# Multi-level Attention Fusion Network for Audio-visual Event Recognition Source: [Multi-level Attention Fusion Network for Audio-visual Event Recognition]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:18:37.363Z Authors: Mathilde Brousmiche, Jean Rouat, St\\'ephane Dupont Published: 2021-06-12T10:24:52.000Z ## Abstract Event classification is inherently sequential and multimodal. Therefore, deep neural models need to dynamically focus on the most relevant time window and/or modality of a video. In this study, we propose the Multi-level Attention Fusion network (MAFnet), an architecture that can dynamically fuse visual and audio information for event recognition. Inspired by prior studies in neuroscience, we couple both modalities at different levels of visual and audio paths. Furthermore, the network dynamically highlights a modality at a given time window relevant to classify events. Experimental results in AVE (Audio-Visual Event), UCF51, and Kinetics-Sounds datasets show that the approach can effectively improve the accuracy in audio-visual event classification. Code is available at: https://github.com/numediart/MAFnet ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()