54 citations · 286 across the 25 of their papers we have counts for
7 papers · 1 filter
MRTNet: Multi-Resolution Temporal Network for Video Sentence Grounding
Wei Ji, Long Chen, Yinwei Wei +2
Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by…
Multi-queue Momentum Contrast for Microvideo-Product Retrieval
Yali Du, Yinwei Wei, Wei Ji +3
The booming development and huge market of micro-videos bring new e-commerce channels for merchants. Currently, more micro-video publishers prefer to embed relevant ads into their…
Causal Inference for Knowledge Graph based Recommendation
Yinwei Wei, Xiang Wang, Liqiang Nie +3
Knowledge Graph (KG), as a side-information, tends to be utilized to supplement the collaborative filtering (CF) based recommendation model. By mapping items with the entities in K…
Privacy-Preserving Synthetic Data Generation for Recommendation Systems
Fan Liu, Zhiyong Cheng, Huilin Chen +3
Recommendation systems make predictions chiefly based on users' historical interaction data (e.g., items previously clicked or purchased). There is a risk of privacy leakage when c…
Semantic-aware Modular Capsule Routing for Visual Question Answering
Yudong Han, Jianhua Yin, Jianlong Wu +2
Visual Question Answering (VQA) is fundamentally compositional in nature, and many questions are simply answered by decomposing them into modular sub-problems. The recent proposed…
Joint Answering and Explanation for Visual Commonsense Reasoning
Zhenyang Li, Yangyang Guo, Kejie Wang +3
Visual Commonsense Reasoning (VCR), deemed as one challenging extension of the Visual Question Answering (VQA), endeavors to pursue a more high-level visual comprehension. It is co…
Dual Preference Distribution Learning for Item Recommendation
Xue Dong, Xuemeng Song, Na Zheng +2
Recommender systems can automatically recommend users with items that they probably like. The goal of them is to model the user-item interaction by effectively representing the use…