Search Results for author: Qi Li

Found 80 papers, 20 papers with code

Truth Discovery in Sequence Labels from Crowds

1 code implementation9 Sep 2021 Nasim Sabetpour, Adithya Kulkarni, Sihong Xie, Qi Li

The proposed Aggregation method for Sequential Labels from Crowds ($AggSLC$) jointly considers the characteristics of sequential labeling tasks, workers' reliabilities, and advanced machine learning techniques.

Named Entity Recognition NER +1

From Contexts to Locality: Ultra-high Resolution Image Segmentation via Locality-aware Contextual Correlation

1 code implementation6 Sep 2021 Qi Li, Weixiang Yang, Wenxi Liu, Yuanlong Yu, Shengfeng He

Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications.

Semantic Segmentation

Towards Balanced Learning for Instance Recognition

no code implementations23 Aug 2021 Jiangmiao Pang, Kai Chen, Qi Li, Zhihai Xu, Huajun Feng, Jianping Shi, Wanli Ouyang, Dahua Lin

In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level.

A Hard Label Black-box Adversarial Attack Against Graph Neural Networks

no code implementations21 Aug 2021 Jiaming Mu, Binghui Wang, Qi Li, Kun Sun, Mingwei Xu, Zhuotao Liu

We also evaluate the effectiveness of our attack under two defenses: one is well-designed adversarial graph detector and the other is that the target GNN model itself is equipped with a defense to prevent adversarial graph generation.

Adversarial Attack Classification +3

QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining

no code implementations ACL 2021 Xinya Du, Luheng He, Qi Li, Dian Yu, Panupong Pasupat, Yuan Zhang

To address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with a span-based QA model.

Zero-shot Slot Filling

HDMapNet: An Online HD Map Construction and Evaluation Framework

no code implementations13 Jul 2021 Qi Li, Yue Wang, Yilun Wang, Hang Zhao

In this paper, we argue that online map learning, which dynamically constructs the HD maps based on local sensor observations, is a more scalable way to provide semantic and geometry priors to self-driving vehicles than traditional pre-annotated HD maps.

Autonomous Driving

Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network

no code implementations11 Jul 2021 Yuecong Xu, Jianfei Yang, Haozhi Cao, Qi Li, Kezhi Mao, Zhenghua Chen

For videos, such negative transfer could be triggered by both spatial and temporal features, which leads to a more challenging Partial Video Domain Adaptation (PVDA) problem.

Partial Domain Adaptation

Face Sketch Synthesis via Semantic-Driven Generative Adversarial Network

no code implementations29 Jun 2021 Xingqun Qi, Muyi Sun, Weining Wang, Xiaoxiao Dong, Qi Li, Caifeng Shan

To tackle these challenges, we propose a novel Semantic-Driven Generative Adversarial Network (SDGAN) which embeds global structure-level style injection and local class-level knowledge re-weighting.

Face Parsing Face Sketch Synthesis +1

Realtime Robust Malicious Traffic Detection via Frequency Domain Analysis

no code implementations28 Jun 2021 Chuanpu Fu, Qi Li, Meng Shen, Ke Xu

To this end, we propose Whisper, a realtime ML based malicious traffic detection system that achieves both high accuracy and high throughput by utilizing frequency domain features.

AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning

no code implementations27 Jun 2021 Guangmeng Zhou, Ke Xu, Qi Li, Yang Liu, Yi Zhao

In a highly heterogeneous environment, AdaptCL achieves a training speedup of 6. 2x with a slight loss of accuracy.

Class agnostic moving target detection by color and location prediction of moving area

no code implementations24 Jun 2021 Zhuang He, Qi Li, Huajun Feng, Zhihai Xu

Then, the color and location probability map of the moving area will be calculated through maximum a posteriori probability.

Optical Flow Estimation

CARTL: Cooperative Adversarially-Robust Transfer Learning

1 code implementation12 Jun 2021 Dian Chen, Hongxin Hu, Qian Wang, Yinli Li, Cong Wang, Chao Shen, Qi Li

In deep learning, a typical strategy for transfer learning is to freeze the early layers of a pre-trained model and fine-tune the rest of its layers on the target domain.

Transfer Learning

One Shot Face Swapping on Megapixels

1 code implementation CVPR 2021 Yuhao Zhu, Qi Li, Jian Wang, Chengzhong Xu, Zhenan Sun

Extensive experiments demonstrate the superiority of MegaFS and the first megapixel level face swapping database is released for research on DeepFake detection and face image editing in the public domain.

DeepFake Detection Face Swapping +1

SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models

no code implementations30 Apr 2021 Haoying Li, Yifan Yang, Meng Chang, Huajun Feng, Zhihai Xu, Qi Li, Yueting Chen

Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones, which is an ill-posed problem because one LR image corresponds to multiple HR images.

Image Manipulation Image Super-Resolution

Few-shot Intent Classification and Slot Filling with Retrieved Examples

no code implementations NAACL 2021 Dian Yu, Luheng He, Yuan Zhang, Xinya Du, Panupong Pasupat, Qi Li

Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain.

Classification Few-Shot Learning +4

Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud

1 code implementation30 Mar 2021 Mingtao Feng, Zhen Li, Qi Li, Liang Zhang, Xiangdong Zhang, Guangming Zhu, HUI ZHANG, Yaonan Wang, Ajmal Mian

There are three main challenges in 3D object grounding: to find the main focus in the complex and diverse description; to understand the point cloud scene; and to locate the target object.

COSINE: A Web Server for Clonal and Subclonal Structure Inference and Evolution in Cancer Genomics

no code implementations28 Mar 2021 Xiguo Yuan, Yuan Zhao, Yang Guo, Linmei Ge, Wei Liu, Shiyu Wen, Qi Li, Zhangbo Wan, Peina Zheng, Tao Guo, Zhida Li, Martin Peifer, Yupeng Cun

In the past decade, a variety of methods have been developed for subclonal reconstruction using bulk tumor sequencing data.

Optical properties of elongated conducting grains

no code implementations11 Mar 2021 X. M. Huang, Qi Li, Aigen Li, J. H. Chen, F. Z. Liu, C. Y. Xiao

Extremely elongated, conducting dust particles (also known as metallic "needles" or "whiskers") are seen in carbonaceous chondrites and in samples brought back from the Itokawa asteroid.

Astrophysics of Galaxies

Truncation-Free Matching System for Display Advertising at Alibaba

no code implementations18 Feb 2021 Jin Li, Jie Liu, Shangzhou Li, Yao Xu, Ran Cao, Qi Li, Biye Jiang, Guan Wang, Han Zhu, Kun Gai, Xiaoqiang Zhu

When receiving a user request, matching system (i) finds the crowds that the user belongs to; (ii) retrieves all ads that have targeted those crowds.

Data Poisoning Attacks and Defenses to Crowdsourcing Systems

no code implementations18 Feb 2021 Minghong Fang, Minghao Sun, Qi Li, Neil Zhenqiang Gong, Jin Tian, Jia Liu

Our empirical results show that the proposed defenses can substantially reduce the estimation errors of the data poisoning attacks.

Data Poisoning

Detecting Localized Adversarial Examples: A Generic Approach using Critical Region Analysis

no code implementations10 Feb 2021 Fengting Li, Xuankai Liu, Xiaoli Zhang, Qi Li, Kun Sun, Kang Li

Particularly, the localized adversarial examples only perturb a small and contiguous region of the target object, so that they are robust and effective in both digital and physical worlds.

Face Recognition Image Classification

Data Poisoning Attacks to Deep Learning Based Recommender Systems

no code implementations7 Jan 2021 Hai Huang, Jiaming Mu, Neil Zhenqiang Gong, Qi Li, Bin Liu, Mingwei Xu

Specifically, we formulate our attack as an optimization problem, such that the injected ratings would maximize the number of normal users to whom the target items are recommended.

Data Poisoning Recommendation Systems

Automatic Historical Feature Generation through Tree-based Method in Ads Prediction

no code implementations31 Dec 2020 Hongjian Wang, Qi Li, Lanbo Zhang, Yue Lu, Steven Yoo, Srinivas Vadrevu, Zhenhui Li

Historical features are important in ads click-through rate (CTR) prediction, because they account for past engagements between users and ads.

Click-Through Rate Prediction

Robust Attacks on Deep Learning Face Recognition in the Physical World

no code implementations27 Nov 2020 Meng Shen, Hao Yu, Liehuang Zhu, Ke Xu, Qi Li, Xiaojiang Du

Deep neural networks (DNNs) have been increasingly used in face recognition (FR) systems.

Face Recognition

Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators?

no code implementations19 Nov 2020 Yunfan Liu, Qi Li, Zhenan Sun, Tieniu Tan

Generative Adversarial Networks (GANs) with style-based generators (e. g. StyleGAN) successfully enable semantic control over image synthesis, and recent studies have also revealed that interpretable image translations could be obtained by modifying the latent code.

Image Generation

Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search

1 code implementation NeurIPS 2020 Houwen Peng, Hao Du, Hongyuan Yu, Qi Li, Jing Liao, Jianlong Fu

The experiments on ImageNet verify such path distillation method can improve the convergence ratio and performance of the hypernetwork, as well as boosting the training of subnetworks.

Neural Architecture Search Object Detection

Manifold learning-based feature extraction for structural defect reconstruction

no code implementations26 Oct 2020 Qi Li, Dianzi Liu, Zhenghua Qian

Data-driven quantitative defect reconstructions using ultrasonic guided waves has recently demonstrated great potential in the area of non-destructive testing.

A novel combination of theoretical analysis and data-driven method for reconstruction of structural defects

no code implementations14 Sep 2020 Qi Li, Yihui Da, Yinghong Zhang, Bin Wang, Dianzi Liu, Zhenghua Qian

To address this issue, a novel approach to quantitative reconstruction of defects using the integration of data-driven method with the guided wave scattering analysis has been proposed in this paper.

Computational Engineering, Finance, and Science J.2

Removing Backdoor-Based Watermarks in Neural Networks with Limited Data

no code implementations2 Aug 2020 Xuankai Liu, Fengting Li, Bihan Wen, Qi Li

In this paper, we benchmark the robustness of watermarking, and propose a novel backdoor-based watermark removal framework using limited data, dubbed WILD.

Data Augmentation

Low-light Image Restoration with Short- and Long-exposure Raw Pairs

no code implementations1 Jul 2020 Meng Chang, Huajun Feng, Zhihai Xu, Qi Li

Using our data generation method and the proposed LSFNet, we can recover the details and color of the original scene, and improve the low-light image quality effectively.

Image Restoration

Quasi-Dense Similarity Learning for Multiple Object Tracking

1 code implementation CVPR 2021 Jiangmiao Pang, Linlu Qiu, Xia Li, Haofeng Chen, Qi Li, Trevor Darrell, Fisher Yu

Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets.

Contrastive Learning Metric Learning +3

Improved supervised prediction of aging-related genes via weighted dynamic network analysis

no code implementations7 May 2020 Qi Li, Khalique Newaz, Tijana Milenković

Instead, we recently inferred a dynamic aging-specific subnetwork using a methodologically more advanced notion of network propagation (NP), which improved upon Induced dynamic aging-specific subnetwork in a different task, that of unsupervised analyses of the aging process.

Partially-Typed NER Datasets Integration: Connecting Practice to Theory

no code implementations1 May 2020 Shi Zhi, Liyuan Liu, Yu Zhang, Shiyin Wang, Qi Li, Chao Zhang, Jiawei Han

While typical named entity recognition (NER) models require the training set to be annotated with all target types, each available datasets may only cover a part of them.

Named Entity Recognition NER

Spatial-Adaptive Network for Single Image Denoising

2 code implementations ECCV 2020 Meng Chang, Qi Li, Huajun Feng, Zhihai Xu

An encoder-decoder structure with a context block is introduced to capture multiscale information.

Ranked #5 on Image Denoising on DND (using extra training data)

Image Denoising

Dual affine moment invariants

no code implementations19 Nov 2019 You Hao, Hanlin Mo, Qi Li, He Zhang, Hua Li

In this paper, we propose a general framework to derive moment invariants under DAT for objects in M-dimensional space with N channels, which can be called dual-affine moment invariants (DAMI).

Affine Transformation

A3GAN: An Attribute-aware Attentive Generative Adversarial Network for Face Aging

no code implementations15 Nov 2019 Yunfan Liu, Qi Li, Zhenan Sun, Tieniu Tan

Face aging, which aims at aesthetically rendering a given face to predict its future appearance, has received significant research attention in recent years.

Adversarial Example in Remote Sensing Image Recognition

no code implementations29 Oct 2019 Li Chen, Guowei Zhu, Qi Li, Haifeng Li

This added adversarial perturbation image is called an adversarial example, which poses a serious security problem for systems based on CNN model recognition results.

A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings

no code implementations10 Oct 2019 Qi Li, Long Mai, Michael A. Alcorn, Anh Nguyen

Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities.

Improving Relation Extraction with Knowledge-attention

no code implementations IJCNLP 2019 Pengfei Li, Kezhi Mao, Xuefeng Yang, Qi Li

While attention mechanisms have been proven to be effective in many NLP tasks, majority of them are data-driven.

Relation Extraction

Supervised prediction of aging-related genes from a context-specific protein interaction subnetwork

no code implementations21 Aug 2019 Qi Li, Tijana Milenković

In a systematic and comprehensive evaluation, we find that in many of the evaluation tests: (i) using an aging-specific subnetwork indeed yields more accurate aging-related gene predictions than using the entire network, and (ii) predictive methods from our framework that have not previously been used for supervised prediction of aging-related genes outperform existing prominent methods for the same purpose.

Causality Extraction based on Self-Attentive BiLSTM-CRF with Transferred Embeddings

1 code implementation16 Apr 2019 Zhaoning Li, Qi Li, Xiaotian Zou, Jiangtao Ren

Causality extraction from natural language texts is a challenging open problem in artificial intelligence.

Feature Engineering

Age Progression and Regression with Spatial Attention Modules

no code implementations6 Mar 2019 Qi Li, Yunfan Liu, Zhenan Sun

Age progression and regression refers to aesthetically render-ing a given face image to present effects of face aging and rejuvenation, respectively.

Network Service Dependencies in Commodity Internet-of-Things Devices

no code implementations25 Feb 2019 Poonam Yadav, Qi Li, Anthony Brown, Richard Mortier

We continue to see increasingly widespread deployment of IoT devices, with apparent intent to embed them in our built environment likely to accelerate if smart city and related programmes succeed.

Networking and Internet Architecture

Understanding the Importance of Single Directions via Representative Substitution

no code implementations20 Jan 2019 Li Chen, Hailun Ding, Qi Li, Zhuo Li, Jian Peng, Haifeng Li

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.

A Data-driven Adversarial Examples Recognition Framework via Adversarial Feature Genome

no code implementations25 Dec 2018 Li Chen, Hailun Ding, Qi Li, Jiawei Zhu, Jian Peng, Haifeng Li

Inspired by AFS, we propose a defense framework based on Adversarial Feature Genome (AFG), which can detect and correctly classify adversarial examples into original classes simultaneously.

General Classification Multi-Label Classification

Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects

1 code implementation CVPR 2019 Michael A. Alcorn, Qi Li, Zhitao Gong, Chengfei Wang, Long Mai, Wei-Shinn Ku, Anh Nguyen

Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects in ImageNet.

Understanding the Importance of Single Directions via Representative Substitution

no code implementations27 Nov 2018 Li Chen, Hailun Ding, Qi Li, Zhuo Li, Jian Peng, Haifeng Li

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.

A Regressive Convolution Neural network and Support Vector Regression Model for Electricity Consumption Forecasting

1 code implementation21 Oct 2018 Youshan Zhang, Qi Li

Electricity consumption forecasting has important implications for the mineral companies on guiding quarterly work, normal power system operation, and the management.

Electricity consumption forecasting method based on MPSO-BP neural network model

no code implementations21 Oct 2018 Youshan Zhang, Liangdong Guo, Qi Li, Junhui Li

This paper deals with the problem of the electricity consumption forecasting method.

Finding Similar Medical Questions from Question Answering Websites

no code implementations14 Oct 2018 Yaliang Li, Liuyi Yao, Nan Du, Jing Gao, Qi Li, Chuishi Meng, Chenwei Zhang, Wei Fan

Patients who have medical information demands tend to post questions about their health conditions on these crowdsourced Q&A websites and get answers from other users.

Question Answering

Attribute-aware Face Aging with Wavelet-based Generative Adversarial Networks

no code implementations CVPR 2019 Yunfan Liu, Qi Li, Zhenan Sun

Since it is difficult to collect face images of the same subject over a long range of age span, most existing face aging methods resort to unpaired datasets to learn age mappings.

Differential and integral invariants under Mobius transformation

no code implementations30 Aug 2018 He Zhang, Hanlin Mo, You Hao, Qi Li, Hua Li

According to the Liouville Theorem, an important part of the conformal transformation is the Mobius transformation, so we focus on Mobius transformation and propose two differential expressions that are invariable under 2-D and 3-D Mobius transformation respectively.

Joint Voxel and Coordinate Regression for Accurate 3D Facial Landmark Localization

1 code implementation28 Jan 2018 Hongwen Zhang, Qi Li, Zhenan Sun

Then, a stacked hourglass network is adopted to estimate the volumetric representation from coarse to fine, followed by a 3D convolution network that takes the estimated volume as input and regresses 3D coordinates of the face shape.

3D Facial Landmark Localization Depth Estimation +1

Global and Local Consistent Age Generative Adversarial Networks

no code implementations25 Jan 2018 Pei-Pei Li, Yibo Hu, Qi Li, Ran He, Zhenan Sun

To utilize both global and local facial information, we propose a Global and Local Consistent Age Generative Adversarial Network (GLCA-GAN).

Learning Deep Similarity Models with Focus Ranking for Fabric Image Retrieval

no code implementations29 Dec 2017 Daiguo Deng, Ruomei Wang, Hefeng Wu, Huayong He, Qi Li, Xiaonan Luo

Fabric image retrieval is beneficial to many applications including clothing searching, online shopping and cloth modeling.

Image Retrieval Representation Learning

Authorship attribution of source code by using back propagation neural network based on particle swarm optimization

1 code implementation PLOS ONE 2017 Xinyu Yang, Guoai Xu, Qi Li, Yanhui Guo, Miao Zhang

Then these metrics are input to neural network for supervised learning, the weights of which are output by PSO and BP hybrid algorithm.

Deep Supervised Discrete Hashing

no code implementations NeurIPS 2017 Qi Li, Zhenan Sun, Ran He, Tieniu Tan

Benefit from recent advances in deep learning, deep hashing methods have achieved promising results for image retrieval.

General Classification Image Retrieval

Combining Data-driven and Model-driven Methods for Robust Facial Landmark Detection

1 code implementation30 Nov 2016 Hongwen Zhang, Qi Li, Zhenan Sun, Yunfan Liu

This Estimation-Correction-Tuning process perfectly combines the advantages of the global robustness of data-driven method (FCN), outlier correction capability of model-driven method (PDM) and non-parametric optimization of RLMS.

Facial Landmark Detection

Distributed Parameter Map-Reduce

no code implementations3 Oct 2015 Qi Li

But the premise of inference is that the map procedure holds parameters for all features in the sample.

Comparison of the Impact of Word Segmentation on Name Tagging for Chinese and Japanese

no code implementations LREC 2014 Hai-Bo Li, Masato Hagiwara, Qi Li, Heng Ji

As long as (2) is ensured, the performance of word segmentation does not have appreciable impact on Chinese and Japanese name tagging.

Chinese Word Segmentation

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