Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning

TL;DR

This paper introduces V-HOI MLCR, a framework that enhances video-based human-object interaction detection by leveraging multiple large language models for improved reasoning, validated through accuracy improvements on existing models.

Contribution

The paper proposes a novel multi-LLM collaboration framework with a two-stage reasoning process and auxiliary training to improve V-HOI detection performance.

Findings

Improved prediction accuracy of V-HOI models through multi-LLM reasoning.

Effective two-stage collaboration system for LLMs in scene understanding.

Enhanced discriminative ability via CLIP integration.

Abstract

Human-centered dynamic scene understanding plays a pivotal role in enhancing the capability of robotic and autonomous systems, in which Video-based Human-Object Interaction (V-HOI) detection is a crucial task in semantic scene understanding, aimed at comprehensively understanding HOI relationships within a video to benefit the behavioral decisions of mobile robots and autonomous driving systems. Although previous V-HOI detection models have made significant strides in accurate detection on specific datasets, they still lack the general reasoning ability like human beings to effectively induce HOI relationships. In this study, we propose V-HOI Multi-LLMs Collaborated Reasoning (V-HOI MLCR), a novel framework consisting of a series of plug-and-play modules that could facilitate the performance of current V-HOI detection models by leveraging the strong reasoning ability of different off-the-shelf pre-trained large language models (LLMs). We design a two-stage collaboration system of different LLMs for the V-HOI task. Specifically, in the first stage, we design a Cross-Agents Reasoning scheme to leverage the LLM conduct reasoning from different aspects. In the second stage, we perform Multi-LLMs Debate to get the final reasoning answer based on the different knowledge in different LLMs. Additionally, we devise an auxiliary training strategy that utilizes CLIP, a large vision-language model to enhance the base V-HOI models' discriminative ability to better cooperate with LLMs. We validate the superiority of our design by demonstrating its effectiveness in improving the prediction accuracy of the base V-HOI model via reasoning from multiple perspectives.