{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"1704.08063","title":"SphereFace: Deep Hypersphere Embedding for Face Recognition","created":"2017-04-26","cited_by_count":737},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2007.09314","title":"Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification","created":"2020-07-18","cited_by_count":111},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109},{"id":"2007.09451","title":"Feature Pyramid Transformer","created":"2020-07-18","cited_by_count":96},{"id":"1804.07094","title":"Part-Aligned Bilinear Representations for Person Re-identification","created":"2018-04-19","cited_by_count":90},{"id":"2009.09450","title":"Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition","created":"2020-09-20","cited_by_count":69},{"id":"2007.08434","title":"Appearance-Preserving 3D Convolution for Video-based Person Re-identification","created":"2020-07-16","cited_by_count":63},{"id":"1812.08967","title":"Densely Semantically Aligned Person Re-Identification","created":"2018-12-21","cited_by_count":58},{"id":"1907.08427","title":"VRSTC: Occlusion-Free Video Person Re-Identification","created":"2019-07-19","cited_by_count":53},{"id":"2007.09357","title":"Temporal Complementary Learning for Video Person Re-Identification","created":"2020-07-18","cited_by_count":53},{"id":"2008.00923","title":"Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning","created":"2020-08-03","cited_by_count":46},{"id":"1809.02874","title":"Unsupervised Person Re-identification by Deep Learning Tracklet Association","created":"2018-09-08","cited_by_count":45},{"id":"2103.04337","title":"Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification","created":"2021-03-07","cited_by_count":45},{"id":"2003.12224","title":"Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification","created":"2020-03-27","cited_by_count":42},{"id":"1604.07528","title":"Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification","created":"2016-04-26","cited_by_count":41},{"id":"1811.07468","title":"Multi-scale 3D Convolution Network for Video Based Person Re-Identification","created":"2018-11-19","cited_by_count":41},{"id":"1708.02286","title":"Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification","created":"2017-08-03","cited_by_count":39},{"id":"1909.00295","title":"Second-order Non-local Attention Networks for Person Re-identification","created":"2019-08-31","cited_by_count":38},{"id":"1607.08378","title":"Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification","created":"2016-07-28","cited_by_count":34},{"id":"1812.10305","title":"Spatial and Temporal Mutual Promotion for Video-based Person Re-identification","created":"2018-12-26","cited_by_count":30},{"id":"2107.11878","title":"Spatio-Temporal Representation Factorization for Video-based Person Re-Identification","created":"2021-07-25","cited_by_count":29},{"id":"2104.01745","title":"A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification","created":"2021-04-05","cited_by_count":28},{"id":"2103.09013","title":"Dense Interaction Learning for Video-based Person Re-identification","created":"2021-03-16","cited_by_count":24},{"id":"1908.01683","title":"Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification","created":"2019-08-05","cited_by_count":23},{"id":"1703.09474","title":"Robust Depth-based Person Re-identification","created":"2017-03-28","cited_by_count":19},{"id":"1701.06351","title":"Person Re-Identification via Recurrent Feature Aggregation","created":"2017-01-23","cited_by_count":17},{"id":"1701.00193","title":"Video-based Person Re-identification with Accumulative Motion Context","created":"2017-01-01","cited_by_count":16},{"id":"2103.16469","title":"Spatiotemporal Transformer for Video-based Person Re-identification","created":"2021-03-30","cited_by_count":15},{"id":"1807.05073","title":"Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention","created":"2018-07-12","cited_by_count":14},{"id":"1808.01911","title":"Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification","created":"2018-08-03","cited_by_count":14},{"id":"1807.05688","title":"SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification","created":"2018-07-16","cited_by_count":12},{"id":"2008.06181","title":"Apparel-invariant Feature Learning for Apparel-changed Person Re-identification","created":"2020-08-14","cited_by_count":10},{"id":"2109.11159","title":"OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification","created":"2021-09-23","cited_by_count":10},{"id":"1912.11236","title":"Ordered or Orderless: A Revisit for Video based Person Re-Identification","created":"2019-12-24","cited_by_count":7},{"id":"2108.06946","title":"Video Person Re-identification using Attribute-enhanced Features","created":"2021-08-16","cited_by_count":7},{"id":"1604.07807","title":"An Enhanced Deep Feature Representation for Person Re-identification","created":"2016-04-26","cited_by_count":6},{"id":"1712.07257","title":"Multi-shot Pedestrian Re-identification via Sequential Decision Making","created":"2017-12-19","cited_by_count":6},{"id":"2011.00774","title":"Set Augmented Triplet Loss for Video Person Re-Identification","created":"2020-11-02","cited_by_count":5},{"id":"2112.05626","title":"Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification","created":"2021-12-10","cited_by_count":4},{"id":"2105.10678","title":"Video-based Person Re-identification without Bells and Whistles","created":"2021-05-22","cited_by_count":3}],"next_cursor":null}