Counterfactual Cross-modality Reasoning for Weakly Supervised Video Moment Localization.

Zezhong Lv Bing Su Ji-Rong Wen

Published in: CoRR (2023)

Keyphrases

weakly supervised
object localization
weakly labeled
object class
superpixels
topic models
relation extraction
video sequences
semi supervised
video data
video frames
viewpoint
multiscale
knowledge base
machine learning
key frames
knowledge representation
bayesian networks
information retrieval