M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining-Reference-Cited by-同舟云学术

M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Dong Xiao¹,Zhan Xunlin¹,Wu Yangxin¹,Wei Yunchao²,Kampffmeyer Michael C.³,Wei Xiaoyong⁴,Lu Minlong⁵,Wang Yaowei⁴,Liang Xiaodan¹

Affiliation:

1. Sun Yat-sen University

2. Beijing Jiaotong University

3. UiT The Arctic University of Norway

4. PengCheng Laboratory

5. Alibaba Group

Funder

Shenzhen Fundamental Research Program

National Key RD Program of China

CAAI-Huawei MindSpore Open Fund

Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology

Publisher

IEEE

Link

Reference59 articles.

1. Zero-shot text-to-image generation;ramesh;ICML volume 139 of Proceedings of Machine Learning Research,2021

2. Learning transferable visual models from natural language supervision;radford;ICML,2021

4. Howto100m: Learning a text-video embedding by watching hundred million narrated video clips;miech;ICCV,2019

Cited by 20 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24

2. Scaling Object-centric Robotic Manipulation with Multimodal Object Identification;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

4. Complementary-Contradictory Feature Regularization against Multimodal Overfitting;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03