{"list":"other","total":54,"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":"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"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":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"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":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"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":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"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":"1807.11590","title":"Acquisition of Localization Confidence for Accurate Object Detection","created":"2018-07-30","cited_by_count":176},{"id":"1810.10510","title":"Neighbourhood Consensus Networks","created":"2018-10-24","cited_by_count":174},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"1901.01660","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","created":"2019-01-07","cited_by_count":156},{"id":"1703.05884","title":"Need for Speed: A Benchmark for Higher Frame Rate Object Tracking","created":"2017-03-17","cited_by_count":137},{"id":"2009.03465","title":"LaSOT: A High-quality Large-scale Single Object Tracking Benchmark","created":"2020-09-08","cited_by_count":132},{"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":"2003.11014","title":"Know Your Surroundings: Exploiting Scene Information for Object Tracking","created":"2020-03-24","cited_by_count":119},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"id":"2004.06711","title":"Deformable Siamese Attention Networks for Visual Object Tracking","created":"2020-04-14","cited_by_count":97},{"id":"2004.10566","title":"Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions","created":"2020-04-22","cited_by_count":93},{"id":"2104.00324","title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","created":"2021-04-01","cited_by_count":91},{"id":"2007.02024","title":"Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation","created":"2020-07-04","cited_by_count":81},{"id":"2004.00305","title":"High-Performance Long-Term Tracking with Meta-Updater","created":"2020-04-01","cited_by_count":80},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77},{"id":"1908.00855","title":"Learning the Model Update for Siamese Trackers","created":"2019-08-02","cited_by_count":76},{"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":"2108.03679","title":"Joint Inductive and Transductive Learning for Video Object Segmentation","created":"2021-08-08","cited_by_count":61},{"id":"2103.16831","title":"Convolutional Hough Matching Networks","created":"2021-03-31","cited_by_count":43},{"id":"2003.12059","title":"Correspondence Networks with Adaptive Neighbourhood Consensus","created":"2020-03-26","cited_by_count":42},{"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":"2112.13983","title":"Siamese Network with Interactive Transformer for Video Object Segmentation","created":"2021-12-28","cited_by_count":11},{"id":"2008.02745","title":"Towards Accurate Pixel-wise Object Tracking by Attention Retrieval","created":"2020-08-06","cited_by_count":9}],"next_cursor":null}