},{"id":"1901.10177","title":"Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding","created":"2019-01-29","cited_by_count":22},{"id":"2304.14122","title":"Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification","created":"2023-04-27","cited_by_count":21},{"id":"2312.16797","title":"Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification","created":"2023-12-28","cited_by_count":20},{"id":"1712.09531","title":"Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project","created":"2017-12-27","cited_by_count":19},{"id":"2312.05719","title":"DVANet: Disentangling View and Action Features for Multi-View Action Recognition","created":"2023-12-10","cited_by_count":19},{"id":"2403.19316","title":"Hypergraph-based Multi-View Action Recognition using Event Cameras","created":"2024-03-28","cited_by_count":19},{"id":"2105.06623","title":"City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones","created":"2021-05-14","cited_by_count":18},{"id":"2212.09258","title":"CHAD: Charlotte Anomaly Dataset","created":"2022-12-19","cited_by_count":18},{"id":"2302.07676","title":"DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes","created":"2023-02-15","cited_by_count":17},{"id":"1809.00421","title":"Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition","created":"2018-09-03","cited_by_count":16},{"id":"1904.10681","title":"A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition","created":"2019-04-24","cited_by_count":16},{"id":"2211.04656","title":"MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification","created":"2022-11-09","cited_by_count":16},{"id":"2303.10280","title":"Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances","created":"2023-03-17","cited_by_count":16},{"id":"2311.03828","title":"Multi-view Information Integration and Propagation for Occluded Person Re-identification","created":"2023-11-07","cited_by_count":16},{"id":"2003.06994","title":"Multi-Drone based Single Object Tracking with Agent Sharing Network","created":"2020-03-16","cited_by_count":14},{"id":"2105.01213","title":"Multi-Target Multi-Camera Tracking of Vehicles using Metadata-Aided Re-ID and Trajectory-Based Camera Link Model","created":"2021-05-03","cited_by_count":14},{"id":"2503.04565","title":"Omnidirectional Multi-Object Tracking","created":"2025-03-06","cited_by_count":13},{"id":"2503.08121","title":"AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification","created":"2025-03-11","cited_by_count":13},{"id":"2104.14236","title":"Learning Multi-Attention Context Graph for Group-Based Re-Identification","created":"2021-04-29","cited_by_count":12},{"id":"2210.10771","title":"Multi-view Tracking Using Weakly Supervised Human Motion Prediction","created":"2022-10-19","cited_by_count":11},{"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},{"id":"1505.06821","title":"Deep Ranking for Person Re-identification via Joint Representation Learning","created":"2015-05-26","cited_by_count":10},{"id":"2202.09124","title":"Multi-view and Multi-modal Event Detection Utilizing Transformer-based Multi-sensor fusion","created":"2022-02-18","cited_by_count":9},{"id":"2412.00692","title":"MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos","created":"2024-12-01","cited_by_count":9},{"id":"1605.02464","title":"Orientation Driven Bag of Appearances for Person Re-identification","created":"2016-05-09","cited_by_count":8},{"id":"1901.02626","title":"MOANA: An Online Learned Adaptive Appearance Model for Robust Multiple Object Tracking in 3D","created":"2019-01-09","cited_by_count":8},{"id":"1911.12512","title":"Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect","created":"2019-11-28","cited_by_count":8},{"id":"2408.13243","title":"MCTR: Multi Camera Tracking Transformer","created":"2024-08-23","cited_by_count":8},{"id":"2410.21938","title":"ReMix: Training Generalized Person Re-identification on a Mixture of Data","created":"2024-10-29","cited_by_count":8},{"id":"2202.10881","title":"Coordinate-Aligned Multi-Camera Collaboration for Active Multi-Object Tracking","created":"2022-02-22","cited_by_count":7},{"id":"2205.04383","title":"Online Unsupervised Domain Adaptation for Person Re-identification","created":"2022-05-09","cited_by_count":7},{"id":"2211.09663","title":"Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach","created":"2022-11-17","cited_by_count":7},{"id":"1607.06408","title":"Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking","created":"2016-07-21","cited_by_count":6},{"id":"2206.02373","title":"Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports","created":"2022-06-06","cited_by_count":6},{"id":"2308.10716","title":"Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification","created":"2023-08-21","cited_by_count":6},{"id":"2308.10717","title":"Rethinking Person Re-identification from a Projection-on-Prototypes Perspective","created":"2023-08-21","cited_by_count":6},{"id":"2401.15900","title":"MV2MAE: Multi-View Video Masked Autoencoders","created":"2024-01-29","cited_by_count":6},{"id":"2405.01101","title":"Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination","created":"2024-05-02","cited_by_count":6},{"id":"2410.03302","title":"Action Selection Learning for Multi-label Multi-view Action Recognition","created":"2024-10-04","cited_by_count":6},{"id":"2411.15106","title":"About Time: Advances, Challenges, and Outlooks of Action Understanding","created":"2024-11-22","cited_by_count":6},{"id":"2503.10982","title":"Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume","created":"2025-03-14","cited_by_count":6},{"id":"2506.01373","title":"No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and Beyond","created":"2025-06-02","cited_by_count":6},{"id":"2009.06599","title":"Collaborative Attention Mechanism for Multi-View Action Recognition","created":"2020-09-14","cited_by_count":5},{"id":"2302.03820","title":"A Unified Multi-view Multi-person Tracking Framework","created":"2023-02-08","cited_by_count":5},{"id":"2403.20225","title":"MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark","created":"2024-03-29","cited_by_count":5},{"id":"2404.08264","title":"Guided Masked Self-Distillation Modeling for Distributed Multimedia Sensor Event Analysis","created":"2024-04-12","cited_by_count":5},{"id":"2411.14695","title":"Anti-Forgetting Adaptation for Unsupervised Person Re-identification","created":"2024-11-22","cited_by_count":5},{"id":"2501.13829","title":"MV-GMN: State Space Model for Multi-View Action Recognition","created":"2025-01-23","cited_by_count":5},{"id":"2502.20111","title":"MITracker: Multi-View Integration for Visual Object Tracking","created":"2025-02-27","cited_by_count":5},{"id":"2209.02986","title":"Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition","created":"2022-09-07","cited_by_count":4},{"id":"2504.02287","title":"MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion","created":"2025-04-03","cited_by_count":4},{"id":"2311.08393","title":"MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation","created":"2023-11-14","cited_by_count":3},{"id":"2303.14358","title":"Multi-view knowledge distillation transformer for human action recognition","created":"2023-03-25","cited_by_count":2},{"id":"2307.02753","title":"CityTrack: Improving City-Scale Multi-Camera Multi-Target Tracking by Location-Aware Tracking and Box-Grained Matching","created":"2023-07-06","cited_by_count":2},{"id":"2405.11345","title":"City-Scale Multi-Camera Vehicle Tracking System with Improved Self-Supervised Camera Link Model","created":"2024-05-18","cited_by_count":2},{"id":"2409.11749","title":"RockTrack: A 3D Robust Multi-Camera-Ken Multi-Object Tracking Framework","created":"2024-09-18","cited_by_count":2},{"id":"2504.03047","title":"Attention-Aware Multi-View Pedestrian Tracking","created":"2025-04-03","cited_by_count":2},{"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},{"id":"1904.02553","title":"Generic Multiview Visual Tracking","created":"2019-04-04","cited_by_count":1},{"id":"2207.02631","title":"Context Sensing Attention Network for Video-based Person Re-identification","created":"2022-07-06","cited_by_count":1},{"id":"2401.14132","title":"Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras","created":"2024-01-25","cited_by_count":1},{"id":"2410.02638","title":"Spatial-Temporal Multi-Cuts for Online Multiple-Camera Vehicle Tracking","created":"2024-10-03","cited_by_count":1},{"id":"2411.15811","title":"FastTrackTr:Towards Fast Multi-Object Tracking with Transformers","created":"2024-11-24","cited_by_count":1}],"next_cursor":"100"}