Skip to content
conftrace_
2024 ICML ICML 2024

STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Jaewoo Lee, Jaehong Yoon, Wonjae Kim, Yunji Kim, Sung Ju Hwang

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Learning Types > Self-Supervised Learning Deep Learning > Techniques > Pretraining

Keywords

zero-shot retrieval continual audio-video pre-training patch importance scoring probabilistic patch selection replay-guided correlation assessment spatio-temporal localized alignment
Download PDF