{"list":"other","total":51,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"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":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"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":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"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":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2006.10721","title":"Ocean: Object-aware Anchor-free Tracking","created":"2020-06-18","cited_by_count":212},{"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":"1808.06048","title":"Distractor-aware Siamese Networks for Visual Object Tracking","created":"2018-08-18","cited_by_count":187},{"id":"1911.06188","title":"SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines","created":"2019-11-14","cited_by_count":177},{"id":"1901.01660","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","created":"2019-01-07","cited_by_count":156},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88},{"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":"2203.01885","title":"TCTrack: Temporal Contexts for Aerial Tracking","created":"2022-03-03","cited_by_count":69},{"id":"1608.03773","title":"Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking","created":"2016-08-12","cited_by_count":66},{"id":"1608.05571","title":"Learning Spatially Regularized Correlation Filters for Visual Tracking","created":"2016-08-19","cited_by_count":66},{"id":"1803.08679","title":"Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking","created":"2018-03-23","cited_by_count":63},{"id":"2003.12949","title":"AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization","created":"2020-03-29","cited_by_count":62},{"id":"2412.15691","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","created":"2024-12-20","cited_by_count":57},{"id":"2203.10541","title":"Unsupervised Domain Adaptation for Nighttime Aerial Tracking","created":"2022-03-20","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":"2401.03142","title":"Explicit Visual Prompts for Visual Object Tracking","created":"2024-01-06","cited_by_count":50},{"id":"1908.02231","title":"Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking","created":"2019-08-06","cited_by_count":47},{"id":"1609.06141","title":"Discriminative Scale Space Tracking","created":"2016-09-20","cited_by_count":46},{"id":"2211.11152","title":"You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model","created":"2022-11-21","cited_by_count":43},{"id":"2308.00255","title":"LGViT: Dynamic Early Exiting for Accelerating Vision Transformer","created":"2023-08-01","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":"2106.15183","title":"Multi-Exit Vision Transformer for Dynamic Inference","created":"2021-06-29","cited_by_count":28},{"id":"2308.10330","title":"Towards Real-World Visual Tracking with Temporal Contexts","created":"2023-08-20","cited_by_count":26},{"id":"2203.13537","title":"Efficient Visual Tracking via Hierarchical Cross-Attention Transformer","created":"2022-03-25","cited_by_count":24},{"id":"2412.13611","title":"Robust Tracking via Mamba-based Context-aware Token Learning","created":"2024-12-18","cited_by_count":15},{"id":"2309.05829","title":"Mobile Vision Transformer-based Visual Object Tracking","created":"2023-09-11","cited_by_count":2}],"next_cursor":null}