Totems: Physical Objects for Verifying Visual Integrity

no code implementations • 26 Sep 2022 • Jingwei Ma, Lucy Chai, Minyoung Huh, Tongzhou Wang, Ser-Nam Lim, Phillip Isola, Antonio Torralba

We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene.

Image Forensics

A Unified Model for Recommendation with Selective Neighborhood Modeling

no code implementations • 19 Oct 2020 • Jingwei Ma, Jiahui Wen, Panpan Zhang, Guangda Zhang, Xue Li

To address this issue, we propose a novel neighborhood-based recommender, where a hybrid gated network is designed to automatically separate similar neighbors from dissimilar (noisy) ones, and aggregate those similar neighbors to comprise neighborhood representations.

Collaborative Filtering

Hierarchical Text Interaction for Rating Prediction

no code implementations • 15 Oct 2020 • Jiahui Wen, Jingwei Ma, Hongkui Tu, Wei Yin, Jian Fang

At review level, we mutually propagate textual features between the user and item, and capture the informative reviews.

Collaborative Filtering Recommendation Systems

DBRec: Dual-Bridging Recommendation via Discovering Latent Groups

no code implementations • 27 Sep 2019 • Jingwei Ma, Jiahui Wen, Mingyang Zhong, Liangchen Liu, Chaojie Li, Weitong Chen, Yin Yang, Honghui Tu, Xue Li

In addition, we propose to jointly learn user-user group (item-item group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations.

Collaborative Filtering Recommendation Systems