Search Results for author: Ziqi Zhang

Found 26 papers, 10 papers with code

CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation

no code implementations31 Mar 2022 Ziqi Zhang, Yuxin Chen, Zongyang Ma, Zhongang Qi, Chunfeng Yuan, Bing Li, Ying Shan, Weiming Hu

In this paper, we propose to CREATE, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration benchmark, to facilitate research and application in video titling and video retrieval in Chinese.

Video Captioning Video Retrieval

DistFL: Distribution-aware Federated Learning for Mobile Scenarios

1 code implementation22 Oct 2021 Bingyan Liu, Yifeng Cai, Ziqi Zhang, Yuanchun Li, Leye Wang, Ding Li, Yao Guo, Xiangqun Chen

Previous studies focus on the "symptoms" directly, as they try to improve the accuracy or detect possible attacks by adding extra steps to conventional FL models.

Federated Learning Privacy Preserving

Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix

no code implementations17 Oct 2021 Ziqi Zhang, Yuexiang Li, Hongxin Wei, Kai Ma, Tao Xu, Yefeng Zheng

The hard samples, which are beneficial for classifier learning, are often mistakenly treated as noises in such a setting since both the hard samples and ones with noisy labels lead to a relatively larger loss value than the easy cases.

Image Classification

Text-Driven Image Manipulation via Semantic-Aware Knowledge Transfer

no code implementations29 Sep 2021 Ziqi Zhang, Cheng Deng, Kun Wei, Xu Yang

And on this basis, a novel attribute transfer method, named semantic directional decomposition network (SDD-Net), is proposed to achieve semantic-level facial attribute transfer by latent semantic direction decomposition, improving the interpretability and editability of our method.

Image Manipulation Transfer Learning

SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of "Subjectivity" and "Identity Terms"

no code implementations6 Sep 2021 Zhixue Zhao, Ziqi Zhang, Frank Hopfgartner

Toxic comment classification models are often found biased toward identity terms which are terms characterizing a specific group of people such as "Muslim" and "black".

Toxic Comment Classification

An Exploratory Study on Utilising the Web of Linked Data for Product Data Mining

no code implementations3 Sep 2021 Ziqi Zhang, Xingyi Song

We process billions of structured data points in the form of RDF n-quads, to create multi-million words of product-related corpora that are later used in three different ways for creating of language resources: training word embedding models, continued pre-training of BERT-like language models, and training Machine Translation models that are used as a proxy to generate product-related keywords.

Machine Translation Natural Language Processing +1

ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection

1 code implementation11 Jun 2021 Yuanchun Li, Ziqi Zhang, Bingyan Liu, Ziyue Yang, Yunxin Liu

The knowledge of a deep learning model may be transferred to a student model, leading to intellectual property infringement or vulnerability propagation.

Model Compression Transfer Learning

PDNet: Towards Better One-stage Object Detection with Prediction Decoupling

no code implementations28 Apr 2021 Li Yang, Yan Xu, Shaoru Wang, Chunfeng Yuan, Ziqi Zhang, Bing Li, Weiming Hu

However, the most suitable positions for inferring different targets, i. e., the object category and boundaries, are generally different.

object-detection Object Detection

Open-book Video Captioning with Retrieve-Copy-Generate Network

no code implementations CVPR 2021 Ziqi Zhang, Zhongang Qi, Chunfeng Yuan, Ying Shan, Bing Li, Ying Deng, Weiming Hu

Due to the rapid emergence of short videos and the requirement for content understanding and creation, the video captioning task has received increasing attention in recent years.

Video Captioning

Depth Self-Optimized Learning Toward Data Science

1 code implementation2 Nov 2020 Ziqi Zhang

We propose a two-stage model called Depth Self-Optimized Learning (DSOL), which aims to realize ANN depth self-configuration, self-optimization as well as ANN training without manual intervention.


Backdoor Attack against Speaker Verification

1 code implementation22 Oct 2020 Tongqing Zhai, Yiming Li, Ziqi Zhang, Baoyuan Wu, Yong Jiang, Shu-Tao Xia

We also demonstrate that existing backdoor attacks cannot be directly adopted in attacking speaker verification.

Backdoor Attack Speaker Verification

Open-sourced Dataset Protection via Backdoor Watermarking

1 code implementation12 Oct 2020 Yiming Li, Ziqi Zhang, Jiawang Bai, Baoyuan Wu, Yong Jiang, Shu-Tao Xia

Based on the proposed backdoor-based watermarking, we use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model of the benign samples and their correspondingly watermarked samples ($i. e.$, images with trigger) on the target class.

Image Classification

Understanding and Diagnosing Vulnerability under Adversarial Attacks

no code implementations17 Jul 2020 Haizhong Zheng, Ziqi Zhang, Honglak Lee, Atul Prakash

Moreover, we design the first diagnostic method to quantify the vulnerability contributed by each layer, which can be used to identify vulnerable parts of model architectures.

Classification General Classification

Adversarial Attacks on Monocular Depth Estimation

no code implementations23 Mar 2020 Ziqi Zhang, Xinge Zhu, Yingwei Li, Xiangqun Chen, Yao Guo

In order to understand the impact of adversarial attacks on depth estimation, we first define a taxonomy of different attack scenarios for depth estimation, including non-targeted attacks, targeted attacks and universal attacks.

Autonomous Driving Monocular Depth Estimation +3

Generating Electronic Health Records with Multiple Data Types and Constraints

no code implementations17 Mar 2020 Chao Yan, Ziqi Zhang, Steve Nyemba, Bradley A. Malin

Sharing electronic health records (EHRs) on a large scale may lead to privacy intrusions.

Object Relational Graph with Teacher-Recommended Learning for Video Captioning

no code implementations CVPR 2020 Ziqi Zhang, Yaya Shi, Chunfeng Yuan, Bing Li, Peijin Wang, Weiming Hu, Zheng-Jun Zha

In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy.

 Ranked #1 on Video Captioning on MSR-VTT (using extra training data)

Language Modelling Video Captioning

Efficient Adversarial Training with Transferable Adversarial Examples

2 code implementations CVPR 2020 Haizhong Zheng, Ziqi Zhang, Juncheng Gu, Honglak Lee, Atul Prakash

Adversarial training is an effective defense method to protect classification models against adversarial attacks.

Fashion Editing with Adversarial Parsing Learning

no code implementations CVPR 2020 Haoye Dong, Xiaodan Liang, Yixuan Zhang, Xujie Zhang, Zhenyu Xie, Bowen Wu, Ziqi Zhang, Xiaohui Shen, Jian Yin

Interactive fashion image manipulation, which enables users to edit images with sketches and color strokes, is an interesting research problem with great application value.

Human Parsing Image Manipulation

Hate Speech Detection: A Solved Problem? The Challenging Case of Long Tail on Twitter

1 code implementation27 Feb 2018 Ziqi Zhang, Lei Luo

Our methods are evaluated on the largest collection of hate speech datasets based on Twitter, and are shown to be able to outperform the best performing method by up to 5 percentage points in macro-average F1, or 8 percentage points in the more challenging case of identifying hateful content.

Hate Speech Detection

SemRe-Rank: Improving Automatic Term Extraction By Incorporating Semantic Relatedness With Personalised PageRank

2 code implementations9 Nov 2017 Ziqi Zhang, Jie Gao, Fabio Ciravegna

Extensively evaluated with 13 state-of-the-art base ATE methods on four datasets of diverse nature, it is shown to have achieved widespread improvement over all base methods and across all datasets, with up to 15 percentage points when measured by the Precision in the top ranked K candidate terms (the average for a set of K's), or up to 28 percentage points in F1 measured at a K that equals to the expected real terms in the candidates (F1 in short).

Term Extraction Word Embeddings

JATE 2.0: Java Automatic Term Extraction with Apache Solr

1 code implementation LREC 2016 Ziqi Zhang, Jie Gao, Fabio Ciravegna

Automatic Term Extraction (ATE) or Recognition (ATR) is a fundamental processing step preceding many complex knowledge engineering tasks.

Term Extraction

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