Avlnet: Learning Audio-visual Language Representations From Instructional Videos

Abstract

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 e

Stats

• citations51
• S2 citations—
• github stars0
• HF likes0
• heat score12.87
• arxiv keyrouditchenko2020avlnet

Related papers

• Objects That Sound (2017)0.00
• Learning Language-visual Embedding For Movie Understanding With Natural-language (2016)0.00
• Separating The "chirp" From The "chat": Self-supervised Visual Grounding Of Sound And Language (2024)7.50
• Jointly Discovering Visual Objects And Spoken Words From Raw Sensory Input (2018)14.27
• Learning Audio-video Modalities From Image Captions (2022)12.54
• Litevl: Efficient Video-language Learning With Enhanced Spatial-temporal Modeling (2022)6.34
• See, Hear, And Read: Deep Aligned Representations (2017)0.00
• Distilling Vision-language Models On Millions Of Videos (2024)7.50