Temporal and cross-modal attention for audio-visual zero-shot learning
This addresses the problem of recognizing novel, unseen classes in videos for researchers in computer vision and multimedia, representing an incremental improvement over existing methods.
The paper tackles audio-visual zero-shot learning for video classification by proposing a multi-modal and temporal cross-attention framework that focuses on cross-modal correspondence across time, achieving state-of-the-art performance on benchmarks like UCF, VGG, and ActivityNet.
Audio-visual generalised zero-shot learning for video classification requires understanding the relations between the audio and visual information in order to be able to recognise samples from novel, previously unseen classes at test time. The natural semantic and temporal alignment between audio and visual data in video data can be exploited to learn powerful representations that generalise to unseen classes at test time. We propose a multi-modal and Temporal Cross-attention Framework (\modelName) for audio-visual generalised zero-shot learning. Its inputs are temporally aligned audio and visual features that are obtained from pre-trained networks. Encouraging the framework to focus on cross-modal correspondence across time instead of self-attention within the modalities boosts the performance significantly. We show that our proposed framework that ingests temporal features yields state-of-the-art performance on the \ucf, \vgg, and \activity benchmarks for (generalised) zero-shot learning. Code for reproducing all results is available at \url{https://github.com/ExplainableML/TCAF-GZSL}.