{"list":"other","total":72,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"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":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"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":"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":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"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":"1901.01660","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","created":"2019-01-07","cited_by_count":156},{"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":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"id":"1805.08982","title":"RGB-T Object Tracking:Benchmark and Baseline","created":"2018-05-23","cited_by_count":121},{"id":"2303.03369","title":"Multimodal Prompting with Missing Modalities for Visual Recognition","created":"2023-03-06","cited_by_count":121},{"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":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"1702.00824","title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","created":"2017-02-02","cited_by_count":109},{"id":"2004.06711","title":"Deformable Siamese Attention Networks for Visual Object Tracking","created":"2020-04-14","cited_by_count":97},{"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":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"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":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80},{"id":"2310.02642","title":"GET: Group Event Transformer for Event-Based Vision","created":"2023-10-04","cited_by_count":73},{"id":"2108.13962","title":"DepthTrack : Unveiling the Power of RGBD Tracking","created":"2021-08-31","cited_by_count":67},{"id":"1804.04273","title":"VITAL: VIsual Tracking via Adversarial Learning","created":"2018-04-12","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":"2207.14571","title":"Prompting for Multi-Modal Tracking","created":"2022-07-29","cited_by_count":59},{"id":"1909.03850","title":"Robust Multi-Modality Multi-Object Tracking","created":"2019-09-09","cited_by_count":56},{"id":"2308.06904","title":"Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking","created":"2023-08-14","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":"1904.09172","title":"Video Object Segmentation and Tracking: A Survey","created":"2019-04-19","cited_by_count":50},{"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":"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":"1907.00618","title":"CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark","created":"2019-07-01","cited_by_count":32},{"id":"2107.10433","title":"MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking","created":"2021-07-22","cited_by_count":32},{"id":"2308.11771","title":"3ET: Efficient Event-based Eye Tracking using a Change-Based ConvLSTM Network","created":"2023-08-22","cited_by_count":30},{"id":"2008.00490","title":"Tensor Low-Rank Reconstruction for Semantic Segmentation","created":"2020-08-02","cited_by_count":29},{"id":"2204.13707","title":"Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalities","created":"2022-04-28","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":"2309.15082","title":"RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation","created":"2023-09-26","cited_by_count":26},{"id":"2112.13659","title":"M2DGR: A Multi-sensor and Multi-scenario SLAM Dataset for Ground Robots","created":"2021-12-19","cited_by_count":25},{"id":"2202.05054","title":"Exploiting Spatial Sparsity for Event Cameras with Visual Transformers","created":"2022-02-10","cited_by_count":23},{"id":"1906.03568","title":"Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking","created":"2019-06-09","cited_by_count":19},{"id":"2309.10491","title":"DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVs","created":"2023-09-19","cited_by_count":16},{"id":"2103.05903","title":"FAST-Dynamic-Vision: Detection and Tracking Dynamic Objects with Event and Depth Sensing","created":"2021-03-10","cited_by_count":14},{"id":"2203.13533","title":"High-Performance Transformer Tracking","created":"2022-03-25","cited_by_count":14},{"id":"2012.04176","title":"Multi-modal Visual Tracking: Review and Experimental Comparison","created":"2020-12-08","cited_by_count":11},{"id":"2203.14134","title":"RGBD Object Tracking: An In-depth Review","created":"2022-03-26","cited_by_count":11},{"id":"2307.13974","title":"Tracking Anything in High Quality","created":"2023-07-26","cited_by_count":9},{"id":"2011.06838","title":"Unified Multi-Modal Landmark Tracking for Tightly Coupled Lidar-Visual-Inertial Odometry","created":"2020-11-13","cited_by_count":8},{"id":"2310.14194","title":"Distractor-aware Event-based Tracking","created":"2023-10-22","cited_by_count":8},{"id":"2211.03055","title":"Learning Dual-Fused Modality-Aware Representations for RGBD Tracking","created":"2022-11-06","cited_by_count":5},{"id":"2005.14042","title":"Joint Reconstruction and Low-Rank Decomposition for Dynamic Inverse Problems","created":"2020-05-28","cited_by_count":3},{"id":"2110.11679","title":"Depth-only Object Tracking","created":"2021-10-22","cited_by_count":3}],"next_cursor":null}