Search Results for author: Xiangyu Wei

Found 3 papers, 2 papers with code

Partial Relaxed Optimal Transport for Denoised Recommendation

no code implementations19 Apr 2022 Yanchao Tan, Carl Yang Member, Xiangyu Wei, Ziyue Wu, Xiaolin Zheng

The interaction data used by recommender systems (RSs) inevitably include noises resulting from mistaken or exploratory clicks, especially under implicit feedbacks.

Denoising Recommendation Systems

Multi-Facet Recommender Networks with Spherical Optimization

1 code implementation27 Mar 2021 Yanchao Tan, Carl Yang, Xiangyu Wei, Yun Ma, Xiaolin Zheng

Metric learning has been proposed to capture user-item interactions from implicit feedback, but existing methods only represent users and items in a single metric space, ignoring the fact that users can have multiple preferences and items can have multiple properties, which leads to potential conflicts limiting their performance in recommendation.

Metric Learning Recommendation Systems +1

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

4 code implementations15 Nov 2019 Okan Köpüklü, Xiangyu Wei, Gerhard Rigoll

YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation.

Action Recognition In Videos

Cannot find the paper you are looking for? You can Submit a new open access paper.