Zero-shot vision language models achieve moderate accuracy on five-class academic facial expression recognition, with happy easiest and distracted almost never detected.
However, these mod- els face challenges in generalizing well across different con- Table 1: The overall performance of Llama-3.2-11B-Vision-Instruct and Qwen2.5-VL-7B-Instruct
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Using Vision Language Models to Detect Students' Academic Emotion through Facial Expressions
Zero-shot vision language models achieve moderate accuracy on five-class academic facial expression recognition, with happy easiest and distracted almost never detected.