# LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training Source: [LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:23:36.215Z Authors: Sumanth Gurram, Andy Fang, David Chan, John Canny Published: 2022-07-16T21:46:16.000Z ## Abstract Generating representations of video data is of key importance in advancing the field of machine perception. Most current techniques rely on hand-annotated data, which can be difficult to work with, expensive to generate, and hard to scale. In this work, we propose a novel learning approach based on contrastive learning, LAVA, which is capable of learning joint language, audio, and video representations in a self-supervised manner. We pre-train LAVA on the Kinetics 700 dataset using transformer encoders to learn representations for each modality. We then demonstrate that LAVA performs competitively with the current state-of-the-art self-supervised and weakly-supervised pretraining techniques on UCF-101 and HMDB-51 video action recognition while using a fraction of the unlabeled data. ## 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]()