Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding.

Peijun Bao Yong Xia Wenhan Yang Boon Poh Ng Meng Hwa Er Alex C. Kot

Published in: AAAI (2024)

Keyphrases

multi modal
weakly supervised
weakly labeled
semantic concepts
multiple modalities
topic models
object class
semi supervised
superpixels
high dimensional
relation extraction
video sequences
multimedia
video data
object detectors
image annotation
key frames
natural language processing
high level
machine learning