{"list":"other","total":80,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156},{"id":"2211.09791","title":"MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors","created":"2022-11-17","cited_by_count":148},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131},{"id":"2103.14258","title":"Learning to Track with Object Permanence","created":"2021-03-26","cited_by_count":119},{"id":"2007.14557","title":"Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking","created":"2020-07-29","cited_by_count":115},{"id":"2203.16761","title":"MeMOT: Multi-Object Tracking with Memory","created":"2022-03-31","cited_by_count":114},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110},{"id":"2111.09621","title":"SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking","created":"2021-11-18","cited_by_count":103},{"id":"2104.00194","title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","created":"2021-04-01","cited_by_count":93},{"id":"2307.15700","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","created":"2023-07-28","cited_by_count":88},{"id":"2205.03806","title":"Transformer Tracking with Cyclic Shifting Window Attention","created":"2022-05-08","cited_by_count":75},{"id":"2105.07014","title":"SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping","created":"2021-05-14","cited_by_count":74},{"id":"2308.00783","title":"Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking","created":"2023-08-01","cited_by_count":67},{"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},{"id":"2008.08063","title":"AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics","created":"2020-08-18","cited_by_count":63},{"id":"2107.02156","title":"Do Different Tracking Tasks Require Different Appearance Models?","created":"2021-07-05","cited_by_count":62},{"id":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60},{"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},{"id":"2108.10312","title":"Exploring Simple 3D Multi-Object Tracking for Autonomous Driving","created":"2021-08-23","cited_by_count":56},{"id":"2301.10938","title":"Compact Transformer Tracker with Correlative Masked Modeling","created":"2023-01-26","cited_by_count":50},{"id":"2205.12740","title":"SIoU Loss: More Powerful Learning for Bounding Box Regression","created":"2022-05-25","cited_by_count":49},{"id":"2306.05238","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","created":"2023-06-08","cited_by_count":48},{"id":"2604.17898","title":"ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval","created":"2026-04-20","cited_by_count":41},{"id":"2308.09905","title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking","created":"2023-08-19","cited_by_count":40},{"id":"2507.05631","title":"OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval","created":"2025-07-08","cited_by_count":40},{"id":"2509.24765","title":"Semantic-Aware Logical Reasoning via a Semiotic Framework","created":"2025-09-29","cited_by_count":32},{"id":"2405.18014","title":"Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model","created":"2024-05-28","cited_by_count":31},{"id":"2604.01617","title":"STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness","created":"2026-04-02","cited_by_count":26},{"id":"2604.18051","title":"INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval","created":"2026-04-20","cited_by_count":26},{"id":"2504.07745","title":"SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding","created":"2025-04-10","cited_by_count":25},{"id":"2601.02902","title":"Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning","created":"2026-01-06","cited_by_count":25},{"id":"2604.18037","title":"HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval","created":"2026-04-20","cited_by_count":24},{"id":"2406.00429","title":"Towards Generalizable Multi-Object Tracking","created":"2024-06-01","cited_by_count":23},{"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},{"id":"2306.17000","title":"MotionTrack: End-to-End Transformer-based Multi-Object Tracing with LiDAR-Camera Fusion","created":"2023-06-29","cited_by_count":19},{"id":"2506.03532","title":"GA-S$^3$: Comprehensive Social Network Simulation with Group Agents","created":"2025-06-04","cited_by_count":19},{"id":"2004.08178","title":"Highway Transformer: Self-Gating Enhanced Self-Attentive Networks","created":"2020-04-17","cited_by_count":18},{"id":"2408.09178","title":"MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model","created":"2024-08-17","cited_by_count":18},{"id":"2507.00029","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","created":"2025-06-17","cited_by_count":18},{"id":"2603.26341","title":"HINT: Composed Image Retrieval with Dual-path Compositional Contextualized Network","created":"2026-03-27","cited_by_count":18},{"id":"2407.20730","title":"Autogenic Language Embedding for Coherent Point Tracking","created":"2024-07-30","cited_by_count":17},{"id":"2603.29291","title":"MELT: Improve Composed Image Retrieval via the Modification Frequentation-Rarity Balance Network","created":"2026-03-31","cited_by_count":17},{"id":"2404.05136","title":"Self-Supervised Multi-Object Tracking with Path Consistency","created":"2024-04-08","cited_by_count":16},{"id":"2604.05516","title":"Coupling Macro Dynamics and Micro States for Long-Horizon Social Simulation","created":"2026-04-07","cited_by_count":15},{"id":"2507.00950","title":"MVP: Winning Solution to SMP Challenge 2025 Video Track","created":"2025-07-01","cited_by_count":14},{"id":"2604.06600","title":"IntervenSim: Intervention-Aware Social Network Simulation for Opinion Dynamics","created":"2026-04-08","cited_by_count":11},{"id":"2407.04249","title":"FeatureSORT: Essential Features for Effective Tracking","created":"2024-07-05","cited_by_count":8},{"id":"2409.00487","title":"TrackSSM: A General Motion Predictor by State-Space Model","created":"2024-08-31","cited_by_count":6},{"id":"2409.17221","title":"Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs","created":"2024-09-25","cited_by_count":4},{"id":"2002.11338","title":"Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units","created":"2020-02-26","cited_by_count":3},{"id":"2604.12665","title":"Hypergraph-State Collaborative Reasoning for Multi-Object Tracking","created":"2026-04-14","cited_by_count":2},{"id":"2509.21715","title":"Motion-Aware Transformer for Multi-Object Tracking","created":"2025-09-26","cited_by_count":1}],"next_cursor":null}