e-CLIP: Large-Scale Vision-Language Representation Learning in E-commerce

被引:8
|
作者
Shin, Wonyoung [1 ]
Park, Jonghun [1 ]
Woo, Taekang [1 ]
Cho, Yongwoo [1 ]
Oh, Kwangjin [1 ]
Song, Hwanjun [2 ]
机构
[1] NAVER Shopping, Seongnam, South Korea
[2] NAVER AI Res, Seongnam, South Korea
关键词
Multimodal pre-training; Large-scale pre-training;
D O I
10.1145/3511808.3557067
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Understanding vision and language representations of product content is vital for search and recommendation applications in e-commerce. As a backbone for online shopping platforms and inspired by the recent success in representation learning research, we propose a contrastive learning framework that aligns language and visual models using unlabeled raw product text and images. We present techniques we used to train large-scale representation learning models and share solutions that address domain-specific challenges. We study the performance using our pre-trained model as backbones for diverse downstream tasks, including category classification, attribute extraction, product matching, product clustering, and adult product recognition. Experimental results show that our proposed method outperforms the baseline in each downstream task regarding both single modality and multiple modalities.
引用
收藏
页码:3484 / 3494
页数:11
相关论文
共 50 条
  • [1] Unified Vision-Language Representation Modeling for E-Commerce Same-style Products Retrieval
    Chen, Ben
    Jin, Linbo
    Wang, Xinxin
    Gao, Dehong
    Jiang, Wen
    Ning, Wei
    COMPANION OF THE WORLD WIDE WEB CONFERENCE, WWW 2023, 2023, : 381 - 385
  • [2] Delving into E-Commerce Product Retrieval with Vision-Language Pre-training
    Zheng, Xiaoyang
    Lv, Fuyu
    Wang, Zilong
    Liu, Qingwen
    Zeng, Xiaoyi
    PROCEEDINGS OF THE 46TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2023, 2023, : 3385 - 3389
  • [3] Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce
    Jin, Yang
    Li, Yongzhi
    Yuan, Zehuan
    Mu, Yadong
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 11060 - 11069
  • [4] Large-scale Visual Search and Similarity for E-Commerce
    Anand, Gaurav
    Wang, Siyun
    Ni, Karl
    APPLICATIONS OF MACHINE LEARNING 2021, 2021, 11843
  • [5] Ontology management for large-scale e-commerce applications
    Lee, J
    Goodwin, R
    DEEC 2005: International Workshop on Data Engineering Issues in E-Commerce, Proceedings, 2005, : 7 - 15
  • [6] Online E-Commerce Fraud: A Large-scale Detection and Analysis
    Weng, Haiqin
    Li, Zhao
    Ji, Shouling
    Chu, Chen
    Lu, Haifeng
    Du, Tianyu
    He, Qinming
    2018 IEEE 34TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE), 2018, : 1435 - 1440
  • [7] Building Large-Scale Deep Learning System for Entity Recognition in E-Commerce Search
    Wen, Musen
    Vasthimal, Deepak Kumar
    Lu, Alan
    Wang, Tian
    Guo, Aimin
    BDCAT'19: PROCEEDINGS OF THE 6TH IEEE/ACM INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING, APPLICATIONS AND TECHNOLOGIES, 2019, : 149 - 154
  • [8] Learning and Transferring IDs Representation in E-commerce
    Zhao, Kui
    Li, Yuechuan
    Shuai, Zhaoqian
    Yang, Cheng
    KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, : 1031 - 1039
  • [9] Heterogeneous Embedding Propagation for Large-scale E-Commerce User Alignment
    Zheng, Vincent W.
    Sha, Mo
    Li, Yuchen
    Yang, Hongxia
    Fang, Yuan
    Zhang, Zhenjie
    Tan, Kian-Lee
    Chang, Kevin Chen-Chuan
    2018 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2018, : 1434 - 1439
  • [10] Large-scale Robust Online Matching and Its Application in E-commerce
    Jin, Rong
    CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2016, : 1351 - 1351