{"list":"other","total":92,"rows":[{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1604.02878","title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","created":"2016-04-11","cited_by_count":903},{"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":"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":"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":"2207.01138","title":"ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges","created":"2022-07-03","cited_by_count":110},{"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":"1811.07770","title":"Aff-Wild2: Extending the Aff-Wild Database for Affect Recognition","created":"2018-11-11","cited_by_count":81},{"id":"2009.07044","title":"Deep Transparent Prediction through Latent Representation Analysis","created":"2020-09-13","cited_by_count":72},{"id":"2106.07524","title":"MIA-COV19D: COVID-19 Detection through 3-D Chest CT Image Analysis","created":"2021-06-14","cited_by_count":72},{"id":"1704.08619","title":"End-to-End Multimodal Emotion Recognition using Deep Neural Networks","created":"2017-04-27","cited_by_count":70},{"id":"2401.01219","title":"Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond","created":"2024-01-02","cited_by_count":60},{"id":"2002.03399","title":"Two-Stream Aural-Visual Affect Analysis in the Wild","created":"2020-02-09","cited_by_count":51},{"id":"2203.12367","title":"Transformer-based Multimodal Information Fusion for Facial Expression Analysis","created":"2022-03-23","cited_by_count":49},{"id":"1910.01417","title":"Exploiting multi-CNN features in CNN-RNN based Dimensional Emotion Recognition on the OMG in-the-wild Dataset","created":"2019-10-03","cited_by_count":39},{"id":"2002.03557","title":"Multitask Emotion Recognition with Incomplete Labels","created":"2020-02-10","cited_by_count":39},{"id":"2303.00175","title":"A Deep Neural Architecture for Harmonizing 3-D Input Data Analysis and Decision Making in Medical Imaging","created":"2023-03-01","cited_by_count":39},{"id":"2203.14779","title":"A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition","created":"2022-03-28","cited_by_count":34},{"id":"1811.08004","title":"Photorealistic Facial Synthesis in the Dimensional Affect Space","created":"2018-11-11","cited_by_count":33},{"id":"2205.04442","title":"MixAugment & Mixup: Augmentation Methods for Facial Expression Recognition","created":"2022-05-09","cited_by_count":31},{"id":"1811.07771","title":"A Multi-Task Learning & Generation Framework: Valence-Arousal, Action Units & Primary Expressions","created":"2018-11-11","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":"1809.04359","title":"Training Deep Neural Networks with Different Datasets In-the-wild: The Emotion Recognition Paradigm","created":"2018-09-12","cited_by_count":20},{"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":"2310.03485","title":"BTDNet: a Multi-Modal Approach for Brain Tumor Radiogenomic Classification","created":"2023-10-05","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":"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":"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":"1707.05395","title":"Incremental Boosting Convolutional Neural Network for Facial Action Unit Recognition","created":"2017-07-17","cited_by_count":16},{"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":"2203.13032","title":"Multi-modal Emotion Estimation for in-the-wild Videos","created":"2022-03-24","cited_by_count":15},{"id":"2002.02957","title":"$M^3$T: Multi-Modal Continuous Valence-Arousal Estimation in the Wild","created":"2020-02-07","cited_by_count":14},{"id":"2303.10335","title":"Multimodal Continuous Emotion Recognition: A Technical Report for ABAW5","created":"2023-03-18","cited_by_count":14},{"id":"2009.14440","title":"Affect Expression Behaviour Analysis in the Wild using Spatio-Channel Attention and Complementary Context Information","created":"2020-09-29","cited_by_count":13},{"id":"1802.01115","title":"End2You -- The Imperial Toolkit for Multimodal Profiling by End-to-End Learning","created":"2018-02-04","cited_by_count":12},{"id":"2107.03465","title":"An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wild","created":"2021-07-07","cited_by_count":12},{"id":"2107.04127","title":"Multitask Multi-database Emotion Recognition","created":"2021-07-08","cited_by_count":12},{"id":"2305.03369","title":"The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation","created":"2023-05-05","cited_by_count":12},{"id":"2103.02993","title":"Speech Emotion Recognition using Semantic Information","created":"2021-03-04","cited_by_count":11},{"id":"2203.13046","title":"Facial Action Unit Recognition With Multi-models Ensembling","created":"2022-03-24","cited_by_count":10},{"id":"2203.13301","title":"Multi-modal Multi-label Facial Action Unit Detection with Transformer","created":"2022-03-24","cited_by_count":10},{"id":"2207.09748","title":"Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challenges","created":"2022-07-20","cited_by_count":10},{"id":"2207.11679","title":"Affective Behaviour Analysis Using Pretrained Model with Facial Priori","created":"2022-07-24","cited_by_count":10},{"id":"2203.12531","title":"Multi-label Transformer for Action Unit Detection","created":"2022-03-23","cited_by_count":9},{"id":"2203.12845","title":"Multiple Emotion Descriptors Estimation at the ABAW3 Challenge","created":"2022-03-24","cited_by_count":9},{"id":"2203.12891","title":"An Ensemble Approach for Facial Expression Analysis in Video","created":"2022-03-24","cited_by_count":9},{"id":"2203.13472","title":"Facial Expression Recognition with Swin Transformer","created":"2022-03-25","cited_by_count":9},{"id":"2002.05447","title":"Emotion Recognition for In-the-wild Videos","created":"2020-02-13","cited_by_count":8},{"id":"2002.09120","title":"Affective Expression Analysis in-the-wild using Multi-Task Temporal Statistical Deep Learning Model","created":"2020-02-21","cited_by_count":8},{"id":"2009.13885","title":"A Multi-term and Multi-task Analyzing Framework for Affective Analysis in-the-wild","created":"2020-09-29","cited_by_count":8},{"id":"2010.03692","title":"An Audio-Video Deep and Transfer Learning Framework for Multimodal Emotion Recognition in the wild","created":"2020-10-07","cited_by_count":8},{"id":"2105.01502","title":"Technical Report for Valence-Arousal Estimation on Affwild2 Dataset","created":"2021-05-04","cited_by_count":8},{"id":"2107.03886","title":"Causal affect prediction model using a facial image sequence","created":"2021-07-08","cited_by_count":8},{"id":"2203.13235","title":"Facial Expression Recognition based on Multi-head Cross Attention Network","created":"2022-03-24","cited_by_count":8},{"id":"2303.09293","title":"A transformer-based approach to video frame-level prediction in Affective Behaviour Analysis In-the-wild","created":"2023-03-16","cited_by_count":8},{"id":"2303.10590","title":"Multi-modal Facial Action Unit Detection with Large Pre-trained Models for the 5th Competition on Affective Behavior Analysis in-the-wild","created":"2023-03-19","cited_by_count":8},{"id":"2002.01105","title":"Multi-label Relation Modeling in Facial Action Units Detection","created":"2020-02-04","cited_by_count":7},{"id":"2002.03238","title":"Multi-Label Class Balancing Algorithm for Action Unit Detection","created":"2020-02-08","cited_by_count":7},{"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":"2107.03143","title":"Action Units Recognition Using Improved Pairwise Deep Architecture","created":"2021-07-07","cited_by_count":6},{"id":"2107.03891","title":"Technical Report for Valence-Arousal Estimation in ABAW2 Challenge","created":"2021-07-08","cited_by_count":6},{"id":"2207.09508","title":"HSE-NN Team at the 4th ABAW Competition: Multi-task Emotion Recognition and Learning from Synthetic Images","created":"2022-07-19","cited_by_count":6},{"id":"2207.13235","title":"Mid-level Representation Enhancement and Graph Embedded Uncertainty Suppressing for Facial Expression Recognition","created":"2022-07-27","cited_by_count":6},{"id":"2303.09145","title":"Facial Affective Behavior Analysis Method for 5th ABAW Competition","created":"2023-03-16","cited_by_count":6},{"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":"2107.05160","title":"Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos","created":"2021-07-12","cited_by_count":5},{"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":"2207.09012","title":"SS-MFAR : Semi-supervised Multi-task Facial Affect Recognition","created":"2022-07-19","cited_by_count":5},{"id":"2207.10025","title":"Learning from Synthetic Data: Facial Expression Classification based on Ensemble of Multi-task Networks","created":"2022-07-20","cited_by_count":5},{"id":"2207.10201","title":"Hybrid CNN-Transformer Model For Facial Affect Recognition In the ABAW4 Challenge","created":"2022-07-20","cited_by_count":5},{"id":"2303.10536","title":"TempT: Temporal consistency for Test-time adaptation","created":"2023-03-19","cited_by_count":5},{"id":"2203.12428","title":"An Attention-based Method for Action Unit Detection at the 3rd ABAW Competition","created":"2022-03-23","cited_by_count":4},{"id":"2203.14466","title":"Multi-model Ensemble Learning Method for Human Expression Recognition","created":"2022-03-28","cited_by_count":4},{"id":"2203.14694","title":"Facial Action Unit Recognition Based on Transfer Learning","created":"2022-03-25","cited_by_count":4},{"id":"2303.08617","title":"Exploring Large-scale Unlabeled Faces to Enhance Facial Expression Recognition","created":"2023-03-15","cited_by_count":4},{"id":"2303.09917","title":"Vision Transformer for Action Units Detection","created":"2023-03-16","cited_by_count":4},{"id":"2207.09716","title":"Multi-Task Learning for Emotion Descriptors Estimation at the fourth ABAW Challenge","created":"2022-07-20","cited_by_count":3},{"id":"2207.10003","title":"BYEL : Bootstrap Your Emotion Latent","created":"2022-07-20","cited_by_count":3},{"id":"2207.10878","title":"An Ensemble Approach for Multiple Emotion Descriptors Estimation Using Multi-task Learning","created":"2022-07-22","cited_by_count":3},{"id":"2207.11389","title":"Two-Aspect Information Fusion Model For ABAW4 Multi-task Challenge","created":"2022-07-23","cited_by_count":3},{"id":"2303.09785","title":"ABAW : Facial Expression Recognition in the wild","created":"2023-03-17","cited_by_count":3},{"id":"2303.08419","title":"Multi Modal Facial Expression Recognition with Transformer-Based Fusion Networks and Dynamic Sampling","created":"2023-03-15","cited_by_count":2},{"id":"2303.10421","title":"Mutilmodal Feature Extraction and Attention-based Fusion for Emotion Estimation in Videos","created":"2023-03-18","cited_by_count":2},{"id":"2303.10511","title":"Exploring Expression-related Self-supervised Learning for Affective Behaviour Analysis","created":"2023-03-18","cited_by_count":2},{"id":"2303.10561","title":"Spatial-temporal Transformer for Affective Behavior Analysis","created":"2023-03-19","cited_by_count":2}],"next_cursor":null}