Search Results for author: Yun He

Found 14 papers, 9 papers with code

PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts

1 code implementation7 Jun 2023 Xiangjue Dong, Yun He, Ziwei Zhu, James Caverlee

A key component of modern conversational systems is the Dialogue State Tracker (or DST), which models a user's goals and needs.

Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions

1 code implementation CVPR 2023 Yun He, Danhang Tang, yinda zhang, xiangyang xue, Yanwei Fu

Most existing point cloud upsampling methods have roughly three steps: feature extraction, feature expansion and 3D coordinate prediction.

Density-preserving Deep Point Cloud Compression

no code implementations CVPR 2022 Yun He, Xinlin Ren, Danhang Tang, yinda zhang, xiangyang xue, Yanwei Fu

To address this, we propose a novel deep point cloud compression method that preserves local density information.

MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks

1 code implementation14 Mar 2022 Yun He, Xue Feng, Cheng Cheng, Geng Ji, Yunsong Guo, James Caverlee

Specifically, in each training iteration and adaptively for each part of the network, the gradient of an auxiliary loss is carefully reduced or enlarged to have a closer magnitude to the gradient of the target loss, preventing auxiliary tasks from being so strong that dominate the target task or too weak to help the target task.

Popularity-Opportunity Bias in Collaborative Filtering

no code implementations WSDM 2021 Ziwei Zhu, Yun He, Xing Zhao, Yin Zhang, Jianling Wang, James Caverlee

This paper connects equal opportunity to popularity bias in implicit recommenders to introduce the problem of popularity-opportunity bias.

Collaborative Filtering

Consistency-Aware Recommendation for User-Generated ItemList Continuation

1 code implementation30 Dec 2019 Yun He, Yin Zhang, Weiwen Liu, James Caverlee

Complementary to methods that exploit specific content patterns (e. g., as in song-based playlists that rely on audio features), the proposed approach models the consistency of item lists based on human curation patterns, and so can be deployed across a wide range of varying item types (e. g., videos, images, books).

A Hierarchical Self-Attentive Model for Recommending User-Generated Item Lists

1 code implementation30 Dec 2019 Yun He, Jianling Wang, Wei Niu, James Caverlee

User-generated item lists are a popular feature of many different platforms.

Motion Representation with Acceleration Images

no code implementations30 Aug 2016 Hirokatsu Kataoka, Yun He, Soma Shirakabe, Yutaka Satoh

Information of time differentiation is extremely important cue for a motion representation.

Optical Flow Estimation

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