English
Related papers

Related papers: State-Anchored Complete-View Distillation for Robu…

200 papers

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small models. In this study, we…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Kaiyou Song , Jin Xie , Shan Zhang , Zimeng Luo

Cued Speech (CS) is a visual coding tool to encode spoken languages at the phonetic level, which combines lip-reading and hand gestures to effectively assist communication among people with hearing impairments. The Automatic CS Recognition…

Multimedia · Computer Science 2023-08-08 Yuxuan Zhang , Lei Liu , Li Liu

Emotion plays a fundamental role in human interaction, and therefore systems capable of identifying emotions in speech are crucial in the context of human-computer interaction. Speech emotion recognition (SER) is a challenging problem,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Lucas Ueda , João Lima , Leonardo Marques , Paula Costa

Mutual knowledge distillation (MKD) improves a model by distilling knowledge from another model. However, \textit{not all knowledge is certain and correct}, especially under adverse conditions. For example, label noise usually leads to less…

Machine Learning · Computer Science 2022-11-17 Ziyun Li , Xinshao Wang , Di Hu , Neil M. Robertson , David A. Clifton , Christoph Meinel , Haojin Yang

Speech Emotion Recognition (SER) aims to help the machine to understand human's subjective emotion from only audio information. However, extracting and utilizing comprehensive in-depth audio information is still a challenging task. In this…

Sound · Computer Science 2022-03-30 Heqing Zou , Yuke Si , Chen Chen , Deepu Rajan , Eng Siong Chng

Although multi-view multi-label learning has been extensively studied, research on the dual-missing scenario, where both views and labels are incomplete, remains largely unexplored. Existing methods mainly rely on contrastive learning or…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Xu Yan , Jun Yin , Shiliang Sun , Minghua Wan

Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data…

Machine Learning · Computer Science 2024-08-15 Dino Ienco , Cassio Fraga Dantas

Multi-modal conversation emotion recognition (MCER) aims to recognize and track the speaker's emotional state using text, speech, and visual information in the conversation scene. Analyzing and studying MCER issues is significant to…

Artificial Intelligence · Computer Science 2025-11-14 Yuntao Shou , Tao Meng , Wei Ai , Fangze Fu , Nan Yin , Keqin Li

Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, learn powerful representations from unlabeled data but are typically pretrained in isolation, overlooking complementary insights and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Sriram Mandalika , Lalitha V

Multimodal emotion recognition (MER) aims to identify human emotions by combining data from various modalities such as language, audio, and vision. Despite the recent advances of MER approaches, the limitations in obtaining extensive…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Yehun Song , Sunyoung Cho

Crossmodal knowledge distillation (KD) aims to enhance a unimodal student using a multimodal teacher model. In particular, when the teacher's modalities include the student's, additional complementary information can be exploited to improve…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Chenqi Guo , Mengshuo Rong , Qianli Feng , Rongfan Feng , Yinglong Ma

Speech emotion recognition (SER) is the task of recognising human's emotional states from speech. SER is extremely prevalent in helping dialogue systems to truly understand our emotions and become a trustworthy human conversational partner.…

Sound · Computer Science 2022-10-27 Zhao Ren , Thanh Tam Nguyen , Yi Chang , Björn W. Schuller

Improving the performance of semantic segmentation models using multispectral information is crucial, especially for environments with low-light and adverse conditions. Multi-modal fusion techniques pursue either the learning of…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Aniruddh Sikdar , Jayant Teotia , Suresh Sundaram

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains…

An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often involves learning new services and confronting…

Computation and Language · Computer Science 2024-10-17 Yujie Feng , Bo Liu , Xiaoyu Dong , Zexin Lu , Li-Ming Zhan , Albert Y. S. Lam , Xiao-Ming Wu

Emotion recognition is an important component of affective computing, and also human-machine interaction. Unimodal emotion recognition is convenient, but the accuracy may not be high enough; on the contrary, multi-modal emotion recognition…

Human-Computer Interaction · Computer Science 2026-02-12 Siyuan Kan , Huanyu Wu , Zhenyao Cui , Fan Huang , Xiaolong Xu , Dongrui Wu

Studies on emotion recognition (ER) show that combining lexical and acoustic information results in more robust and accurate models. The majority of the studies focus on settings where both modalities are available in training and…

Computation and Language · Computer Science 2019-06-26 Gustavo Aguilar , Viktor Rozgić , Weiran Wang , Chao Wang

Previous work on multimodal sentence embedding has proposed multimodal contrastive learning and achieved promising results. However, by taking the rest of the batch as negative samples without reviewing when forming contrastive pairs, those…

Computation and Language · Computer Science 2024-03-27 Cong-Duy Nguyen , Thong Nguyen , Xiaobao Wu , Anh Tuan Luu

Training large foundation models using self-supervised objectives on unlabeled data, followed by fine-tuning on downstream tasks, has emerged as a standard procedure. Unfortunately, the efficacy of this approach is often constrained by both…

Recently, multi-modal content generation has attracted lots of attention from researchers by investigating the utilization of visual instruction tuning based on large language models (LLMs). To enhance the performance and generalization…

Computer Vision and Pattern Recognition · Computer Science 2023-11-15 Xinwei Li , Li Lin , Shuai Wang , Chen Qian