Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition

arXiv:2401.06287v2 Announce Type: replace
Abstract: Audio-visual video recognition (AVVR) aims to integrate audio and visual clues to categorize videos accurately. While existing methods train AVVR models using provided datasets and achieve satisfactory results, they struggle to retain historical class knowledge when confronted with new classes in real-world situations. Currently, there are no dedicated methods for addressing this problem, so this paper concentrates on exploring Class Incremental Audio-Visual Video Recognition (CIAVVR). For CIAVVR, since both stored data and learned model of …

abstract arxiv audio augmentation class cs.cv datasets distillation hierarchical incremental knowledge recognition results struggle train type video videos visual world