In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, ...
Abstract: Emotion recognition through facial expressions and gesture analysis has emerged as a key area of research in computer vision and human-computer interaction. The ability to automatically ...
Professors Emma Alexander, Manling Li, Han Liu, Marcelo Worsley, and their students represented Northwestern CS at CVPR 2026 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results