{"list":"other","total":55,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"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":"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":"1905.00641","title":"RetinaFace: Single-stage Dense Face Localisation in the Wild","created":"2019-05-02","cited_by_count":165},{"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":"2203.07378","title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","created":"2022-03-14","cited_by_count":157},{"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":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116},{"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":"2402.19344","title":"The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition","created":"2024-02-29","cited_by_count":78},{"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":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58},{"id":"2407.03835","title":"7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition","created":"2024-07-04","cited_by_count":53},{"id":"2002.03399","title":"Two-Stream Aural-Visual Affect Analysis in the Wild","created":"2020-02-09","cited_by_count":51},{"id":"2210.05335","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","created":"2022-10-11","cited_by_count":41},{"id":"2303.04439","title":"A Light Weight Model for Active Speaker Detection","created":"2023-03-08","cited_by_count":40},{"id":"2310.20494","title":"A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations","created":"2023-10-31","cited_by_count":37},{"id":"2104.03509","title":"Py-Feat: Python Facial Expression Analysis Toolbox","created":"2021-04-08","cited_by_count":33},{"id":"2103.09154","title":"Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition","created":"2021-03-16","cited_by_count":30},{"id":"2404.10779","title":"Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations","created":"2024-03-23","cited_by_count":28},{"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":"2303.08356","title":"Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognition","created":"2023-03-15","cited_by_count":20},{"id":"2111.05222","title":"Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition","created":"2021-11-09","cited_by_count":19},{"id":"2403.10825","title":"Affective Behaviour Analysis via Integrating Multi-Modal Knowledge","created":"2024-03-16","cited_by_count":18},{"id":"2401.15489","title":"Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport","created":"2024-01-27","cited_by_count":15},{"id":"2403.13659","title":"Recursive Joint Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognition","created":"2024-03-20","cited_by_count":15},{"id":"2303.06845","title":"Transformer Encoder with Multiscale Deep Learning for Pain Classification Using Physiological Signals","created":"2023-03-13","cited_by_count":14},{"id":"2403.10488","title":"Joint Multimodal Transformer for Emotion Recognition in the Wild","created":"2024-03-15","cited_by_count":14},{"id":"2207.10851","title":"Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction","created":"2022-07-22","cited_by_count":13},{"id":"2308.04502","title":"Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition","created":"2023-08-08","cited_by_count":13},{"id":"2403.07260","title":"LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristics","created":"2024-03-12","cited_by_count":13},{"id":"2201.09165","title":"A Pre-trained Audio-Visual Transformer for Emotion Recognition","created":"2022-01-23","cited_by_count":12},{"id":"2401.12987","title":"TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation","created":"2024-01-16","cited_by_count":12},{"id":"2004.13236","title":"Deep Auto-Encoders with Sequential Learning for Multimodal Dimensional Emotion Recognition","created":"2020-04-28","cited_by_count":11},{"id":"2304.06910","title":"HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition","created":"2023-04-14","cited_by_count":11},{"id":"2402.00281","title":"Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues","created":"2024-02-01","cited_by_count":11},{"id":"2303.15430","title":"TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models","created":"2023-03-27","cited_by_count":6},{"id":"2403.20289","title":"Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation","created":"2024-03-29","cited_by_count":3}],"next_cursor":null}