Search Results for author: Ziqi Zhang

Found 43 papers, 15 papers with code

Towards Scalability and Extensibility of Query Reformulation Modeling in E-commerce Search

no code implementations17 Feb 2024 Ziqi Zhang, Yupin Huang, Quan Deng, Jinghui Xiao, Vivek Mittal, Jingyuan Deng

Notably, employing the proposed solution in search ranking resulted in 0. 14% and 0. 29% increase in overall revenue in Japanese and Hindi cases, respectively, and a 0. 08\% incremental gain in the English case compared to the legacy implementation; while in search Ads matching led to a 0. 36% increase in Ads revenue in the Japanese case.

Context-Former: Stitching via Latent Conditioned Sequence Modeling

no code implementations29 Jan 2024 Ziqi Zhang, Jingzehua Xu, Jinxin Liu, Zifeng Zhuang, Donglin Wang

On the other hand, Decision Transformer (DT) abstracts the decision-making as sequence modeling, showcasing competitive performance on offline RL benchmarks, however, recent studies demonstrate that DT lacks of stitching capability, thus exploit stitching capability for DT is vital to further improve its performance.

D4RL Imitation Learning +2

Set Prediction Guided by Semantic Concepts for Diverse Video Captioning

no code implementations25 Dec 2023 Yifan Lu, Ziqi Zhang, Chunfeng Yuan, Peng Li, Yan Wang, Bing Li, Weiming Hu

Each caption in the set is attached to a concept combination indicating the primary semantic content of the caption and facilitating element alignment in set prediction.

Video Captioning

Adaptive Proximal Policy Optimization with Upper Confidence Bound

no code implementations12 Dec 2023 Ziqi Zhang, Jingzehua Xu, Zifeng Zhuang, Jinxin Liu, Donglin Wang

Trust Region Policy Optimization (TRPO) attractively optimizes the policy while constraining the update of the new policy within a trust region, ensuring the stability and monotonic optimization.

No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML

1 code implementation11 Oct 2023 Ziqi Zhang, Chen Gong, Yifeng Cai, Yuanyuan Yuan, Bingyan Liu, Ding Li, Yao Guo, Xiangqun Chen

These solutions, referred to as TEE-Shielded DNN Partition (TSDP), partition a DNN model into two parts, offloading the privacy-insensitive part to the GPU while shielding the privacy-sensitive part within the TEE.

Inference Attack Membership Inference Attack

Sample Efficient Reward Augmentation in offline-to-online Reinforcement Learning

no code implementations7 Oct 2023 Ziqi Zhang, Xiao Xiong, Zifeng Zhuang, Jinxin Liu, Donglin Wang

Offline-to-online RL can make full use of pre-collected offline datasets to initialize policies, resulting in higher sample efficiency and better performance compared to only using online algorithms alone for policy training.

Offline RL reinforcement-learning +1

The Barriers to Online Clothing Websites for Visually Impaired People: An Interview and Observation Approach to Understanding Needs

no code implementations19 May 2023 Amnah Alluqmani, Morgan Harvey, Ziqi Zhang

Visually impaired (VI) people often face challenges when performing everyday tasks and identify shopping for clothes as one of the most challenging.

Mining Healthcare Procurement Data Using Text Mining and Natural Language Processing -- Reflection From An Industrial Project

no code implementations9 Jan 2023 Ziqi Zhang, Tomas Jasaitis, Richard Freeman, Rowida Alfrjani, Adam Funk

In this work, we describe an industry project that developed text mining and NLP solutions to mine millions of heterogeneous, multilingual procurement documents in the healthcare sector.

ViLEM: Visual-Language Error Modeling for Image-Text Retrieval

no code implementations CVPR 2023 Yuxin Chen, Zongyang Ma, Ziqi Zhang, Zhongang Qi, Chunfeng Yuan, Ying Shan, Bing Li, Weiming Hu, XiaoHu Qie, Jianping Wu

ViLEM then enforces the model to discriminate the correctness of each word in the plausible negative texts and further correct the wrong words via resorting to image information.

Contrastive Learning Retrieval +3

Decoupled Mixup for Generalized Visual Recognition

1 code implementation26 Oct 2022 Haozhe Liu, Wentian Zhang, Jinheng Xie, Haoqian Wu, Bing Li, Ziqi Zhang, Yuexiang Li, Yawen Huang, Bernard Ghanem, Yefeng Zheng

Since the observation is that noise-prone regions such as textural and clutter backgrounds are adverse to the generalization ability of CNN models during training, we enhance features from discriminative regions and suppress noise-prone ones when combining an image pair.

Can Offline Reinforcement Learning Help Natural Language Understanding?

no code implementations15 Sep 2022 Ziqi Zhang, Yile Wang, Yue Zhang, Donglin Wang

Experimental results show that our RL pre-trained models can give close performance compared with the models using the LM training objective, showing that there exist common useful features across these two modalities.

Language Modelling Natural Language Understanding +3

KSG: Knowledge and Skill Graph

no code implementations13 Sep 2022 Feng Zhao, Ziqi Zhang, Donglin Wang

This is the first study that we are aware of that looks into dynamic KSG for skill retrieval and learning.

Attribute Knowledge Graphs +2

Distillation to Enhance the Portability of Risk Models Across Institutions with Large Patient Claims Database

no code implementations6 Jul 2022 Steve Nyemba, Chao Yan, Ziqi Zhang, Amol Rajmane, Pablo Meyer, Prithwish Chakraborty, Bradley Malin

We further show that the transfer learning approach based on the BAN produces models that are better than those trained on just a single institution's data.

Readmission Prediction Transfer Learning

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.

Retrieval Video Captioning +1

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.

Attribute Image Manipulation +1

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 Word Embeddings

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: Toward Better One-Stage Object Detection With Prediction Decoupling

1 code implementation28 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 object-detection +1

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.

Retrieval 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.

Reinforcement Learning (RL)

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 Clustering +1

Open-sourced Dataset Protection via Backdoor Watermarking

2 code implementations12 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

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 #8 on Video Captioning on VATEX (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.

Generative Adversarial Network Human Parsing +1

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.

Benchmarking Term Extraction

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