We present Attend-Fusion, a novel and efficient approach for audio-visual fusion in video classification tasks. Our method addresses the challenge of exploiting both audio and visual modalities while maintaining a compact model architecture. Through extensive experiments on the YouTube-8M dataset, we demonstrate that our Attend-Fusion achieves competitive performance with significantly reduced model complexity compared to larger baseline models.
@article{arxiv.2411.05603,
title = {Efficient Audio-Visual Fusion for Video Classification},
author = {Mahrukh Awan and Asmar Nadeem and Armin Mustafa},
journal= {arXiv preprint arXiv:2411.05603},
year = {2024}
}