VERD: Emergence of Product-Based Video E-Commerce Retrieval Dataset from User's Perspective

Editorial Material Computer Science, Information Systems

RPC: a large-scale and fine-grained retail product checkout dataset

Xiu-Shen Wei et al.

SCIENCE CHINA-INFORMATION SCIENCES (2022)

Proceedings Paper Computer Science, Information Systems

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

Wonyoung Shin et al.

Summary: This article introduces a contrastive learning framework to align language and visual models for improving search and recommendation applications in e-commerce. Experimental results show that the framework performs well in various downstream tasks, whether it is single modality or multiple modalities.

PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022 (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

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

Xiao Dong et al.

Summary: This study constructs a large-scale multi-modal pretraining dataset M5Product by leveraging the natural suitability of E-commerce and proposes a novel pretraining framework SCALE to integrate different modalities. Through testing current state-of-the-art multi-modal pretraining methods, the research demonstrates the superior performance of the SCALE model in dealing with a large number of modalities, while also verifying the importance of dataset scale and diversity for pretraining.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Temporal Context Aggregation for Video Retrieval with Contrastive Learning

Jie Shao et al.

Summary: The paper introduces TCA framework for video representation learning that incorporates long-range temporal information using self-attention mechanism, and proposes a supervised contrastive learning method with memory bank mechanism to improve negative sample capacity. Extensive experiments show significant performance advantages in multiple video retrieval tasks.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021 (2021)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic