Sounak Mondal

Analysis (1)

scanpath prediction (3) gaze prediction (3) visual search (2) eye tracking (2) zero-shot learning (2) vision-language alignment (1) bottom-up attention (1) visual attention (1) personalized model (1) vision-language model (1) semantic encoding (1) fixation prediction (1) gaze scanpath (1) top-down attention (1) transformer architecture (1) subject embedding (1) representation learning (1) contrastive learning (1) metric learning (1) few-shot learning (1)