{"list":"other","total":56,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"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":"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":"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":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"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":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"1510.07945","title":"Learning Multi-Domain Convolutional Neural Networks for Visual Tracking","created":"2015-10-27","cited_by_count":209},{"id":"2003.06761","title":"Siamese Box Adaptive Network for Visual Tracking","created":"2020-03-15","cited_by_count":189},{"id":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"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":"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":"1805.08982","title":"RGB-T Object Tracking:Benchmark and Baseline","created":"2018-05-23","cited_by_count":121},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116},{"id":"2104.13202","title":"LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking","created":"2021-04-27","cited_by_count":96},{"id":"2004.00305","title":"High-Performance Long-Term Tracking with Meta-Updater","created":"2020-04-01","cited_by_count":80},{"id":"1908.00855","title":"Learning the Model Update for Siamese Trackers","created":"2019-08-02","cited_by_count":76},{"id":"2403.10574","title":"Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers","created":"2024-03-15","cited_by_count":76},{"id":"2203.01885","title":"TCTrack: Temporal Contexts for Aerial Tracking","created":"2022-03-03","cited_by_count":69},{"id":"2108.13962","title":"DepthTrack : Unveiling the Power of RGBD Tracking","created":"2021-08-31","cited_by_count":67},{"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":"2305.15896","title":"MixFormerV2: Efficient Fully Transformer Tracking","created":"2023-05-25","cited_by_count":57},{"id":"2412.15691","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","created":"2024-12-20","cited_by_count":57},{"id":"2308.06904","title":"Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking","created":"2023-08-14","cited_by_count":53},{"id":"2112.09686","title":"Efficient Visual Tracking with Exemplar Transformers","created":"2021-12-17","cited_by_count":48},{"id":"2403.06534","title":"SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection","created":"2024-03-11","cited_by_count":48},{"id":"1907.07485","title":"Multi-Adapter RGBT Tracking","created":"2019-07-17","cited_by_count":38},{"id":"2112.07957","title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","created":"2021-12-15","cited_by_count":38},{"id":"2011.07189","title":"RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss","created":"2020-11-14","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":"2205.14443","title":"A Closer Look at Self-Supervised Lightweight Vision Transformers","created":"2022-05-28","cited_by_count":31},{"id":"2309.03979","title":"Separable Self and Mixed Attention Transformers for Efficient Object Tracking","created":"2023-09-07","cited_by_count":31},{"id":"2401.01244","title":"Temporal Adaptive RGBT Tracking with Modality Prompt","created":"2024-01-02","cited_by_count":30},{"id":"1912.00660","title":"DAL -- A Deep Depth-aware Long-term Tracker","created":"2019-12-02","cited_by_count":26},{"id":"2309.09249","title":"LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking","created":"2023-09-17","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":"2208.05810","title":"Towards Sequence-Level Training for Visual Tracking","created":"2022-08-11","cited_by_count":13},{"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":"2308.16386","title":"RGB-T Tracking via Multi-Modal Mutual Prompt Learning","created":"2023-08-31","cited_by_count":8},{"id":"2310.05392","title":"Lightweight Full-Convolutional Siamese Tracker","created":"2023-10-09","cited_by_count":8},{"id":"2308.13764","title":"Unified Single-Stage Transformer Network for Efficient RGB-T Tracking","created":"2023-08-26","cited_by_count":6},{"id":"2406.07189","title":"RGB-Sonar Tracking Benchmark and Spatial Cross-Attention Transformer Tracker","created":"2024-06-11","cited_by_count":6},{"id":"2405.03177","title":"Transformer-based RGB-T Tracking with Channel and Spatial Feature Fusion","created":"2024-05-06","cited_by_count":4},{"id":"2403.16834","title":"From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and Knowledge Distillation","created":"2024-03-25","cited_by_count":2}],"next_cursor":null}