{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"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":"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":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"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":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"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":"2006.10721","title":"Ocean: Object-aware Anchor-free Tracking","created":"2020-06-18","cited_by_count":212},{"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":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"1901.01660","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","created":"2019-01-07","cited_by_count":156},{"id":"1911.07241","title":"SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking","created":"2019-11-17","cited_by_count":148},{"id":"2207.09603","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","created":"2022-07-20","cited_by_count":137},{"id":"2004.08692","title":"A Spatio-temporal Transformer for 3D Human Motion Prediction","created":"2020-04-18","cited_by_count":133},{"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":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126},{"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":"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":"1907.12740","title":"Deep Learning in Video Multi-Object Tracking: A Survey","created":"2019-07-18","cited_by_count":107},{"id":"2004.06711","title":"Deformable Siamese Attention Networks for Visual Object Tracking","created":"2020-04-14","cited_by_count":97},{"id":"2205.03806","title":"Transformer Tracking with Cyclic Shifting Window Attention","created":"2022-05-08","cited_by_count":75},{"id":"2108.00202","title":"HiFT: Hierarchical Feature Transformer for Aerial Tracking","created":"2021-07-31","cited_by_count":72},{"id":"2011.11204","title":"Graph Attention Tracking","created":"2020-11-23","cited_by_count":70},{"id":"1912.00535","title":"Deep Learning for Visual Tracking: A Comprehensive Survey","created":"2019-12-02","cited_by_count":61},{"id":"1512.01355","title":"Staple: Complementary Learners for Real-Time Tracking","created":"2015-12-04","cited_by_count":60},{"id":"2203.02250","title":"Patch Similarity Aware Data-Free Quantization for Vision Transformers","created":"2022-03-04","cited_by_count":56},{"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":"2205.03776","title":"SparseTT: Visual Tracking with Sparse Transformers","created":"2022-05-08","cited_by_count":36},{"id":"2203.15175","title":"Unified Transformer Tracker for Object Tracking","created":"2022-03-29","cited_by_count":31},{"id":"1303.4803","title":"A Survey of Appearance Models in Visual Object Tracking","created":"2013-03-20","cited_by_count":21},{"id":"2203.01536","title":"Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work","created":"2022-03-03","cited_by_count":21},{"id":"2204.07780","title":"Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks","created":"2022-04-16","cited_by_count":21},{"id":"2104.00829","title":"Learning to Filter: Siamese Relation Network for Robust Tracking","created":"2021-04-02","cited_by_count":15},{"id":"2110.08822","title":"Siamese Transformer Pyramid Networks for Real-Time UAV Tracking","created":"2021-10-17","cited_by_count":15},{"id":"2112.02571","title":"Learning Tracking Representations via Dual-Branch Fully Transformer Networks","created":"2021-12-05","cited_by_count":15},{"id":"2105.03817","title":"TrTr: Visual Tracking with Transformer","created":"2021-05-09","cited_by_count":14},{"id":"2210.15511","title":"ProContEXT: Exploring Progressive Context Transformer for Tracking","created":"2022-10-27","cited_by_count":14},{"id":"1511.07940","title":"Video Tracking Using Learned Hierarchical Features","created":"2015-11-25","cited_by_count":4},{"id":"1604.07507","title":"Once for All: a Two-flow Convolutional Neural Network for Visual Tracking","created":"2016-04-26","cited_by_count":3},{"id":"2102.11730","title":"RGB-D Railway Platform Monitoring and Scene Understanding for Enhanced Passenger Safety","created":"2021-02-23","cited_by_count":3}],"next_cursor":null}