MAiVAR: Multimodal Audio-Image and Video Action Recognizer
This addresses action recognition for video analysis applications, but it is incremental as it builds on existing CNN methods by adding multimodal fusion.
The authors tackled action recognition by proposing MAiVAR, a CNN-based model that fuses audio-image and video modalities, achieving superior performance compared to individual modalities on a large-scale dataset.
Currently, action recognition is predominately performed on video data as processed by CNNs. We investigate if the representation process of CNNs can also be leveraged for multimodal action recognition by incorporating image-based audio representations of actions in a task. To this end, we propose Multimodal Audio-Image and Video Action Recognizer (MAiVAR), a CNN-based audio-image to video fusion model that accounts for video and audio modalities to achieve superior action recognition performance. MAiVAR extracts meaningful image representations of audio and fuses it with video representation to achieve better performance as compared to both modalities individually on a large-scale action recognition dataset.