中文
相关论文

相关论文: A Mixture-of-Experts Model for Multimodal Emotion …

200 篇论文

Emotion Recognition in Conversations (ERC) is an important and active research area. Recent work has shown the benefits of using multiple modalities (e.g., text, audio, and video) for the ERC task. In a conversation, participants tend to…

计算与语言 · 计算机科学 2022-11-08 Harsh Agarwal , Keshav Bansal , Abhinav Joshi , Ashutosh Modi

Emotion Recognition in Conversation (ERC) plays a crucial role in enabling dialogue systems to effectively respond to user requests. The emotions in a conversation can be identified by the representations from various modalities, such as…

计算与语言 · 计算机科学 2024-04-02 Taeyang Yun , Hyunkuk Lim , Jeonghwan Lee , Min Song

The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual information. Previous ERC methods relied on simple connections for cross-modal fusion and ignored the…

计算与语言 · 计算机科学 2024-05-29 Haoxiang Shi , Xulong Zhang , Ning Cheng , Yong Zhang , Jun Yu , Jing Xiao , Jianzong Wang

Advances in multimodal models have greatly improved how interactions relevant to various tasks are modeled. Today's multimodal models mainly focus on the correspondence between images and text, using this for tasks like image-text matching.…

计算与语言 · 计算机科学 2024-09-27 Haofei Yu , Zhengyang Qi , Lawrence Jang , Ruslan Salakhutdinov , Louis-Philippe Morency , Paul Pu Liang

Emotion Recognition in Conversation~(ERC) across modalities is of vital importance for a variety of applications, including intelligent healthcare, artificial intelligence for conversation, and opinion mining over chat history. The crux of…

计算与语言 · 计算机科学 2023-06-07 Xingwei Liang , You Zou , Ruifeng Xu

Emotion Recognition in Conversation (ERC) plays an important role in driving the development of human-machine interaction. Emotions can exist in multiple modalities, and multimodal ERC mainly faces two problems: (1) the noise problem in the…

计算与语言 · 计算机科学 2023-10-10 Shihao Zou , Xianying Huang , Xudong Shen

Emotion Recognition in Conversations (ERC) is hard because discriminative evidence is sparse, localized, and often asynchronous across modalities. We center ERC on emotion hotspots and present a unified model that detects per-utterance…

计算与语言 · 计算机科学 2025-10-13 Yu Liu , Hanlei Shi , Haoxun Li , Yuqing Sun , Yuxuan Ding , Linlin Gong , Leyuan Qu , Taihao Li

Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors. From a psychological perspective, emotions are the expression of affect or feelings…

计算与语言 · 计算机科学 2022-11-22 Guimin Hu , Ting-En Lin , Yi Zhao , Guangming Lu , Yuchuan Wu , Yongbin Li

Emotion Recognition in Conversation (ERC) aims to detect the emotions of individual utterances within a conversation. Generating efficient and modality-specific representations for each utterance remains a significant challenge. Previous…

机器学习 · 计算机科学 2025-06-24 Jie Li , Shifei Ding , Lili Guo , Xuan Li

Multimodal emotion recognition (MER) is crucial for human-computer interaction, yet real-world challenges like dynamic modality incompleteness and asynchrony severely limit its robustness. Existing methods often assume consistently complete…

人机交互 · 计算机科学 2025-08-19 Yitong Zhu , Lei Han , Guanxuan Jiang , PengYuan Zhou , Yuyang Wang

Emotion Recognition in Conversations (ERC) is a key step towards successful human-machine interaction. While the field has seen tremendous advancement in the last few years, new applications and implementation scenarios present novel…

计算与语言 · 计算机科学 2024-10-22 Patrícia Pereira , Helena Moniz , Joao Paulo Carvalho

While text-based emotion recognition methods have achieved notable success, real-world dialogue systems often demand a more nuanced emotional understanding than any single modality can offer. Multimodal Emotion Recognition in Conversations…

计算与语言 · 计算机科学 2025-09-10 Chengyan Wu , Yiqiang Cai , Yang Liu , Pengxu Zhu , Yun Xue , Ziwei Gong , Julia Hirschberg , Bolei Ma

Emotion Recognition in Conversations (ERC) is crucial in developing sympathetic human-machine interaction. In conversational videos, emotion can be present in multiple modalities, i.e., audio, video, and transcript. However, due to the…

计算机视觉与模式识别 · 计算机科学 2022-06-07 Vishal Chudasama , Purbayan Kar , Ashish Gudmalwar , Nirmesh Shah , Pankaj Wasnik , Naoyuki Onoe

Emotion recognition in conversation (ERC) aims to detect the emotion for each utterance in a given conversation. The newly proposed ERC models have leveraged pre-trained language models (PLMs) with the paradigm of pre-training and…

计算与语言 · 计算机科学 2022-07-28 Jingjie Yi , Deqing Yang , Siyu Yuan , Caiyan Cao , Zhiyao Zhang , Yanghua Xiao

Multilingual speech recognition for both monolingual and code-switching speech is a challenging task. Recently, based on the Mixture of Experts (MoE), many works have made good progress in multilingual and code-switching ASR, but present…

声音 · 计算机科学 2023-07-17 Wenxuan Wang , Guodong Ma , Yuke Li , Binbin Du

Named Entity Recognition (NER) is an essential steppingstone in the field of natural language processing. Although promising performance has been achieved by various distantly supervised models, we argue that distant supervision inevitably…

计算与语言 · 计算机科学 2024-05-01 Xinwei Chen , Kun Li , Tianyou Song , Jiangjian Guo

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer from two critical limitations: (1) inefficient token-to-expert…

计算与语言 · 计算机科学 2025-10-10 Jing Li , Zhijie Sun , Dachao Lin , Xuan He , Binfan Zheng , Yi Lin , Rongqian Zhao , Xin Chen

Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs)…

计算与语言 · 计算机科学 2026-05-12 Ryan Wang , Akshita Bhagia , Sewon Min

Due to the inherent difficulty in modeling phonetic similarities across different languages, code-switching speech recognition presents a formidable challenge. This study proposes a Collaborative-MoE, a Mixture of Experts (MoE) model that…

计算与语言 · 计算机科学 2024-09-06 Hukai Huang , Jiayan Lin , Kaidi Wang , Yishuang Li , Wenhao Guan , Lin Li , Qingyang Hong

Multimodal emotion understanding requires effective integration of text, audio, and visual modalities for both discrete emotion recognition and continuous sentiment analysis. We present EGMF, a unified framework combining expert-guided…

计算与语言 · 计算机科学 2026-01-13 Jiaqi Qiao , Xiujuan Xu , Xinran Li , Yu Liu
‹ 上一页 1 2 3 10 下一页 ›