{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"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":"1411.7923","title":"Learning Face Representation from Scratch","created":"2014-11-28","cited_by_count":453},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"1804.08348","title":"Deep Facial Expression Recognition: A Survey","created":"2018-04-23","cited_by_count":270},{"id":"2007.03943","title":"Remix: Rebalanced Mixup","created":"2020-07-08","cited_by_count":144},{"id":"2108.11116","title":"TransFER: Learning Relation-aware Facial Expression Representations with Transformers","created":"2021-08-25","cited_by_count":85},{"id":"2205.01782","title":"Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition","created":"2022-05-02","cited_by_count":82},{"id":"2207.10299","title":"Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition","created":"2022-07-21","cited_by_count":67},{"id":"2003.08834","title":"J$\\hat{\\text{A}}$A-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention","created":"2020-03-18","cited_by_count":62},{"id":"1904.09939","title":"Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition","created":"2019-04-22","cited_by_count":53},{"id":"2108.08504","title":"Understanding and Mitigating Annotation Bias in Facial Expression Recognition","created":"2021-08-19","cited_by_count":50},{"id":"2203.12367","title":"Transformer-based Multimodal Information Fusion for Facial Expression Analysis","created":"2022-03-23","cited_by_count":49},{"id":"2204.04083","title":"POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition","created":"2022-04-08","cited_by_count":49},{"id":"1808.03457","title":"Facial Action Unit Detection Using Attention and Relation Learning","created":"2018-08-10","cited_by_count":46},{"id":"1511.08861","title":"Loss Functions for Neural Networks for Image Processing","created":"2015-11-28","cited_by_count":41},{"id":"1803.05873","title":"Deep Structure Inference Network for Facial Action Unit Recognition","created":"2018-03-15","cited_by_count":38},{"id":"1702.02925","title":"EAC-Net: A Region-based Deep Enhancing and Cropping Approach for Facial Action Unit Detection","created":"2017-02-09","cited_by_count":26},{"id":"1910.11012","title":"Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition","created":"2019-10-24","cited_by_count":26},{"id":"2103.16554","title":"Pre-training strategies and datasets for facial representation learning","created":"2021-03-30","cited_by_count":26},{"id":"1910.10334","title":"Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection","created":"2019-10-23","cited_by_count":25},{"id":"2004.09681","title":"Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution","created":"2020-04-20","cited_by_count":22},{"id":"2103.10189","title":"Learning to Amend Facial Expression Representation via De-albino and Affinity","created":"2021-03-18","cited_by_count":19},{"id":"1704.04481","title":"Deep Structured Learning for Facial Action Unit Intensity Estimation","created":"2017-04-14","cited_by_count":17},{"id":"2103.13372","title":"Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition","created":"2021-03-24","cited_by_count":16},{"id":"1812.05788","title":"AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection","created":"2018-12-14","cited_by_count":14},{"id":"2204.07935","title":"Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition","created":"2022-04-17","cited_by_count":12},{"id":"2004.06657","title":"A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation","created":"2020-04-14","cited_by_count":10},{"id":"1704.02206","title":"DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding","created":"2017-04-07","cited_by_count":9},{"id":"1701.03102","title":"Linear Disentangled Representation Learning for Facial Actions","created":"2017-01-11","cited_by_count":6},{"id":"2204.01349","title":"MGRR-Net: Multi-level Graph Relational Reasoning Network for Facial Action Units Detection","created":"2022-04-04","cited_by_count":6},{"id":"1608.04664","title":"Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units","created":"2016-08-16","cited_by_count":3},{"id":"2204.00379","title":"Weakly Supervised Regional and Temporal Learning for Facial Action Unit Recognition","created":"2022-04-01","cited_by_count":3},{"id":"2203.16678","title":"Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels","created":"2022-03-30","cited_by_count":1}],"next_cursor":null}