English

Boosting Video-Text Retrieval with Explicit High-Level Semantics

Computer Vision and Pattern Recognition 2022-08-10 v2

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.

Keywords

Cite

@article{arxiv.2208.04215,
  title  = {Boosting Video-Text Retrieval with Explicit High-Level Semantics},
  author = {Haoran Wang and Di Xu and Dongliang He and Fu Li and Zhong Ji and Jungong Han and Errui Ding},
  journal= {arXiv preprint arXiv:2208.04215},
  year   = {2022}
}

Comments

Accepted by ACMMM 2022

R2 v1 2026-06-25T01:34:19.848Z