Search Results for author: Xiaoyu Du

Found 14 papers, 7 papers with code

Counterfactual Matters: Intrinsic Probing For Dialogue State Tracking

no code implementations EANCS 2021 Yi Huang, Junlan Feng, Xiaoting Wu, Xiaoyu Du

Our findings are: the performance variance of generative DSTs is not only due to the model structure itself, but can be attributed to the distribution of cross-domain values.

Dialogue State Tracking Task-Oriented Dialogue Systems

Triplet Contrastive Learning for Unsupervised Vehicle Re-identification

1 code implementation23 Jan 2023 Fei Shen, Xiaoyu Du, Liyan Zhang, Jinhui Tang

For the inter-class instance, a hybrid contrastive loss (HCL) re-defines the sample correlations by approaching the positive cluster features and leaving the all negative instance features.

Contrastive Learning Vehicle Re-Identification

BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorization

no code implementations5 Dec 2022 Yixin Yang, Zhongzheng Peng, Xiaoyu Du, Zhulin Tao, Jinhui Tang, Jinshan Pan

To overcome this problem, we further develop a mixed expert block to extract semantic information for modeling the object boundaries of frames so that the semantic image prior can better guide the colorization process for better performance.

Colorization Semantic correspondence

Automated Artefact Relevancy Determination from Artefact Metadata and Associated Timeline Events

no code implementations2 Dec 2020 Xiaoyu Du, Quan Le, Mark Scanlon

This is due to an ever-growing number of cases requiring digital forensic investigation coupled with the growing volume of data to be processed per case.

Methodology for the Automated Metadata-Based Classification of Incriminating Digital Forensic Artefacts

no code implementations2 Jul 2019 Xiaoyu Du, Mark Scanlon

In this paper, a methodology for the automatic prioritisation of suspicious file artefacts (i. e., file artefacts that are pertinent to the investigation) is proposed to reduce the manual analysis effort required.

General Classification

Modeling Embedding Dimension Correlations via Convolutional Neural Collaborative Filtering

1 code implementation26 Jun 2019 Xiaoyu Du, Xiangnan He, Fajie Yuan, Jinhui Tang, Zhiguang Qin, Tat-Seng Chua

In this work, we emphasize on modeling the correlations among embedding dimensions in neural networks to pursue higher effectiveness for CF.

Collaborative Filtering Recommendation Systems

Fast Matrix Factorization with Non-Uniform Weights on Missing Data

1 code implementation11 Nov 2018 Xiangnan He, Jinhui Tang, Xiaoyu Du, Richang Hong, Tongwei Ren, Tat-Seng Chua

This poses an imbalanced learning problem, since the scale of missing entries is usually much larger than that of observed entries, but they cannot be ignored due to the valuable negative signal.

Adversarial Training Towards Robust Multimedia Recommender System

1 code implementation19 Sep 2018 Jinhui Tang, Xiaoyu Du, Xiangnan He, Fajie Yuan, Qi Tian, Tat-Seng Chua

To this end, we propose a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning.

Information Retrieval Multimedia

Adversarial Personalized Ranking for Recommendation

1 code implementation12 Aug 2018 Xiangnan He, Zhankui He, Xiaoyu Du, Tat-Seng Chua

Extensive experiments on three public real-world datasets demonstrate the effectiveness of APR --- by optimizing MF with APR, it outperforms BPR with a relative improvement of 11. 2% on average and achieves state-of-the-art performance for item recommendation.

Recommendation Systems

Outer Product-based Neural Collaborative Filtering

1 code implementation12 Aug 2018 Xiangnan He, Xiaoyu Du, Xiang Wang, Feng Tian, Jinhui Tang, Tat-Seng Chua

In this work, we contribute a new multi-layer neural network architecture named ONCF to perform collaborative filtering.

Collaborative Filtering

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