Search papers, labs, and topics across Lattice.
Nanjing University of Posts and Telecommunications, Center for Machine Vision and Signal Analysis, Nanjing university of posts and telecommunications, University of Oulu, *Corresponding author
3
0
3
Micro-gesture recognition gets a boost from a new method that uses fine-grained semantic guidance to capture subtle motion differences.
By explicitly modeling the shift from local independence to global dependencies between facial action units, micro-AU CLIP achieves state-of-the-art performance in micro-expression analysis.
Recognizing emotions from deliberately disguised facial expressions is now possible thanks to a new method that focuses on the apex of the disguise, rather than its onset.
