{"list":"other","total":65,"rows":[{"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":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"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":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"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":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2103.05677","title":"SMIL: Multimodal Learning with Severely Missing Modality","created":"2021-03-09","cited_by_count":245},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220},{"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":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"2307.14126","title":"Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling","created":"2023-07-26","cited_by_count":163},{"id":"1911.07241","title":"SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking","created":"2019-11-17","cited_by_count":148},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"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":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"id":"2303.03369","title":"Multimodal Prompting with Missing Modalities for Visual Recognition","created":"2023-03-06","cited_by_count":121},{"id":"2003.11014","title":"Know Your Surroundings: Exploiting Scene Information for Object Tracking","created":"2020-03-24","cited_by_count":119},{"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":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"id":"2308.05140","title":"Robust Object Modeling for Visual Tracking","created":"2023-08-09","cited_by_count":80},{"id":"2403.10574","title":"Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers","created":"2024-03-15","cited_by_count":76},{"id":"2309.14611","title":"Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline","created":"2023-09-26","cited_by_count":73},{"id":"2311.02072","title":"HIPTrack: Visual Tracking with Historical Prompts","created":"2023-11-03","cited_by_count":71},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65},{"id":"2312.17133","title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","created":"2023-12-28","cited_by_count":59},{"id":"2202.04557","title":"Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models","created":"2022-02-09","cited_by_count":55},{"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":"2401.03142","title":"Explicit Visual Prompts for Visual Object Tracking","created":"2024-01-06","cited_by_count":50},{"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":"2303.12783","title":"Conformal Prediction for Time Series with Modern Hopfield Networks","created":"2023-03-22","cited_by_count":42},{"id":"2404.03828","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","created":"2024-04-04","cited_by_count":38},{"id":"2412.11023","title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","created":"2024-12-15","cited_by_count":37},{"id":"2312.17346","title":"STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction","created":"2023-12-28","cited_by_count":35},{"id":"2504.09228","title":"Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking","created":"2025-04-12","cited_by_count":22},{"id":"2405.17773","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","created":"2024-05-28","cited_by_count":21},{"id":"2503.00516","title":"Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking","created":"2025-03-01","cited_by_count":15},{"id":"2503.17699","title":"MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Tracking","created":"2025-03-22","cited_by_count":15},{"id":"2405.08707","title":"Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory","created":"2024-05-14","cited_by_count":12},{"id":"2602.23734","title":"UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking","created":"2026-02-27","cited_by_count":9},{"id":"2310.14194","title":"Distractor-aware Event-based Tracking","created":"2023-10-22","cited_by_count":8},{"id":"2505.20834","title":"Fully Spiking Neural Networks for Unified Frame-Event Object Tracking","created":"2025-05-27","cited_by_count":6},{"id":"2602.23963","title":"SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking","created":"2026-02-27","cited_by_count":5},{"id":"2511.06225","title":"MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition","created":"2025-11-09","cited_by_count":4},{"id":"2601.22853","title":"Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification","created":"2026-01-30","cited_by_count":4},{"id":"2410.08889","title":"Exploiting Memory-aware Q-distribution Prediction for Nuclear Fusion via Modern Hopfield Network","created":"2024-10-11","cited_by_count":3},{"id":"2604.12502","title":"SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker","created":"2026-04-14","cited_by_count":3},{"id":"2506.23783","title":"Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking","created":"2025-06-30","cited_by_count":2},{"id":"2511.20609","title":"Adaptive Hopfield Network: Rethinking Similarities in Associative Memory","created":"2025-11-25","cited_by_count":1}],"next_cursor":null}