AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
This work addresses the need for efficient multi-modal learning in AI by enabling audio-visual representation learning from raw data, though it is incremental as it builds on existing self-supervised and multi-modal approaches.
The authors tackled the problem of learning audio-visual language representations without relying on text annotations by introducing AVLnet, a self-supervised network trained on instructional videos, which achieved state-of-the-art performance on image and video retrieval tasks.
Current methods for learning visually grounded language from videos often rely on text annotation, such as human generated captions or machine generated automatic speech recognition (ASR) transcripts. In this work, we introduce the Audio-Video Language Network (AVLnet), a self-supervised network that learns a shared audio-visual embedding space directly from raw video inputs. To circumvent the need for text annotation, we learn audio-visual representations from randomly segmented video clips and their raw audio waveforms. We train AVLnet on HowTo100M, a large corpus of publicly available instructional videos, and evaluate on image retrieval and video retrieval tasks, achieving state-of-the-art performance. We perform analysis of AVLnet's learned representations, showing our model utilizes speech and natural sounds to learn audio-visual concepts. Further, we propose a tri-modal model that jointly processes raw audio, video, and text captions from videos to learn a multi-modal semantic embedding space useful for text-video retrieval. Our code, data, and trained models will be released at avlnet.csail.mit.edu