Training-free Video Temporal Grounding using Large-scale Pre-trained Models

TL;DR

This paper introduces a training-free approach for video temporal grounding that leverages large pre-trained models, especially large language models, to identify relevant video segments without any additional training, improving generalization across datasets.

Contribution

The paper proposes a novel training-free method that combines large visual language models and large language models to improve zero-shot video temporal grounding and handle complex event relationships.

Findings

Achieves state-of-the-art zero-shot performance on Charades-STA and ActivityNet Captions.

Demonstrates superior generalization in cross-dataset and out-of-distribution scenarios.

Effectively models event relationships and transitions without training.

Abstract

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data collection costs, but they exhibit poor generalization capability under the across-dataset and out-of-distribution (OOD) settings. In this paper, we propose a Training-Free Video Temporal Grounding (TFVTG) approach that leverages the ability of pre-trained large models. A naive baseline is to enumerate proposals in the video and use the pre-trained visual language models (VLMs) to select the best proposal according to the vision-language alignment. However, most existing VLMs are trained on image-text pairs or trimmed video clip-text pairs, making it struggle to (1) grasp the relationship and distinguish the temporal boundaries of multiple events within the same video; (2) comprehend and be sensitive to the dynamic transition of events (the transition from one event to another) in the video. To address these issues, we propose leveraging large language models (LLMs) to analyze multiple sub-events contained in the query text and analyze the temporal order and relationships between these events. Secondly, we split a sub-event into dynamic transition and static status parts and propose the dynamic and static scoring functions using VLMs to better evaluate the relevance between the event and the description. Finally, for each sub-event description, we use VLMs to locate the top-k proposals and leverage the order and relationships between sub-events provided by LLMs to filter and integrate these proposals. Our method achieves the best performance on zero-shot video temporal grounding on Charades-STA and ActivityNet Captions datasets without any training and demonstrates better generalization capabilities in cross-dataset and OOD settings.