Multi-scale temporal convolutions plus capsule routing improve video-text moment localization to 42.9% R@0.5 and 41.1% mIoU on ActivityNet Captions.
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Video-Text Temporal Localization via Multi-Scale Convolution and Dynamic Routing
Multi-scale temporal convolutions plus capsule routing improve video-text moment localization to 42.9% R@0.5 and 41.1% mIoU on ActivityNet Captions.