TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding

TL;DR

This paper introduces TAG, a straightforward temporal-aware method for zero-shot video temporal grounding that improves localization accuracy by capturing temporal context and addressing similarity distortions without additional training.

Contribution

The paper presents a novel zero-shot VTG approach incorporating temporal pooling, coherence clustering, and similarity adjustment, outperforming existing methods without relying on LLMs.

Findings

Achieves state-of-the-art results on Charades-STA and ActivityNet Captions datasets.

Effectively captures temporal context and reduces semantic fragmentation.

Does not require training or large language models.

Abstract

Video Temporal Grounding (VTG) aims to extract relevant video segments based on a given natural language query. Recently, zero-shot VTG methods have gained attention by leveraging pretrained vision-language models (VLMs) to localize target moments without additional training. However, existing approaches suffer from semantic fragmentation, where temporally continuous frames sharing the same semantics are split across multiple segments. When segments are fragmented, it becomes difficult to predict an accurate target moment that aligns with the text query. Also, they rely on skewed similarity distributions for localization, making it difficult to select the optimal segment. Furthermore, they heavily depend on the use of LLMs which require expensive inferences. To address these limitations, we propose a \textit{TAG}, a simple yet effective Temporal-Aware approach for zero-shot video temporal Grounding, which incorporates temporal pooling, temporal coherence clustering, and similarity adjustment. Our proposed method effectively captures the temporal context of videos and addresses distorted similarity distributions without training. Our approach achieves state-of-the-art results on Charades-STA and ActivityNet Captions benchmark datasets without rely on LLMs. Our code is available at https://github.com/Nuetee/TAG