{"list":"other","total":51,"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":"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1604.02878","title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","created":"2016-04-11","cited_by_count":903},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1607.08221","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","created":"2016-07-27","cited_by_count":624},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","created":"2013-07-01","cited_by_count":302},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"1910.04855","title":"Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace","created":"2019-09-25","cited_by_count":222},{"id":"2106.15318","title":"Analysing Affective Behavior in the second ABAW2 Competition","created":"2021-06-14","cited_by_count":163},{"id":"1608.01041","title":"Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution","created":"2016-08-03","cited_by_count":158},{"id":"2002.10392","title":"Suppressing Uncertainties for Large-Scale Facial Expression Recognition","created":"2020-02-24","cited_by_count":157},{"id":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144},{"id":"1905.04075","title":"Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition","created":"2019-05-10","cited_by_count":127},{"id":"2108.11116","title":"TransFER: Learning Relation-aware Facial Expression Representations with Transformers","created":"2021-08-25","cited_by_count":85},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59},{"id":"2109.07270","title":"Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition","created":"2021-09-15","cited_by_count":55},{"id":"1609.06426","title":"From Facial Expression Recognition to Interpersonal Relation Prediction","created":"2016-09-21","cited_by_count":53},{"id":"1808.05561","title":"Emotion Recognition in Speech using Cross-Modal Transfer in the Wild","created":"2018-08-16","cited_by_count":49},{"id":"2103.16854","title":"Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion","created":"2021-03-31","cited_by_count":49},{"id":"2104.05160","title":"Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition","created":"2021-04-12","cited_by_count":49},{"id":"1805.04855","title":"Covariance Pooling For Facial Expression Recognition","created":"2018-05-13","cited_by_count":37},{"id":"1710.03144","title":"Island Loss for Learning Discriminative Features in Facial Expression Recognition","created":"2017-10-09","cited_by_count":35},{"id":"1905.03711","title":"Processing Megapixel Images with Deep Attention-Sampling Models","created":"2019-05-03","cited_by_count":29},{"id":"2106.04520","title":"MVT: Mask Vision Transformer for Facial Expression Recognition in the wild","created":"2021-06-08","cited_by_count":27},{"id":"2107.04187","title":"A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognition","created":"2021-07-09","cited_by_count":24},{"id":"2108.04228","title":"Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition","created":"2021-07-21","cited_by_count":21},{"id":"2107.04225","title":"A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysis","created":"2021-07-09","cited_by_count":19},{"id":"2107.03107","title":"Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition","created":"2021-07-07","cited_by_count":18},{"id":"2107.03708","title":"Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition","created":"2021-07-08","cited_by_count":18},{"id":"1808.02531","title":"SchiNet: Automatic Estimation of Symptoms of Schizophrenia from Facial Behaviour Analysis","created":"2018-08-07","cited_by_count":16},{"id":"1505.04026","title":"Automatic Facial Expression Recognition Using Features of Salient Facial Patches","created":"2015-05-15","cited_by_count":13},{"id":"2205.14361","title":"Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher","created":"2022-05-28","cited_by_count":12},{"id":"1604.03225","title":"Geometric Feature-Based Facial Expression Recognition in Image Sequences Using Multi-Class AdaBoost and Support Vector Machines","created":"2016-04-12","cited_by_count":10},{"id":"2107.04192","title":"Emotion Recognition with Incomplete Labels Using Modified Multi-task Learning Technique","created":"2021-07-09","cited_by_count":10},{"id":"1911.05188","title":"Expression Analysis Based on Face Regions in Read-world Conditions","created":"2019-10-23","cited_by_count":7}],"next_cursor":null}