{"total":666,"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":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764,"area":null},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566,"area":null},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518,"area":null},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435,"area":null},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350,"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"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":"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":"2202.03958","title":"Uncertainty Modeling for Out-of-Distribution Generalization","created":"2022-02-08","cited_by_count":125,"area":null},{"id":"2106.04095","title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","created":"2021-06-08","cited_by_count":120,"area":null},{"id":"2108.08728","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","created":"2021-08-19","cited_by_count":114,"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":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91,"area":null},{"id":"2103.11568","title":"Cluster Contrast for Unsupervised Person Re-Identification","created":"2021-03-22","cited_by_count":89,"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":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75,"area":null},{"id":"2306.02898","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","created":"2023-06-05","cited_by_count":75,"area":null},{"id":"2103.16364","title":"ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification","created":"2021-03-30","cited_by_count":69,"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":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67,"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":"2108.07422","title":"Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences","created":"2021-08-17","cited_by_count":66,"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":"2107.02053","title":"MixStyle Neural Networks for Domain Generalization and Adaptation","created":"2021-07-05","cited_by_count":64,"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":"2206.10520","title":"SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Data","created":"2022-06-21","cited_by_count":63,"area":null},{"id":"2107.02156","title":"Do Different Tracking Tasks Require Different Appearance Models?","created":"2021-07-05","cited_by_count":62,"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":"2105.01922","title":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water","created":"2021-05-05","cited_by_count":61,"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":"2211.01917","title":"Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Dataset","created":"2022-11-03","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":"2203.14675","title":"Part-based Pseudo Label Refinement for Unsupervised Person Re-identification","created":"2022-03-28","cited_by_count":59,"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":"2103.12366","title":"Group-aware Label Transfer for Domain Adaptive Person Re-identification","created":"2021-03-23","cited_by_count":58,"area":null},{"id":"2206.07704","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","created":"2022-06-15","cited_by_count":58,"area":null},{"id":"2204.09331","title":"NFormer: Robust Person Re-identification with Neighbor Transformer","created":"2022-04-20","cited_by_count":57,"area":null},{"id":"2102.02267","title":"DEFT: Detection Embeddings for Tracking","created":"2021-02-03","cited_by_count":56,"area":null},{"id":"2103.11658","title":"Intra-Inter Camera Similarity for Unsupervised Person Re-Identification","created":"2021-03-22","cited_by_count":52,"area":null},{"id":"2108.02413","title":"IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID","created":"2021-08-05","cited_by_count":51,"area":null},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50,"area":null},{"id":"2108.02922","title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers","created":"2021-08-06","cited_by_count":49,"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":"2103.16178","title":"Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking","created":"2021-03-30","cited_by_count":47,"area":null},{"id":"2105.15076","title":"Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark","created":"2021-05-31","cited_by_count":47,"area":null},{"id":"2104.13643","title":"On the Unreasonable Effectiveness of Centroids in Image Retrieval","created":"2021-04-28","cited_by_count":45,"area":null},{"id":"2106.06133","title":"Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification","created":"2021-06-11","cited_by_count":45,"area":null},{"id":"2104.04163","title":"Combined Depth Space based Architecture Search For Person Re-identification","created":"2021-04-09","cited_by_count":44,"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":"2312.08952","title":"UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation","created":"2023-12-14","cited_by_count":44,"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":"2103.15145","title":"TransCenter: Transformers with Dense Representations for Multiple-Object Tracking","created":"2021-03-28","cited_by_count":42,"area":null},{"id":"2108.02452","title":"VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild","created":"2021-08-05","cited_by_count":39,"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":"2108.09039","title":"Video-based Person Re-identification with Spatial and Temporal Memory Networks","created":"2021-08-20","cited_by_count":35,"area":null},{"id":"2111.11892","title":"LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking","created":"2021-11-23","cited_by_count":34,"area":null},{"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,"area":null},{"id":"2105.14432","title":"TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification","created":"2021-05-30","cited_by_count":32,"area":null},{"id":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32,"area":null},{"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,"area":null},{"id":"2104.12961","title":"Unsupervised Multi-Source Domain Adaptation for Person Re-Identification","created":"2021-04-27","cited_by_count":30,"area":null},{"id":"2106.12733","title":"Feature Completion for Occluded Person Re-Identification","created":"2021-06-24","cited_by_count":30,"area":null},{"id":"2110.05741","title":"Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization","created":"2021-10-12","cited_by_count":30,"area":null},{"id":"2103.04618","title":"Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification","created":"2021-03-08","cited_by_count":29,"area":null},{"id":"2107.11878","title":"Spatio-Temporal Representation Factorization for Video-based Person Re-Identification","created":"2021-07-25","cited_by_count":29,"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":"2211.08824","title":"SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking","created":"2022-11-16","cited_by_count":29,"area":null},{"id":"2104.12233","title":"The 5th AI City Challenge","created":"2021-04-25","cited_by_count":28,"area":null},{"id":"2205.01551","title":"Cross-View Cross-Scene Multi-View Crowd Counting","created":"2022-05-03","cited_by_count":28,"area":null},{"id":"2404.02785","title":"Domain Generalization through Meta-Learning: A Survey","created":"2024-04-03","cited_by_count":28,"area":null},{"id":"2404.05072","title":"Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind","created":"2024-04-07","cited_by_count":28,"area":null},{"id":"2102.00813","title":"About Face: A Survey of Facial Recognition Evaluation","created":"2021-02-01","cited_by_count":27,"area":null},{"id":"2107.03576","title":"Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting","created":"2021-07-08","cited_by_count":27,"area":null},{"id":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26,"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":"2104.09441","title":"One More Check: Making \"Fake Background\" Be Tracked Again","created":"2021-04-19","cited_by_count":25,"area":null},{"id":"2111.05943","title":"Self-Supervised Multi-Object Tracking with Cross-Input Consistency","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2210.11940","title":"JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking","created":"2022-10-20","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":"2403.12573","title":"Lifting Multi-View Detection and Tracking to the Bird's Eye View","created":"2024-03-19","cited_by_count":25,"area":null},{"id":"2103.09013","title":"Dense Interaction Learning for Video-based Person Re-identification","created":"2021-03-16","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":"2305.13495","title":"Type-to-Track: Retrieve Any Object via Prompt-based Tracking","created":"2023-05-22","cited_by_count":24,"area":null},{"id":"2308.13229","title":"ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking","created":"2023-08-25","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":"2101.12521","title":"Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification","created":"2021-01-29","cited_by_count":23,"area":null},{"id":"2110.04764","title":"Deep learning-based person re-identification methods: A survey and outlook of recent works","created":"2021-10-10","cited_by_count":23,"area":null},{"id":"2204.10380","title":"The 6th AI City Challenge","created":"2022-04-21","cited_by_count":23,"area":null},{"id":"2101.12159","title":"Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking","created":"2021-01-28","cited_by_count":22,"area":null},{"id":"2109.14157","title":"Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id","created":"2021-09-29","cited_by_count":22,"area":null},{"id":"2110.03090","title":"Player Tracking and Identification in Ice Hockey","created":"2021-10-06","cited_by_count":22,"area":null},{"id":"2111.07868","title":"Tracking People with 3D Representations","created":"2021-11-15","cited_by_count":22,"area":null},{"id":"2202.08837","title":"Adiabatic Quantum Computing for Multi Object Tracking","created":"2022-02-17","cited_by_count":22,"area":null}],"next_cursor":"100"}