Jia Li
+
Alma Mater:University of Science and Technology of China
Scientific Research
Current position:
Home
/
Scientific Research
Research Field
Computer Vision
Multimodal Emotion Recognition
Representation Learning
Paper Publications
- Li J, He Y, Xu J, et al. Traits Run Deep: Enhancing Personality Assessment via Psychology-Guided LLM Representations and Multimodal Apparent Behaviors. ACM Multimedia 2025.
- Xiao J, Song Z, J Hu, Z Hu*, J Li*(通讯作者), R Hong. Contrastive Alignment with Semantic Gap-Aware Corrections in Text-Video Retrieval. NeurIPS 2025.
- Cheng H, Zhao Z, He Y, Z Hu, J Li*(通讯作者), et al. VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection. ACM Multimedia 2025.
- Qian W, Hu Z*, Song Z, J Li*(通讯作者). Concept Drift Guided LayerNorm Tuning for Efficient Multimodal Metaphor Identification. ICMR 2025
- Chen Y, Li J*(通讯作者), Zhang Y, et al. Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data. IEEE Transactions on Affective Computing, 2025.
Patents
Published Books
- No content