2022 年 88 巻 3 号 p. 263-268
In this paper, we propose a new method for audio-visual event localization 1) to find the corresponding segment between audio and visual event. While previous methods use Long Short-Term Memory (LSTM) networks to extract temporal features, recurrent neural networks like LSTM are not able to precisely learn long-term features. Thus, we propose a Temporal Cross-Modal Attention (TCMA) module, which extract temporal features more precisely from the two modalities. Inspired by the success of attention modules in capturing long-term features, we introduce TCMA, which incorporates self-attention. Finally, we were able to localize audio-visual event precisely and achieved a higher accuracy than the previous works.