Publications

See full publications in Google Scholar.

FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval

Published in AAAI, 2024

TL;DR: This paper defines and analyzes the common phenomenon of “visual dominance” in the composed image retrieval task, where retrieval results are dominated by reference images and overlook the modification text. To mitigate this “visual dominance”, we propose a Fashion Enhance-and-Refine Network (FashionERN) that enhances text semantics and filters visual semantics.

Recommended citation: Yanzhe Chen, Huasong Zhong, Xiangteng He, Yuxin Peng, Jiahuan Zhou and Lele Cheng, "FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval", AAAI 2024.
Download Paper

Real20M: A Large-scale E-commerce Dataset for Cross-domain Retrieval

Published in ACM MM, 2023

TL;DR: We propose a cross-domain retrieval benchmark and a corresponding large-scale e-commerce dataset Real20M, which possesses features: (1) cross-domain and multimodal, (2) query-driven, and (3) massive and diverse. We also present a query-driven framework for aligning the product and micro-video domains.

Recommended citation: Yanzhe Chen, Huasong Zhong, Xiangteng He, Yuxin Peng and Lele Cheng, "Real20M: A Large-scale E-commerce Dataset for Cross-domain Retrieval", ACM MM 2023.
Download Paper