{"total":214,"rows":[{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823,"area":null},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518,"area":null},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381,"area":null},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346,"area":null},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320,"area":null},{"id":"2111.14690","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","created":"2021-11-29","cited_by_count":217,"area":null},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213,"area":null},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192,"area":null},{"id":"2211.09791","title":"MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors","created":"2022-11-17","cited_by_count":148,"area":null},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146,"area":null},{"id":"2302.11813","title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","created":"2023-02-23","cited_by_count":132,"area":null},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2111.09621","title":"SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking","created":"2021-11-18","cited_by_count":103,"area":null},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97,"area":null},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93,"area":null},{"id":"2307.15700","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","created":"2023-07-28","cited_by_count":88,"area":null},{"id":"2103.07351","title":"Monocular Quasi-Dense 3D Object Tracking","created":"2021-03-12","cited_by_count":81,"area":null},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79,"area":null},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"id":"2308.00783","title":"Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking","created":"2023-08-01","cited_by_count":67,"area":null},{"id":"2211.14317","title":"Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space","created":"2022-11-24","cited_by_count":66,"area":null},{"id":"2303.10404","title":"MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking","created":"2023-03-18","cited_by_count":64,"area":null},{"id":"2212.03038","title":"Unifying Short and Long-Term Tracking with Graph Hierarchies","created":"2022-12-06","cited_by_count":62,"area":null},{"id":"2210.06984","title":"QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking","created":"2022-10-12","cited_by_count":61,"area":null},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60,"area":null},{"id":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60,"area":null},{"id":"2403.02075","title":"DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction","created":"2024-03-04","cited_by_count":59,"area":null},{"id":"2304.08408","title":"OVTrack: Open-Vocabulary Multiple Object Tracking","created":"2023-04-17","cited_by_count":53,"area":null},{"id":"2209.02540","title":"CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion","created":"2022-09-06","cited_by_count":50,"area":null},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50,"area":null},{"id":"2306.05238","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2202.11983","title":"GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021","created":"2022-02-24","cited_by_count":46,"area":null},{"id":"2206.04656","title":"Simple Cues Lead to a Strong Multi-Object Tracker","created":"2022-06-09","cited_by_count":44,"area":null},{"id":"2207.12978","title":"Tracking Every Thing in the Wild","created":"2022-07-26","cited_by_count":44,"area":null},{"id":"2106.11958","title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","created":"2021-06-22","cited_by_count":43,"area":null},{"id":"2103.15145","title":"TransCenter: Transformers with Dense Representations for Multiple-Object Tracking","created":"2021-03-28","cited_by_count":42,"area":null},{"id":"2305.14298","title":"MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking","created":"2023-05-23","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":"2207.05518","title":"Tracking Objects as Pixel-wise Distributions","created":"2022-07-12","cited_by_count":37,"area":null},{"id":"2112.02582","title":"PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation","created":"2021-12-05","cited_by_count":36,"area":null},{"id":"2209.14858","title":"4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation","created":"2022-09-29","cited_by_count":35,"area":null},{"id":"2202.12100","title":"DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion with Deep Association","created":"2022-02-24","cited_by_count":33,"area":null},{"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,"area":null},{"id":"2212.01247","title":"CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion","created":"2022-12-02","cited_by_count":31,"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":"2211.08824","title":"SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking","created":"2022-11-16","cited_by_count":29,"area":null},{"id":"2207.14012","title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","created":"2022-07-28","cited_by_count":28,"area":null},{"id":"2303.14346","title":"Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation","created":"2023-03-25","cited_by_count":27,"area":null},{"id":"2402.18115","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","created":"2024-02-28","cited_by_count":27,"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":"2302.14589","title":"Focus On Details: Online Multi-object Tracking with Diverse Fine-grained Representation","created":"2023-02-28","cited_by_count":25,"area":null},{"id":"2305.13495","title":"Type-to-Track: Retrieve Any Object via Prompt-based Tracking","created":"2023-05-22","cited_by_count":24,"area":null},{"id":"2310.16447","title":"ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors","created":"2023-10-25","cited_by_count":24,"area":null},{"id":"2303.12782","title":"Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation","created":"2023-03-22","cited_by_count":23,"area":null},{"id":"2406.00429","title":"Towards Generalizable Multi-Object Tracking","created":"2024-06-01","cited_by_count":23,"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":"2103.14829","title":"Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers","created":"2021-03-27","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":"2303.15334","title":"ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box","created":"2023-03-27","cited_by_count":20,"area":null},{"id":"2303.15904","title":"Mask-Free Video Instance Segmentation","created":"2023-03-28","cited_by_count":20,"area":null},{"id":"2305.12724","title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","created":"2023-05-22","cited_by_count":20,"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":"2408.09178","title":"MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model","created":"2024-08-17","cited_by_count":18,"area":null},{"id":"2105.02426","title":"Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking","created":"2021-05-06","cited_by_count":17,"area":null},{"id":"2212.01568","title":"Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation","created":"2022-12-03","cited_by_count":17,"area":null},{"id":"2404.05136","title":"Self-Supervised Multi-Object Tracking with Path Consistency","created":"2024-04-08","cited_by_count":16,"area":null},{"id":"2205.00968","title":"Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker","created":"2022-05-02","cited_by_count":15,"area":null},{"id":"2310.01926","title":"DARTH: Holistic Test-time Adaptation for Multiple Object Tracking","created":"2023-10-03","cited_by_count":15,"area":null},{"id":"2211.02175","title":"Large Scale Real-World Multi-Person Tracking","created":"2022-11-03","cited_by_count":14,"area":null},{"id":"2202.03747","title":"STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation","created":"2022-02-08","cited_by_count":13,"area":null},{"id":"2303.14395","title":"MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos","created":"2023-03-25","cited_by_count":13,"area":null},{"id":"2306.10681","title":"VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision","created":"2023-06-19","cited_by_count":13,"area":null},{"id":"2402.02941","title":"Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey","created":"2024-02-05","cited_by_count":13,"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":"2210.10771","title":"Multi-view Tracking Using Weakly Supervised Human Motion Prediction","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2212.11920","title":"Beyond SOT: Tracking Multiple Generic Objects at Once","created":"2022-12-22","cited_by_count":11,"area":null},{"id":"2303.16628","title":"DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking","created":"2023-03-29","cited_by_count":11,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2303.17228","title":"Streaming Video Model","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2308.05911","title":"Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking","created":"2023-08-11","cited_by_count":10,"area":null},{"id":"2412.06708","title":"FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies","created":"2024-12-09","cited_by_count":10,"area":null},{"id":"2207.07454","title":"Multi-Object Tracking and Segmentation via Neural Message Passing","created":"2022-07-15","cited_by_count":9,"area":null},{"id":"2302.09043","title":"Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences","created":"2023-02-17","cited_by_count":9,"area":null},{"id":"2308.11450","title":"Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Tracking","created":"2023-08-22","cited_by_count":9,"area":null},{"id":"2403.02767","title":"DeconfuseTrack:Dealing with Confusion for Multi-Object Tracking","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2412.00133","title":"ETAP: Event-based Tracking of Any Point","created":"2024-11-28","cited_by_count":9,"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":"2208.07479","title":"Context-Aware Streaming Perception in Dynamic Environments","created":"2022-08-16","cited_by_count":8,"area":null},{"id":"2210.09455","title":"Track Targets by Dense Spatio-Temporal Position Encoding","created":"2022-10-17","cited_by_count":8,"area":null},{"id":"2211.09108","title":"Robust Online Video Instance Segmentation with Track Queries","created":"2022-11-16","cited_by_count":8,"area":null},{"id":"2303.00977","title":"Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning","created":"2023-03-02","cited_by_count":8,"area":null},{"id":"2304.08709","title":"You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking","created":"2023-04-18","cited_by_count":8,"area":null},{"id":"2309.00942","title":"Tracking without Label: Unsupervised Multiple Object Tracking via Contrastive Similarity Learning","created":"2023-09-02","cited_by_count":8,"area":null},{"id":"2309.04422","title":"Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving","created":"2023-09-08","cited_by_count":8,"area":null},{"id":"2403.08018","title":"Learning Data Association for Multi-Object Tracking using Only Coordinates","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2407.04249","title":"FeatureSORT: Essential Features for Effective Tracking","created":"2024-07-05","cited_by_count":8,"area":null}],"next_cursor":"100"}