{"list":"other","total":54,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"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":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2005.07143","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","created":"2020-05-14","cited_by_count":628},{"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":"1910.04855","title":"Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace","created":"2019-09-25","cited_by_count":222},{"id":"1804.10938","title":"Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond","created":"2018-04-29","cited_by_count":216},{"id":"2001.11409","title":"Analysing Affective Behavior in the First ABAW 2020 Competition","created":"2020-01-30","cited_by_count":178},{"id":"2103.15792","title":"Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework","created":"2021-03-29","cited_by_count":174},{"id":"2105.03790","title":"Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study","created":"2021-05-08","cited_by_count":168},{"id":"2106.15318","title":"Analysing Affective Behavior in the second ABAW2 Competition","created":"2021-06-14","cited_by_count":163},{"id":"2104.03502","title":"Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings","created":"2021-04-08","cited_by_count":162},{"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":"2202.10659","title":"ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges","created":"2022-02-22","cited_by_count":156},{"id":"1910.11111","title":"Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network","created":"2019-10-15","cited_by_count":155},{"id":"2303.01498","title":"ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges","created":"2023-03-02","cited_by_count":110},{"id":"2203.15565","title":"Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC","created":"2022-03-28","cited_by_count":74},{"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":"2111.02392","title":"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion","created":"2021-11-03","cited_by_count":61},{"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":"2004.04989","title":"Improved Residual Networks for Image and Video Recognition","created":"2020-04-10","cited_by_count":52},{"id":"2203.12367","title":"Transformer-based Multimodal Information Fusion for Facial Expression Analysis","created":"2022-03-23","cited_by_count":49},{"id":"2301.12149","title":"POSTER++: A simpler and stronger facial expression recognition network","created":"2023-01-28","cited_by_count":25},{"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":"2203.13031","title":"Continuous Emotion Recognition using Visual-audio-linguistic information: A Technical Report for ABAW3","created":"2022-03-24","cited_by_count":20},{"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":"2203.13052","title":"Coarse-to-Fine Cascaded Networks with Smooth Predicting for Video Facial Expression Recognition","created":"2022-03-24","cited_by_count":17},{"id":"2203.13436","title":"Frame-level Prediction of Facial Expressions, Valence, Arousal and Action Units for Mobile Devices","created":"2022-03-25","cited_by_count":16},{"id":"2210.15878","title":"Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation","created":"2022-10-28","cited_by_count":16},{"id":"2203.13032","title":"Multi-modal Emotion Estimation for in-the-wild Videos","created":"2022-03-24","cited_by_count":15},{"id":"2303.10335","title":"Multimodal Continuous Emotion Recognition: A Technical Report for ABAW5","created":"2023-03-18","cited_by_count":14},{"id":"2107.04192","title":"Emotion Recognition with Incomplete Labels Using Modified Multi-task Learning Technique","created":"2021-07-09","cited_by_count":10},{"id":"2203.13046","title":"Facial Action Unit Recognition With Multi-models Ensembling","created":"2022-03-24","cited_by_count":10},{"id":"2203.13472","title":"Facial Expression Recognition with Swin Transformer","created":"2022-03-25","cited_by_count":9},{"id":"2210.03853","title":"Revisiting Self-Supervised Contrastive Learning for Facial Expression Recognition","created":"2022-10-08","cited_by_count":9},{"id":"2203.13285","title":"Continuous-Time Audiovisual Fusion with Recurrence vs. Attention for In-The-Wild Affect Recognition","created":"2022-03-24","cited_by_count":7},{"id":"2303.09162","title":"EmotiEffNet Facial Features in Uni-task Emotion Recognition in Video at ABAW-5 competition","created":"2023-03-16","cited_by_count":7},{"id":"2303.10644","title":"Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detection","created":"2023-03-19","cited_by_count":7},{"id":"2303.09158","title":"Facial Affect Recognition based on Transformer Encoder and Audiovisual Fusion for the ABAW5 Challenge","created":"2023-03-16","cited_by_count":6},{"id":"2203.12899","title":"Facial Expression Classification using Fusion of Deep Neural Network in Video for the 3rd ABAW3 Competition","created":"2022-03-24","cited_by_count":5},{"id":"2303.08545","title":"Local Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detection","created":"2023-03-15","cited_by_count":5},{"id":"2303.09917","title":"Vision Transformer for Action Units Detection","created":"2023-03-16","cited_by_count":4},{"id":"2303.10033","title":"Multi-modal Expression Recognition with Ensemble Method","created":"2023-03-17","cited_by_count":3}],"next_cursor":null}