QUAG, a query-centric audio-visual cognition network, reports state-of-the-art moment retrieval and segmentation on HIREST and competitive video summarization on TVSum.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning
QUAG, a query-centric audio-visual cognition network, reports state-of-the-art moment retrieval and segmentation on HIREST and competitive video summarization on TVSum.