CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding.

Xingyu Bruce Liu Ruolin Wang Dingzeyu Li Xiang Anthony Chen Amy Pavel

Published in: UIST (2022)

Keyphrases

cross modal
multi modal
visual data
video sequences
multimedia
video data
video streams
video content
multimedia retrieval
video analysis
semantic concepts
image retrieval
space time
high dimensional
video frames
multimedia data
multimedia databases
visual recognition
event detection
image search