Boosting Video-Text Retrieval with Explicit High-Level Semantics

TL;DR

This paper introduces HiSE, a novel model for video-text retrieval that incorporates explicit high-level semantic information from both modalities, significantly improving cross-modal alignment and retrieval performance.

Contribution

The work proposes a hierarchical high-level semantic modeling approach for VTR, decomposing semantics into discrete and holistic levels and integrating them via graph reasoning.

Findings

Achieves superior performance on MSR-VTT, MSVD, and DiDeMo datasets.

Effectively models high-level semantics to improve cross-modal alignment.

Outperforms state-of-the-art methods in video-text retrieval tasks.

Abstract

Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual information to align video and text, whilst lacking the awareness of homogeneous high-level semantic information residing in both modalities. To fill this gap, in this work, we propose a novel visual-linguistic aligning model named HiSE for VTR, which improves the cross-modal representation by incorporating explicit high-level semantics. First, we explore the hierarchical property of explicit high-level semantics, and further decompose it into two levels, i.e. discrete semantics and holistic semantics. Specifically, for visual branch, we exploit an off-the-shelf semantic entity predictor to generate discrete high-level semantics. In parallel, a trained video captioning model is employed to output holistic high-level semantics. As for the textual modality, we parse the text into three parts including occurrence, action and entity. In particular, the occurrence corresponds to the holistic high-level semantics, meanwhile both action and entity represent the discrete ones. Then, different graph reasoning techniques are utilized to promote the interaction between holistic and discrete high-level semantics. Extensive experiments demonstrate that, with the aid of explicit high-level semantics, our method achieves the superior performance over state-of-the-art methods on three benchmark datasets, including MSR-VTT, MSVD and DiDeMo.