Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics.

Hangjie Yuan Mang Wang Dong Ni Liangpeng Xu

Published in: CoRR (2022)

Keyphrases

image sequences
cross modal
human object interactions
human motion
multi modal
visual data

feature points
action recognition
multimedia retrieval
visual recognition
d objects
human actions

human pose
multimedia databases
pose estimation
search engine
image classification
visual similarity

spatial relations
semantic information
contextual information
data processing
multi view