{"list":"other","total":115,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"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":"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":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"1804.08150","title":"Deep Learning in Spiking Neural Networks","created":"2018-04-22","cited_by_count":263},{"id":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2009.03465","title":"LaSOT: A High-quality Large-scale Single Object Tracking Benchmark","created":"2020-09-08","cited_by_count":132},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","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":"1805.08982","title":"RGB-T Object Tracking:Benchmark and Baseline","created":"2018-05-23","cited_by_count":121},{"id":"2104.13202","title":"LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking","created":"2021-04-27","cited_by_count":96},{"id":"2204.04120","title":"Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline","created":"2022-04-08","cited_by_count":91},{"id":"2304.05172","title":"LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images","created":"2023-04-11","cited_by_count":87},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"id":"2108.13962","title":"DepthTrack : Unveiling the Power of RGBD Tracking","created":"2021-08-31","cited_by_count":67},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65},{"id":"1908.11714","title":"Multi-Modal Fusion for End-to-End RGB-T Tracking","created":"2019-08-30","cited_by_count":63},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62},{"id":"2207.14571","title":"Prompting for Multi-Modal Tracking","created":"2022-07-29","cited_by_count":59},{"id":"2303.12027","title":"Joint Visual Grounding and Tracking with Natural Language Specification","created":"2023-03-21","cited_by_count":59},{"id":"2412.15691","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","created":"2024-12-20","cited_by_count":57},{"id":"2007.13143","title":"Challenge-Aware RGBT Tracking","created":"2020-07-26","cited_by_count":53},{"id":"2211.11010","title":"Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric","created":"2022-11-20","cited_by_count":52},{"id":"2412.19138","title":"SUTrack: Towards Simple and Unified Single Object Tracking","created":"2024-12-26","cited_by_count":52},{"id":"2007.02041","title":"Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking","created":"2020-07-04","cited_by_count":48},{"id":"2207.01076","title":"Divert More Attention to Vision-Language Tracking","created":"2022-07-03","cited_by_count":47},{"id":"2312.10611","title":"Bi-directional Adapter for Multi-modal Tracking","created":"2023-12-17","cited_by_count":46},{"id":"2108.05630","title":"3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud","created":"2021-08-12","cited_by_count":45},{"id":"2403.16002","title":"SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking","created":"2024-03-24","cited_by_count":44},{"id":"2305.15688","title":"Frame-Event Alignment and Fusion Network for High Frame Rate Tracking","created":"2023-05-25","cited_by_count":43},{"id":"2307.04129","title":"Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers","created":"2023-07-09","cited_by_count":43},{"id":"2208.09787","title":"RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking","created":"2022-08-21","cited_by_count":42},{"id":"1907.07485","title":"Multi-Adapter RGBT Tracking","created":"2019-07-17","cited_by_count":38},{"id":"2308.11322","title":"CiteTracker: Correlating Image and Text for Visual Tracking","created":"2023-08-22","cited_by_count":36},{"id":"2011.07188","title":"Duality-Gated Mutual Condition Network for RGBT Tracking","created":"2020-11-14","cited_by_count":35},{"id":"1811.10863","title":"Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters","created":"2018-11-27","cited_by_count":33},{"id":"2309.01728","title":"Generative-based Fusion Mechanism for Multi-Modal Tracking","created":"2023-09-04","cited_by_count":33},{"id":"1907.00618","title":"CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark","created":"2019-07-01","cited_by_count":32},{"id":"1912.06316","title":"Grounding-Tracking-Integration","created":"2019-12-13","cited_by_count":32},{"id":"2011.07189","title":"RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss","created":"2020-11-14","cited_by_count":32},{"id":"2401.01244","title":"Temporal Adaptive RGBT Tracking with Modality Prompt","created":"2024-01-02","cited_by_count":30},{"id":"2406.10638","title":"Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly","created":"2024-06-15","cited_by_count":30},{"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":"1907.11751","title":"Real-time Visual Object Tracking with Natural Language Description","created":"2019-07-26","cited_by_count":26},{"id":"1912.00660","title":"DAL -- A Deep Depth-aware Long-term Tracker","created":"2019-12-02","cited_by_count":26},{"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":"2201.08673","title":"Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking","created":"2022-01-21","cited_by_count":26},{"id":"2403.03493","title":"VastTrack: Vast Category Visual Object Tracking","created":"2024-03-06","cited_by_count":26},{"id":"2211.12735","title":"Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration","created":"2022-11-23","cited_by_count":24},{"id":"2403.19975","title":"Context-Aware Integration of Language and Visual References for Natural Language Tracking","created":"2024-03-29","cited_by_count":22},{"id":"2404.18174","title":"Mamba-FETrack: Frame-Event Tracking via State Space Model","created":"2024-04-28","cited_by_count":22},{"id":"2304.14394","title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking","created":"2023-04-27","cited_by_count":21},{"id":"2312.16244","title":"Modality-missing RGBT Tracking: Invertible Prompt Learning and High-quality Benchmarks","created":"2023-12-25","cited_by_count":17},{"id":"2401.02826","title":"CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras","created":"2024-01-05","cited_by_count":17},{"id":"2408.08827","title":"RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba","created":"2024-08-16","cited_by_count":17},{"id":"2405.19818","title":"WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark","created":"2024-05-30","cited_by_count":15},{"id":"2408.02222","title":"Cross-modulated Attention Transformer for RGBT Tracking","created":"2024-08-05","cited_by_count":14},{"id":"2408.07889","title":"MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking","created":"2024-08-15","cited_by_count":14},{"id":"1912.02854","title":"An Accelerated Correlation Filter Tracker","created":"2019-12-05","cited_by_count":12},{"id":"2303.13885","title":"ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data","created":"2023-03-24","cited_by_count":12},{"id":"2410.02492","title":"DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM","created":"2024-10-03","cited_by_count":12},{"id":"2411.01756","title":"ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model","created":"2024-11-04","cited_by_count":12},{"id":"2012.04176","title":"Multi-modal Visual Tracking: Review and Experimental Comparison","created":"2020-12-08","cited_by_count":11},{"id":"2103.07302","title":"Siamese Infrared and Visible Light Fusion Network for RGB-T Tracking","created":"2021-03-12","cited_by_count":11},{"id":"2203.14134","title":"RGBD Object Tracking: An In-depth Review","created":"2022-03-26","cited_by_count":11},{"id":"2307.10046","title":"Divert More Attention to Vision-Language Object Tracking","created":"2023-07-19","cited_by_count":11},{"id":"2401.01674","title":"Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens","created":"2024-01-03","cited_by_count":11},{"id":"2410.11586","title":"Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation","created":"2024-10-15","cited_by_count":11},{"id":"2502.06583","title":"Adaptive Perception for Unified Visual Multi-modal Object Tracking","created":"2025-02-10","cited_by_count":11},{"id":"2005.04063","title":"TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generator","created":"2020-05-08","cited_by_count":10},{"id":"2406.20024","title":"eMoE-Tracker: Environmental MoE-based Transformer for Robust Event-guided Object Tracking","created":"2024-06-28","cited_by_count":10},{"id":"2409.08887","title":"Visual Language Tracking with Multi-modal Interaction: A Robust Benchmark","created":"2024-09-13","cited_by_count":10},{"id":"2411.15600","title":"How Texts Help? A Fine-grained Evaluation to Reveal the Role of Language in Vision-Language Tracking","created":"2024-11-23","cited_by_count":10},{"id":"2003.07650","title":"M$^5$L: Multi-Modal Multi-Margin Metric Learning for RGBT Tracking","created":"2020-03-17","cited_by_count":9},{"id":"2311.17085","title":"Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking","created":"2023-11-28","cited_by_count":9},{"id":"2405.05004","title":"TENet: Targetness Entanglement Incorporating with Multi-Scale Pooling and Mutually-Guided Fusion for RGB-E Object Tracking","created":"2024-05-08","cited_by_count":9},{"id":"2405.17903","title":"Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion","created":"2024-05-28","cited_by_count":9},{"id":"2411.15459","title":"MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking","created":"2024-11-23","cited_by_count":9},{"id":"2308.16386","title":"RGB-T Tracking via Multi-Modal Mutual Prompt Learning","created":"2023-08-31","cited_by_count":8},{"id":"2312.14446","title":"Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset","created":"2023-12-22","cited_by_count":8},{"id":"2111.04264","title":"Cross-Modal Object Tracking: Modality-Aware Representations and A Unified Benchmark","created":"2021-11-08","cited_by_count":7},{"id":"2304.04264","title":"RGB-T Tracking Based on Mixed Attention","created":"2023-04-09","cited_by_count":7},{"id":"2312.14471","title":"Prototype-based Cross-Modal Object Tracking","created":"2023-12-22","cited_by_count":7},{"id":"2405.14200","title":"Awesome Multi-modal Object Tracking","created":"2024-05-23","cited_by_count":7},{"id":"1802.09227","title":"Depth Masked Discriminative Correlation Filter","created":"2018-02-26","cited_by_count":6},{"id":"2108.04521","title":"Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking","created":"2021-08-10","cited_by_count":6},{"id":"2201.09296","title":"A Survey for Deep RGBT Tracking","created":"2022-01-23","cited_by_count":6},{"id":"2308.13764","title":"Unified Single-Stage Transformer Network for Efficient RGB-T Tracking","created":"2023-08-26","cited_by_count":6}],"next_cursor":"100"}