Xingtao Wang

Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning

2025 · IEEE Transactions on Circuits and Systems for Video Technology

Audio-visual zero-shot learning (ZSL) has been extensively researched for its capability to classify video data from unseen classes during training. Nevertheless, current methodologies often struggle with background scene biases and inadequate motion detail. This paper …