Efficient Audio-Visual Fusion for Video Classification

Autor:	Awan, Mahrukh, Nadeem, Asmar, Mustafa, Armin
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: CVMP Short Paper
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.05603 Zobrazit plný text záznamu View this record from Arxiv