JoVALE: Detecting Human Actions in Video Using Audiovisual and Language Contexts

TL;DR

JoVALE is a novel multi-modal video action detection system that integrates audio, visual, and scene language context using a transformer-based architecture, achieving state-of-the-art results on key benchmarks.

Contribution

This work introduces the first VAD method to combine audio, visual, and scene language features through an actor-centric transformer model, advancing multi-modal action recognition.

Findings

Achieves new state-of-the-art performance on AVA, UCF101-24, and JHMDB51-21 benchmarks.

Demonstrates that multi-modal integration significantly improves action detection accuracy.

Validates the effectiveness of scene descriptive context in enhancing VAD performance.

Abstract

Video Action Detection (VAD) entails localizing and categorizing action instances within videos, which inherently consist of diverse information sources such as audio, visual cues, and surrounding scene contexts. Leveraging this multi-modal information effectively for VAD poses a significant challenge, as the model must identify action-relevant cues with precision. In this study, we introduce a novel multi-modal VAD architecture, referred to as the Joint Actor-centric Visual, Audio, Language Encoder (JoVALE). JoVALE is the first VAD method to integrate audio and visual features with scene descriptive context sourced from large-capacity image captioning models. At the heart of JoVALE is the actor-centric aggregation of audio, visual, and scene descriptive information, enabling adaptive integration of crucial features for recognizing each actor's actions. We have developed a Transformer-based architecture, the Actor-centric Multi-modal Fusion Network, specifically designed to capture the dynamic interactions among actors and their multi-modal contexts. Our evaluation on three prominent VAD benchmarks, including AVA, UCF101-24, and JHMDB51-21, demonstrates that incorporating multi-modal information significantly enhances performance, setting new state-of-the-art performances in the field.