{"total":17,"rows":[{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2210.17444","title":"Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations","created":"2022-10-31","cited_by_count":48,"area":null},{"id":"2103.09666","title":"Multimodal End-to-End Sparse Model for Emotion Recognition","created":"2021-03-17","cited_by_count":40,"area":null},{"id":"2109.02401","title":"Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization","created":"2021-09-06","cited_by_count":32,"area":null},{"id":"2206.05833","title":"COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition","created":"2022-06-12","cited_by_count":22,"area":null},{"id":"2201.03804","title":"CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition","created":"2022-01-11","cited_by_count":10,"area":null},{"id":"2108.07543","title":"Graph Capsule Aggregation for Unaligned Multimodal Sequences","created":"2021-08-17","cited_by_count":6,"area":null},{"id":"2407.18552","title":"Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2408.07694","title":"End-to-end Semantic-centric Video-based Multimodal Affective Computing","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2104.11560","title":"Weakly-supervised Multi-task Learning for Multimodal Affect Recognition","created":"2021-04-23","cited_by_count":3,"area":null},{"id":"2112.01697","title":"LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2505.06536","title":"TACFN: Transformer-based Adaptive Cross-modal Fusion Network for Multimodal Emotion Recognition","created":"2025-05-10","cited_by_count":3,"area":null},{"id":"2208.09180","title":"Effective Transfer Learning for Low-Resource Natural Language Understanding","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2209.10170","title":"FV2ES: A Fully End2End Multimodal System for Fast Yet Effective Video Emotion Recognition Inference","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2207.02663","title":"Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands","created":"2022-07-06","cited_by_count":0,"area":null},{"id":"2209.09768","title":"An Efficient End-to-End Transformer with Progressive Tri-modal Attention for Multi-modal Emotion Recognition","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2410.12828","title":"GCM-Net: Graph-enhanced Cross-Modal Infusion with a Metaheuristic-Driven Network for Video Sentiment and Emotion Analysis","created":"2024-10-02","cited_by_count":0,"area":null}],"next_cursor":null}