Summary
Mr. Liang Li is a dedicated postgraduate student specializing in multimodal and cross-modal vision research at Shanghai Dianji University. His work has been published in Information Fusion, introducing TVT-Transformer, a cutting-edge framework for fusing tactile, visual, and textual data to enhance object recognition accuracy and support embodied intelligence development.
Education
Postgraduate Student, Shanghai Dianji University
Specializing in multimodal and cross-modal vision, focusing on innovative techniques in data fusion and intelligent systems.
Professional Experience
- Researcher: Developed TVT-Transformer, a three-modal fusion network that integrates tactile, visual, and textual modalities.
- Contributed to the release of the MSDO dataset, advancing standardization in multimodal perception.
Research Interests
- Multimodal Vision: Exploring advanced fusion strategies for tactile, visual, and textual data.
- Cross-Modal AI: Developing intelligent systems for robotics, human-computer interaction, and decision-making assistance.