Recently, Team of Intelligent Decision and Control Technology from SEE (School of Electrical Engineering) published its important findings titled VITO-Transformer: A Visual-Tactile Fusion Network for Object Recognition in the prestigious journal of the measurement field IEEE Transactions on Instrumentation and Measurement (with an Impact Factor of 5.6, ranking Q2 in JCR of Chinese Academy of Sciences [CAS]). Li Baojiang stands out as the first author and corresponding author with SDJU as first author affiliation.
Object recognition stands as a crucial research area within artificial intelligence. Despite substantial advancements in various recognition algorithms, the challenge persists when faced with objects exhibiting similar or limited visual information, and recognizing such objects remain difficult and formidable task. Addressing this challenge, the SEE Team has proposed a VITO-Transformer fusion network. This innovative approach aims to tackle the intricate fusion of visual-tactile multimodal heterogeneous information associated with objects. The VITO-Transformer utilizes a specialized visual-tactile fusion mechanism to process diverse multimodal information, presenting a novel solution to advance the development of visual-tactile fusion in the field.
link: https://ieeexplore.ieee.org/document/10288485