Ran Jing
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ran Jing has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Ruifeng Xu
Harbin Institute of Technology, Shenzhen, China
4 shared publications - Geng Tu
Harbin Institute of Technology, Shenzhen, China
3 shared publications - Bojun Jin
Harbin Institute of Technology, Shenzhen, China and Shenzhen Loop Area Institute, Shenzhen, China
2 shared publications - Qiwei Lang
Harbin Institute of Technology, Shenzhen, China and Shenzhen Loop Area Institute, Shenzhen, China
2 shared publications - Shengzhe Sun
Harbin Institute of Technology, Shenzhen, China
2 shared publications - Yang Wu
Department of Computer Science, City University of Hong Kong, Hong Kong, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17415-17421
Consensus-Guided Iterative Refinement for Multimodal Emotion Preference Prediction in MER 2026 Track 3
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17415-17421
Open AccessConsensus-Guided Iterative Refinement for Multimodal Emotion Preference Prediction in MER 2026 Track 3
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17633-17639
Cross-Session Multimodal Fusion for AdoDAS Prediction
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17633-17639
Open AccessCross-Session Multimodal Fusion for AdoDAS Prediction
- Top Cited Papers
- 17 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
Is multimodal conversational emotion recognition satisfactory? Exploring the gaps in performance, generalization, and confidence
- 17 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
Top Cited PapersIs multimodal conversational emotion recognition satisfactory? Exploring the gaps in performance, generalization, and confidence
- 1 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (4) , 3043-3054
Generalizing to Unseen Speakers: Multimodal Emotion Recognition in Conversations With Speaker Generalization
Multimodal Emotion Recognition in Conversations (MERC) aims to identify the emotion expressed in each utterance within conversational videos. Current efforts are directed toward modeling speaker-sensitive context dependencies and multimodal fusion. However, they still struggle to handle utterances from unseen speakers, hampering the model's generalizability. To tackle this challenge, we propose a Speaker Generalization Framework for MERC. Specifically, we build a prototype graph to learn Speaker-based Utterance Representations (SUR), leveraging prototypes as the bridge between seen and unseen speakers. Speaker-aware Contrastive Learning (CL) is then applied to refine SUR, pulling utterances (or prototypes) from the same speaker together while pushing those from different speakers apart. Further, we introduce a prototypical graph CL to generalize SUR to unseen speakers, ensuring that the same speakers exhibit similar graph structures, while dissimilar ones differ. To further enhance model generalization, we introduce Uncertainty-based Generalization for Speakers, randomly sampling SUR statistics from the estimated Gaussian distribution and probabilistically replacing the original SUR. Experimental findings on two datasets highlight that our framework substantially improves the generalization of various MERC models, surpassing state-of-the-art methods.
- 1 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (4) , 3043-3054
Generalizing to Unseen Speakers: Multimodal Emotion Recognition in Conversations With Speaker Generalization
Multimodal Emotion Recognition in Conversations (MERC) aims to identify the emotion expressed in each utterance within conversational videos. Current efforts are directed toward modeling speaker-sensitive context dependencies and multimodal fusion. However, they still struggle to handle utterances from unseen speakers, hampering the model's generalizability. To tackle this challenge, we propose a Speaker Generalization Framework for MERC. Specifically, we build a prototype graph to learn Speaker-based Utterance Representations (SUR), leveraging prototypes as the bridge between seen and unseen speakers. Speaker-aware Contrastive Learning (CL) is then applied to refine SUR, pulling utterances (or prototypes) from the same speaker together while pushing those from different speakers apart. Further, we introduce a prototypical graph CL to generalize SUR to unseen speakers, ensuring that the same speakers exhibit similar graph structures, while dissimilar ones differ. To further enhance model generalization, we introduce Uncertainty-based Generalization for Speakers, randomly sampling SUR statistics from the estimated Gaussian distribution and probabilistically replacing the original SUR. Experimental findings on two datasets highlight that our framework substantially improves the generalization of various MERC models, surpassing state-of-the-art methods.