Boosting Video-Text Retrieval with Explicit High-Level Semantics

被引:6
|
作者
Wang, Haoran [1 ]
Xu, Di [2 ]
He, Dongliang [1 ]
Li, Fu [1 ]
Ji, Zhong [3 ]
Han, Jungong [4 ]
Ding, Errui [1 ]
机构
[1] Baidu Inc, Dept Comp Vis Technol VIS, Beijing, Peoples R China
[2] Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
[3] Tianjin Univ, Sch Elect & Informat Engn, Tianjin, Peoples R China
[4] Aberystwyth Univ, Comp Sci Dept, Aberystwyth SY23 3FL, Dyfed, Wales
关键词
Video-Text Retrieval; High-level Semantics; Vision-language Understanding;
D O I
10.1145/3503161.3548010
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
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.
引用
收藏
页码:4887 / 4898
页数:12
相关论文
共 50 条
  • [1] Mask to Reconstruct: Cooperative Semantics Completion for Video-text Retrieval
    Fang, Han
    Yang, Zhifei
    Zang, Xianghao
    Ban, Chao
    He, Zhongjiang
    Sun, Hao
    Zhou, Lanxiang
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 3847 - 3856
  • [2] Learning Semantics-Grounded Vocabulary Representation for Video-Text Retrieval
    Shi, Yaya
    Liu, Haowei
    Xu, Haiyang
    Ma, Zongyang
    Ye, Qinghao
    Hu, Anwen
    Yan, Ming
    Zhang, Ji
    Huang, Fei
    Yuan, Chunfeng
    Li, Bing
    Hu, Weiming
    Zha, Zheng-Jun
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 4460 - 4470
  • [3] A NOVEL CONVOLUTIONAL ARCHITECTURE FOR VIDEO-TEXT RETRIEVAL
    Li, Zheng
    Guo, Caili
    Yang, Bo
    Feng, Zerun
    Zhang, Hao
    2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2020,
  • [4] Deep learning for video-text retrieval: a review
    Zhu, Cunjuan
    Jia, Qi
    Chen, Wei
    Guo, Yanming
    Liu, Yu
    INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2023, 12 (01)
  • [5] Progressive Semantic Matching for Video-Text Retrieval
    Liu, Hongying
    Luo, Ruyi
    Shang, Fanhua
    Niu, Mantang
    Liu, Yuanyuan
    PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 5083 - 5091
  • [6] Multi-event Video-Text Retrieval
    Zhang, Gengyuan
    Ren, Jisen
    Gu, Jindong
    Tresp, Volker
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 22056 - 22066
  • [7] A Framework for Video-Text Retrieval with Noisy Supervision
    Vaseqi, Zahra
    Fan, Pengnan
    Clark, James
    Levine, Martin
    PROCEEDINGS OF THE 2022 INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, ICMI 2022, 2022, : 373 - 383
  • [8] Deep learning for video-text retrieval: a review
    Cunjuan Zhu
    Qi Jia
    Wei Chen
    Yanming Guo
    Yu Liu
    International Journal of Multimedia Information Retrieval, 2023, 12
  • [9] Visual Consensus Modeling for Video-Text Retrieval
    Cao, Shuqiang
    Wang, Bairui
    Zhang, Wei
    Ma, Lin
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 167 - 175
  • [10] MILES: Visual BERT Pre-training with Injected Language Semantics for Video-Text Retrieval
    Ge, Yuying
    Ge, Yixiao
    Liu, Xihui
    Wang, Jinpeng
    Wu, Jianping
    Shan, Ying
    Qie, Xiaohu
    Luo, Ping
    COMPUTER VISION - ECCV 2022, PT XXXV, 2022, 13695 : 691 - 708