{"list":"other","total":78,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"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":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220},{"id":"1804.00518","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","created":"2018-03-26","cited_by_count":208},{"id":"2003.06761","title":"Siamese Box Adaptive Network for Visual Tracking","created":"2020-03-15","cited_by_count":189},{"id":"1911.06188","title":"SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines","created":"2019-11-14","cited_by_count":177},{"id":"1911.07241","title":"SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking","created":"2019-11-17","cited_by_count":148},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143},{"id":"2207.09603","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","created":"2022-07-20","cited_by_count":137},{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126},{"id":"2203.05328","title":"Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking","created":"2022-03-10","cited_by_count":119},{"id":"2203.11192","title":"Transforming Model Prediction for Tracking","created":"2022-03-21","cited_by_count":117},{"id":"2303.16580","title":"Generalized Relation Modeling for Transformer Tracking","created":"2023-03-29","cited_by_count":93},{"id":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","cited_by_count":82},{"id":"2403.10574","title":"Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers","created":"2024-03-15","cited_by_count":76},{"id":"2108.00202","title":"HiFT: Hierarchical Feature Transformer for Aerial Tracking","created":"2021-07-31","cited_by_count":72},{"id":"2311.02072","title":"HIPTrack: Visual Tracking with Historical Prompts","created":"2023-11-03","cited_by_count":71},{"id":"2011.11204","title":"Graph Attention Tracking","created":"2020-11-23","cited_by_count":70},{"id":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70},{"id":"2203.01885","title":"TCTrack: Temporal Contexts for Aerial Tracking","created":"2022-03-03","cited_by_count":69},{"id":"2108.00803","title":"Learn to Match: Automatic Matching Network Design for Visual Tracking","created":"2021-08-02","cited_by_count":67},{"id":"1804.04273","title":"VITAL: VIsual Tracking via Adversarial Learning","created":"2018-04-12","cited_by_count":65},{"id":"2303.12027","title":"Joint Visual Grounding and Tracking with Natural Language Specification","created":"2023-03-21","cited_by_count":59},{"id":"2312.17133","title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","created":"2023-12-28","cited_by_count":59},{"id":"2305.15896","title":"MixFormerV2: Efficient Fully Transformer Tracking","created":"2023-05-25","cited_by_count":57},{"id":"2412.19138","title":"SUTrack: Towards Simple and Unified Single Object Tracking","created":"2024-12-26","cited_by_count":52},{"id":"2401.03142","title":"Explicit Visual Prompts for Visual Object Tracking","created":"2024-01-06","cited_by_count":50},{"id":"2207.01076","title":"Divert More Attention to Vision-Language Tracking","created":"2022-07-03","cited_by_count":47},{"id":"2112.02838","title":"Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook","created":"2021-12-06","cited_by_count":46},{"id":"2205.10851","title":"Vision-based Anti-UAV Detection and Tracking","created":"2022-05-22","cited_by_count":44},{"id":"2412.11023","title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","created":"2024-12-15","cited_by_count":37},{"id":"2308.11322","title":"CiteTracker: Correlating Image and Text for Visual Tracking","created":"2023-08-22","cited_by_count":36},{"id":"2101.08446","title":"All-Day Object Tracking for Unmanned Aerial Vehicle","created":"2021-01-21","cited_by_count":28},{"id":"2307.03373","title":"All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment","created":"2023-07-07","cited_by_count":27},{"id":"2401.11228","title":"Unifying Visual and Vision-Language Tracking via Contrastive Learning","created":"2024-01-20","cited_by_count":27},{"id":"2201.07425","title":"WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking","created":"2022-01-19","cited_by_count":26},{"id":"2308.10330","title":"Towards Real-World Visual Tracking with Temporal Contexts","created":"2023-08-20","cited_by_count":26},{"id":"2310.10071","title":"ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking","created":"2023-10-16","cited_by_count":25},{"id":"2503.06625","title":"Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking","created":"2025-03-09","cited_by_count":23},{"id":"2504.09228","title":"Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking","created":"2025-04-12","cited_by_count":22},{"id":"2503.06621","title":"Dynamic Updates for Language Adaptation in Visual-Language Tracking","created":"2025-03-09","cited_by_count":18},{"id":"2306.15767","title":"Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV System","created":"2023-06-27","cited_by_count":14},{"id":"2202.05659","title":"Tiny Object Tracking: A Large-scale Dataset and A Baseline","created":"2022-02-11","cited_by_count":11},{"id":"2412.13615","title":"MambaLCT: Boosting Tracking via Long-term Context State Space Model","created":"2024-12-18","cited_by_count":11},{"id":"2504.11967","title":"Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions","created":"2025-04-16","cited_by_count":11},{"id":"2507.19875","title":"ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking","created":"2025-07-26","cited_by_count":10},{"id":"2405.14200","title":"Awesome Multi-modal Object Tracking","created":"2024-05-23","cited_by_count":7},{"id":"2409.11785","title":"Distilling Channels for Efficient Deep Tracking","created":"2024-09-18","cited_by_count":5},{"id":"2411.15761","title":"MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking","created":"2024-11-24","cited_by_count":5},{"id":"2504.13604","title":"FocusTrack: A Self-Adaptive Local Sampling Algorithm for Efficient Anti-UAV Tracking","created":"2025-04-18","cited_by_count":5},{"id":"2505.04917","title":"A Simple Detector with Frame Dynamics is a Strong Tracker","created":"2025-05-08","cited_by_count":3},{"id":"2412.00626","title":"MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum Learning","created":"2024-12-01","cited_by_count":2},{"id":"2504.01321","title":"COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking","created":"2025-04-02","cited_by_count":2},{"id":"2508.13000","title":"Omni Survey for Multimodality Analysis in Visual Object Tracking","created":"2025-08-18","cited_by_count":2},{"id":"2511.18344","title":"A Tri-Modal Dataset and a Baseline System for Tracking Unmanned Aerial Vehicles","created":"2025-11-23","cited_by_count":2},{"id":"2512.02668","title":"UAUTrack: Towards Unified Multimodal Anti-UAV Visual Tracking","created":"2025-12-02","cited_by_count":1}],"next_cursor":null}