Multi-modal transformer for video retrieval using improved sentence embeddings

Zhi Liu; Fangyuan Zhao; Mengmeng Zhang

doi:10.1117/12.2643741

12 October 2022 Multi-modal transformer for video retrieval using improved sentence embeddings

Zhi Liu, Fangyuan Zhao, Mengmeng Zhang

Author Affiliations +

Proceedings Volume 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022); 1234221 (2022) https://doi.org/10.1117/12.2643741
Event: Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 2022, Wuhan, China

Abstract

With the explosive growth of the number of online videos, video retrieval becomes increasingly difficult. Multi-modal visual and language understanding based video-text retrieval is one of the mainstream framework to solve this problem. Among them, MMT (Multi-modal Transformer) is a novel and mainstream model. On the language side, BERT (Bidirectional Encoder Representation for Transformers) is used to encode text, where the pretrained BERT will be fine tuned during training. However, there exists a mismatch in this stage. The pre-training tasks of BERT is based on NSP (Next Sentence Prediction) and MLM(masked language model) which have weak correlation with video retrieval. For text encoder will encode text into semantic embeddings. On the visual side, Transformer is used to aggregate multimodal experts of videos. We find that the output of visual transformer is not fully utilized. In this paper, a sentence- BERT model is introduced to substitute BERT model in MMT to improve sentence embeddings efficiency. In addition, a max-pooling layer is adopted after Transformer to improve the utilization efficiency of the output of the model. Experiment results show that the proposed model outperforms MMT.

Citation Download Citation

Zhi Liu, Fangyuan Zhao, and Mengmeng Zhang "Multi-modal transformer for video retrieval using improved sentence embeddings", Proc. SPIE 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 1234221 (12 October 2022); https://doi.org/10.1117/12.2643741

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Video

Computer programming

Transformers

Video acceleration

Feature extraction

Visualization

Fourier transforms

Show All Keywords

Keywords/Phrases

Search In:

Publication Years