A query-guided frame and audio segment selection module, called TWM, improves nine multimodal models on AVQA, video captioning, and video-text retrieval in the reported tables.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding
A query-guided frame and audio segment selection module, called TWM, improves nine multimodal models on AVQA, video captioning, and video-text retrieval in the reported tables.