Search Results for author: Xin Li

Found 204 papers, 78 papers with code

Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction

no code implementations ECCV 2020 Xin Xiong, Haipeng Xiong, Ke Xian, Chen Zhao, Zhiguo Cao, Xin Li

Depth completion is a widely studied problem of predicting a dense depth map from a sparse set of measurements and a single RGB image.

Depth Completion graph construction

DDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition

no code implementations ECCV 2020 Matthew Korban, Xin Li

We propose a Dynamic Directed Graph Convolutional Network (DDGCN) to model spatial and temporal features of human actions from their skeletal representations.

Action Recognition

Aspect-based Sentiment Analysis in Question Answering Forums

1 code implementation Findings (EMNLP) 2021 Wenxuan Zhang, Yang Deng, Xin Li, Lidong Bing, Wai Lam

This motivates us to investigate the task of ABSA on QA forums (ABSA-QA), aiming to jointly detect the discussed aspects and their sentiment polarities for a given QA pair.

Aspect-Based Sentiment Analysis Question Answering

A Saliency-Guided Street View Image Inpainting Framework for Efficient Last-Meters Wayfinding

no code implementations14 May 2022 Chuanbo Hu, Shan Jia, Fan Zhang, Xin Li

However, due to the large diversity of geographic context and acquisition conditions, the captured SVI always contains various distracting objects (e. g., pedestrians and vehicles), which will distract human visual attention from efficiently finding the destination in the last few meters.

Image Inpainting Object Detection +1

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

2 code implementations11 May 2022 Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang

The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.

Image Super-Resolution

SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment

no code implementations9 May 2022 Jianzhao Liu, Xin Li, Yanding Peng, Tao Yu, Zhibo Chen

In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space.

Image Compression Image Quality Assessment

Relational Representation Learning in Visually-Rich Documents

no code implementations5 May 2022 Xin Li, Yan Zheng, Yiqing Hu, Haoyu Cao, Yunfei Wu, Deqiang Jiang, Yinsong Liu, Bo Ren

To deal with the unpredictable definition of relations, we propose a novel contrastive learning task named Relational Consistency Modeling (RCM), which harnesses the fact that existing relations should be consistent in differently augmented positive views.

Contrastive Learning Key information extraction +1

Global Mapping of Gene/Protein Interactions in PubMed Abstracts: A Framework and an Experiment with P53 Interactions

no code implementations22 Apr 2022 Xin Li, Hsinchun Chen, Zan Huang, Hua Su, Jesse D. Martinez

In this paper, we propose a comprehensive framework for constructing and analyzing large-scale gene functional networks based on the gene/protein interactions extracted from biomedical literature repositories using text mining tools.

Gene Function Prediction with Gene Interaction Networks: A Context Graph Kernel Approach

no code implementations22 Apr 2022 Xin Li, Hsinchun Chen, Jiexun Li, Zhu Zhang

Predicting gene functions is a challenge for biologists in the post genomic era.

The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training

no code implementations18 Apr 2022 Hao liu, Xinghua Jiang, Xin Li, Antai Guo, Deqiang Jiang, Bo Ren

The self-supervised Masked Image Modeling (MIM) schema, following "mask-and-reconstruct" pipeline of recovering contents from masked image, has recently captured the increasing interest in the multimedia community, owing to the excellent ability of learning visual representation from unlabeled data.

DR-GAN: Distribution Regularization for Text-to-Image Generation

no code implementations17 Apr 2022 Hongchen Tan, Xiuping Liu, BaoCai Yin, Xin Li

This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning.

Text to image generation Text-to-Image Generation

Context-aware Visual Tracking with Joint Meta-updating

no code implementations4 Apr 2022 Qiuhong Shen, Xin Li, Fanyang Meng, Yongsheng Liang

These deep trackers usually do not perform online update or update single sub-branch of the tracking model, for which they cannot adapt to the appearance variation of objects.

Meta-Learning Visual Object Tracking +1

Unsupervised Learning of Accurate Siamese Tracking

1 code implementation4 Apr 2022 Qiuhong Shen, Lei Qiao, Jinyang Guo, Peixia Li, Xin Li, Bo Li, Weitao Feng, Weihao Gan, Wei Wu, Wanli Ouyang

As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward.

Visual Object Tracking

DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

1 code implementation19 Mar 2022 Thanh-Dat Truong, Quoc-Huy Bui, Chi Nhan Duong, Han-Seok Seo, Son Lam Phung, Xin Li, Khoa Luu

Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video action recognition with competitive results.

Action Classification Action Recognition +2

Aggregate effects of advertising decisions: a complex systems look at search engine advertising via an experimental study

no code implementations4 Mar 2022 Yanwu Yang, Xin Li, Bernard J. Jansen, Daniel Zeng

Originality: This is one of the first research works to explore collective group decisions and resulting phenomena in the complex context of search engine advertising via developing and validating a simulation framework that supports assessments of various advertising strategies and estimations of the impact of mechanisms on the search market.

Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence

no code implementations2 Mar 2022 Zhihong Pan, Baopu Li, Dongliang He, Mingde Yao, Wenhao Wu, Tianwei Lin, Xin Li, Errui Ding

Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel.

Image Super-Resolution

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

no code implementations2 Mar 2022 Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, Wai Lam

More specifically, we provide a new taxonomy for ABSA which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks.

Aspect-Based Sentiment Analysis

Model Attribution of Face-swap Deepfake Videos

1 code implementation25 Feb 2022 Shan Jia, Xin Li, Siwei Lyu

Then we take Deepfakes model attribution as a multiclass classification task and propose a spatial and temporal attention based method to explore the differences among Deepfakes in the new dataset.

Face Swapping

Low-Rank Phase Retrieval with Structured Tensor Models

no code implementations15 Feb 2022 Soo Min Kwon, Xin Li, Anand D. Sarwate

We study the low-rank phase retrieval problem, where the objective is to recover a sequence of signals (typically images) given the magnitude of linear measurements of those signals.

Learning Optical Flow with Adaptive Graph Reasoning

1 code implementation8 Feb 2022 Ao Luo, Fan Yang, Kunming Luo, Xin Li, Haoqiang Fan, Shuaicheng Liu

Our key idea is to decouple the context reasoning from the matching procedure, and exploit scene information to effectively assist motion estimation by learning to reason over the adaptive graph.

Motion Estimation Optical Flow Estimation +1

Multi-modal Sensor Fusion for Auto Driving Perception: A Survey

no code implementations6 Feb 2022 Keli Huang, Botian Shi, Xiang Li, Xin Li, Siyuan Huang, Yikang Li

Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers.

Autonomous Driving Object Detection +1

A multi-domain virtual network embedding algorithm with delay prediction

no code implementations3 Feb 2022 Peiying Zhang, Xue Pang, Yongjing Ni, Haipeng Yao, Xin Li

Virtual network embedding (VNE) is an crucial part of network virtualization (NV), which aims to map the virtual networks (VNs) to a shared substrate network (SN).

Network Embedding

Machine learning prediction for mean motion resonance behaviour -- The planar case

no code implementations18 Jan 2022 Xin Li, Jian Li, Zhihong Jeff Xia, Nikolaos Georgakarakos

Most recently, machine learning has been used to study the dynamics of integrable Hamiltonian systems and the chaotic 3-body problem.

Numerical Integration

A Survey on Applications of Digital Human Avatars toward Virtual Co-presence

no code implementations11 Jan 2022 Matthew Korban, Xin Li

This paper investigates different approaches to build and use digital human avatars toward interactive Virtual Co-presence (VCP) environments.

SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning

1 code implementation31 Dec 2021 Hongyu Zang, Xin Li, Mingzhong Wang

This work explores how to learn robust and generalizable state representation from image-based observations with deep reinforcement learning methods.


Robust Depth Completion with Uncertainty-Driven Loss Functions

no code implementations15 Dec 2021 Yufan Zhu, Weisheng Dong, Leida Li, Jinjian Wu, Xin Li, Guangming Shi

In this work, we introduce uncertainty-driven loss functions to improve the robustness of depth completion and handle the uncertainty in depth completion.

Depth Completion

An Informative Tracking Benchmark

1 code implementation13 Dec 2021 Xin Li, Qiao Liu, Wenjie Pei, Qiuhong Shen, YaoWei Wang, Huchuan Lu, Ming-Hsuan Yang

Along with the rapid progress of visual tracking, existing benchmarks become less informative due to redundancy of samples and weak discrimination between current trackers, making evaluations on all datasets extremely time-consuming.

Visual Tracking

Uncertainty-Driven Loss for Single Image Super-Resolution

no code implementations NeurIPS 2021 Qian Ning, Weisheng Dong, Xin Li, Jinjian Wu, Guangming Shi

Specifically, we introduce variance estimation characterizing the uncertainty on a pixel-by-pixel basis into SISR solutions so the targeted pixels in a high-resolution image (mean) and their corresponding uncertainty (variance) can be learned simultaneously.

Image Super-Resolution

Interactive Model with Structural Loss for Language-based Abductive Reasoning

no code implementations1 Dec 2021 Linhao Li, Ming Xu, Yongfeng Dong, Xin Li, Ao Wang, QinGhua Hu

Therefore, we propose to group instead of ranking the hypotheses and design a structural loss called ``joint softmax focal loss'' in this paper.

Language Modelling Natural Language Inference

Document Layout Analysis with Aesthetic-Guided Image Augmentation

no code implementations27 Nov 2021 Tianlong Ma, Xingjiao Wu, Xin Li, Xiangcheng Du, Zhao Zhou, Liang Xue, Cheng Jin

To measure the proposed image layer modeling method, we propose a manually-labeled non-Manhattan layout fine-grained segmentation dataset named FPD.

Document Layout Analysis Image Augmentation

Neural Collaborative Graph Machines for Table Structure Recognition

no code implementations26 Nov 2021 Hao liu, Xin Li, Bing Liu, Deqiang Jiang, Yinsong Liu, Bo Ren

We also show that the proposed NCGM can modulate collaborative pattern of different modalities conditioned on the context of intra-modality cues, which is vital for diversified table cases.

Simple Contrastive Representation Adversarial Learning for NLP Tasks

no code implementations26 Nov 2021 Deshui Miao, JiaQi Zhang, WenBo Xie, Jian Song, Xin Li, Lijuan Jia, Ning Guo

In this paper, adversarial training is performed to generate challenging and harder learning adversarial examples over the embedding space of NLP as learning pairs.

Contrastive Learning Natural Language Understanding +2

Confounder Identification-free Causal Visual Feature Learning

no code implementations26 Nov 2021 Xin Li, Zhizheng Zhang, Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Xin Jin, Zhibo Chen

In this paper, we propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders.

Domain Generalization Meta-Learning

NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition

1 code implementation25 Nov 2021 Hao liu, Xinghua Jiang, Xin Li, Zhimin Bao, Deqiang Jiang, Bo Ren

For the sake of trade-off between efficiency and performance, a group of works merely perform SA operation within local patches, whereas the global contextual information is abandoned, which would be indispensable for visual recognition tasks.

Object Detection Semantic Segmentation

Few-Shot Real Image Super-resolution via Distortion-Relation Guided Transfer Learning

no code implementations25 Nov 2021 Xin Li, Xin Jin, Jun Fu, Xiaoyuan Yu, Bei Tong, Zhibo Chen

DRTL assigns a knowledge graph to capture the distortion relation between auxiliary tasks (i. e., synthetic distortions) and target tasks (i. e., real distortions with few images), and then adopt a gradient weighting strategy to guide the knowledge transfer from auxiliary task to target task.

Image Restoration Image Super-Resolution +2

Knowledge Based Multilingual Language Model

no code implementations22 Nov 2021 Linlin Liu, Xin Li, Ruidan He, Lidong Bing, Shafiq Joty, Luo Si

Knowledge enriched language representation learning has shown promising performance across various knowledge-intensive NLP tasks.

Knowledge Graphs Language Modelling +4

Internationalizing AI: Evolution and Impact of Distance Factors

no code implementations10 Nov 2021 Xuli Tang, Xin Li, Feicheng Ma

A framework including 13 indicators to quantify the distance factors between countries from 5 perspectives (i. e., geographic distance, economic distance, cultural distance, academic distance, and industrial distance) is proposed.

Deep Models with Fusion Strategies for MVP Point Cloud Registration

1 code implementation18 Oct 2021 Lifa Zhu, Changwei Lin, Dongrui Liu, Xin Li, Francisco Gómez-Fernández

The main goal of point cloud registration in Multi-View Partial (MVP) Challenge 2021 is to estimate a rigid transformation to align a point cloud pair.

Point Cloud Registration

Probabilistic prediction of the heave motions of a semi-submersible by a deep learning problem model

1 code implementation9 Oct 2021 Xiaoxian Guo, Xiantao Zhang, Xinliang Tian, Wenyue Lu, Xin Li

In this study, we extend a deep learning (DL) model, which could predict the heave and surge motions of a floating semi-submersible 20 to 50 seconds ahead with good accuracy, to quantify its uncertainty of the predictive time series with the help of the dropout technique.

Motion Compensation motion prediction +1

Vector-quantized Image Modeling with Improved VQGAN

1 code implementation ICLR 2022 Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alexander Ku, Yuanzhong Xu, Jason Baldridge, Yonghui Wu

Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively.

Image Generation Representation Learning +1

Aspect Sentiment Quad Prediction as Paraphrase Generation

1 code implementation EMNLP 2021 Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, Wai Lam

Aspect-based sentiment analysis (ABSA) has been extensively studied in recent years, which typically involves four fundamental sentiment elements, including the aspect category, aspect term, opinion term, and sentiment polarity.

Aspect-Based Sentiment Analysis Paraphrase Generation

Multilingual AMR Parsing with Noisy Knowledge Distillation

1 code implementation Findings (EMNLP) 2021 Deng Cai, Xin Li, Jackie Chun-Sing Ho, Lidong Bing, Wai Lam

We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher.

AMR Parsing Knowledge Distillation

Characterizing interdisciplinarity in drug research: a translational science perspective

no code implementations4 Sep 2021 Xin Li, Xuli Tang

Despite the significant advances in life science, it still takes decades to translate a basic drug discovery into a cure for human disease.

Drug Discovery

Detection of Illicit Drug Trafficking Events on Instagram: A Deep Multimodal Multilabel Learning Approach

no code implementations19 Aug 2021 Chuanbo Hu, Minglei Yin, Bin Liu, Xin Li, Yanfang Ye

Accordingly, accurate detection of illicit drug trafficking events (IDTEs) from social media has become even more challenging.

Identifying Illicit Drug Dealers on Instagram with Large-scale Multimodal Data Fusion

no code implementations18 Aug 2021 Chuanbo Hu, Minglei Yin, Bin Liu, Xin Li, Yanfang Ye

Unlike existing methods that focus on posting-based detection, we propose to tackle the problem of illicit drug dealer identification by constructing a large-scale multimodal dataset named Identifying Drug Dealers on Instagram (IDDIG).

Community Detection

VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows

2 code implementations11 Aug 2021 Xiao Wang, Jianing Li, Lin Zhu, Zhipeng Zhang, Zhe Chen, Xin Li, YaoWei Wang, Yonghong Tian, Feng Wu

Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency.

Frame Object Tracking

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction

2 code implementations ICCV 2021 Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Ruifeng Deng, Xin Li, Errui Ding, Hao Wang

Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks.

Object Detection Style Transfer

Saliency-Associated Object Tracking

1 code implementation ICCV 2021 Zikun Zhou, Wenjie Pei, Xin Li, Hongpeng Wang, Feng Zheng, Zhenyu He

A potential limitation of such trackers is that not all patches are equally informative for tracking.

Object Tracking

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

2 code implementations ICCV 2021 Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Meiling Wang, Xin Li, Zhengxing Sun, Qian Li, Errui Ding

Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics.

Style Transfer Video Style Transfer

Metasurface-Enabled On-Chip Multiplexed Diffractive Neural Networks in the Visible

no code implementations13 Jul 2021 Xuhao Luo, Yueqiang Hu, Xin Li, Xiangnian Ou, Jiajie Lai, Na Liu, Huigao Duan

Replacing electrons with photons is a compelling route towards light-speed, highly parallel, and low-power artificial intelligence computing.

Autonomous Driving

Self-Supervised Tracking via Target-Aware Data Synthesis

no code implementations21 Jun 2021 Xin Li, Wenjie Pei, Zikun Zhou, Zhenyu He, Huchuan Lu, Ming-Hsuan Yang

While deep-learning based tracking methods have achieved substantial progress, they entail large-scale and high-quality annotated data for sufficient training.

Representation Learning Self-Supervised Learning +1

Probabilistic Model Distillation for Semantic Correspondence

1 code implementation CVPR 2021 Xin Li, Deng-Ping Fan, Fan Yang, Ao Luo, Hong Cheng, Zicheng Liu

We address this problem with the use of a novel Probabilistic Model Distillation (PMD) approach which transfers knowledge learned by a probabilistic teacher model on synthetic data to a static student model with the use of unlabeled real image pairs.

Representation Learning Semantic correspondence

Task-driven Semantic Coding via Reinforcement Learning

no code implementations7 Jun 2021 Xin Li, Jun Shi, Zhibo Chen

However, the traditional hybrid coding framework cannot be optimized in an end-to-end manner, which makes task-driven semantic fidelity metric unable to be automatically integrated into the rate-distortion optimization process.

Face Detection License Plate Detection +3

DeepReduce: A Sparse-tensor Communication Framework for Federated Deep Learning

1 code implementation NeurIPS 2021 Hang Xu, Kelly Kostopoulou, Aritra Dutta, Xin Li, Alexandros Ntoulas, Panos Kalnis

DeepReduce is orthogonal to existing gradient sparsifiers and can be applied in conjunction with them, transparently to the end-user, to significantly lower the communication overhead.

Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness

1 code implementation28 Apr 2021 Manyu Zhu, Dongliang He, Xin Li, Chao Li, Fu Li, Xiao Liu, Errui Ding, Zhaoxiang Zhang

Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial.

Image Inpainting

Learning Semantic Person Image Generation by Region-Adaptive Normalization

1 code implementation CVPR 2021 Zhengyao Lv, Xiaoming Li, Xin Li, Fu Li, Tianwei Lin, Dongliang He, WangMeng Zuo

In the first stage, we predict the target semantic parsing maps to eliminate the difficulties of pose transfer and further benefit the latter translation of per-region appearance style.

Pose Transfer Semantic Parsing +1

Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer

2 code implementations CVPR 2021 Tianwei Lin, Zhuoqi Ma, Fu Li, Dongliang He, Xin Li, Errui Ding, Nannan Wang, Jie Li, Xinbo Gao

Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).

Style Transfer

Searching Efficient Model-guided Deep Network for Image Denoising

no code implementations6 Apr 2021 Qian Ning, Weisheng Dong, Xin Li, Jinjian Wu, Leida Li, Guangming Shi

Similar to the success of NAS in high-level vision tasks, it is possible to find a memory and computationally efficient solution via NAS with highly competent denoising performance.

Image Denoising Neural Architecture Search

Mutual Graph Learning for Camouflaged Object Detection

1 code implementation CVPR 2021 Qiang Zhai, Xin Li, Fan Yang, Chenglizhao Chen, Hong Cheng, Deng-Ping Fan

Automatically detecting/segmenting object(s) that blend in with their surroundings is difficult for current models.

Graph Learning Object Detection

A Detector-oblivious Multi-arm Network for Keypoint Matching

1 code implementation2 Apr 2021 Xuelun Shen, Cheng Wang, Xin Li, Qian Hu, Jingyi Zhang

This paper presents a matching network to establish point correspondence between images.

Local Patch AutoAugment with Multi-Agent Collaboration

2 code implementations20 Mar 2021 Shiqi Lin, Tao Yu, Ruoyu Feng, Xin Li, Xin Jin, Zhibo Chen

We formulate it as a multi-agent reinforcement learning (MARL) problem, where each agent learns an augmentation policy for each patch based on its content together with the semantics of the whole image.

Data Augmentation Fine-Grained Image Recognition +2

DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning

1 code implementation NeurIPS 2021 Kelly Kostopoulou, Hang Xu, Aritra Dutta, Xin Li, Alexandros Ntoulas, Panos Kalnis

This paper introduces DeepReduce, a versatile framework for the compressed communication of sparse tensors, tailored for distributed deep learning.

Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models

1 code implementation3 Feb 2021 Shang Wang, Peiming Yang, Yuxuan Zheng, Xin Li, Gennady Pekhimenko

Driven by the tremendous effort in researching novel deep learning (DL) algorithms, the training cost of developing new models increases staggeringly in recent years.

TEAC: Intergrating Trust Region and Max Entropy Actor Critic for Continuous Control

1 code implementation1 Jan 2021 Hongyu Zang, Xin Li, Li Zhang, Peiyao Zhao, Mingzhong Wang

Trust region methods and maximum entropy methods are two state-of-the-art branches used in reinforcement learning (RL) for the benefits of stability and exploration in continuous environments, respectively.

Continuous Control reinforcement-learning

Learning Inter- and Intraframe Representations for Non-Lambertian Photometric Stereo

no code implementations26 Dec 2020 Yanlong Cao, Binjie Ding, Zewei He, Jiangxin Yang, Jingxi Chen, Yanpeng Cao, Xin Li

Photometric stereo provides an important method for high-fidelity 3D reconstruction based on multiple intensity images captured under different illumination directions.

3D Reconstruction

Understanding Team Collaboration in Artificial Intelligence from the perspective of Geographic Distance

no code implementations25 Dec 2020 Xuli Tang, Xin Li, Ying Ding, Feicheng Ma

This paper analyzes team collaboration in the field of Artificial Intelligence (AI) from the perspective of geographic distance.

Learned Block-based Hybrid Image Compression

no code implementations17 Dec 2020 Yaojun Wu, Xin Li, Zhizheng Zhang, Xin Jin, Zhibo Chen

Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications.

Image Compression MS-SSIM +1

Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints

1 code implementation14 Dec 2020 Xin Li, Xiangrui Li, Deng Pan, Dongxiao Zhu

This inspires us to propose a new Probabilistically Compact (PC) loss with logit constraints which can be used as a drop-in replacement for cross-entropy (CE) loss to improve CNN's adversarial robustness.

Adversarial Robustness

Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution

no code implementations11 Dec 2020 Xin Li, Xin Jin, Tao Yu, Yingxue Pang, Simeng Sun, Zhizheng Zhang, Zhibo Chen

Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i. e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations.

Image Super-Resolution

A New Action Recognition Framework for Video Highlights Summarization in Sporting Events

no code implementations1 Dec 2020 Cheng Yan, Xin Li, Guoqiang Li

To date, machine learning for human action recognition in video has been widely implemented in sports activities.

Action Recognition Video Summarization

Magnetoelectric coupling and decoupling in multiferroic hexagonal YbFeO3 thin films

no code implementations13 Nov 2020 Yu Yun, Xin Li, Arashdeep Singh Thind, Yuewei Yin, Hao liu, Qiang Li, Wenbin Wang, Alpha T. N Diaye, Corbyn Mellinger, Xuanyuan Jiang, Rohan Mishra, Xiaoshan Xu

The coupling between ferroelectric and magnetic orders in multiferroic materials and the nature of magnetoelectric (ME) effects are enduring experimental challenges.

Materials Science Other Condensed Matter

Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model

1 code implementation4 Nov 2020 Zheheng Jiang, Feixiang Zhou, Aite Zhao, Xin Li, Ling Li, DaCheng Tao, Xuelong Li, Huiyu Zhou

To address this problem, we here propose a novel multiview latent-attention and dynamic discriminative model that jointly learns view-specific and view-shared sub-structures, where the former captures unique dynamics of each view whilst the latter encodes the interaction between the views.

Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond

no code implementations23 Oct 2020 Xin Li, Lidong Bing, Wenxuan Zhang, Zheng Li, Wai Lam

Cross-lingual adaptation with multilingual pre-trained language models (mPTLMs) mainly consists of two lines of works: zero-shot approach and translation-based approach, which have been studied extensively on the sequence-level tasks.

Cross-Lingual Transfer Translation

Limitations of Autoregressive Models and Their Alternatives

no code implementations NAACL 2021 Chu-Cheng Lin, Aaron Jaech, Xin Li, Matthew R. Gormley, Jason Eisner

Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol.

Language Modelling

Deformable Kernel Convolutional Network for Video Extreme Super-Resolution

no code implementations1 Oct 2020 Xuan Xu, Xin Xiong, Jinge Wang, Xin Li

Thanks to newly designed Deformable Kernel Convolution Alignment (DKC_Align) and Deformable Kernel Spatial Attention (DKSA) modules, DKSAN can better exploit both spatial and temporal redundancies to facilitate the information propagation across different layers.

Video Super-Resolution

FAN: Frequency Aggregation Network for Real Image Super-resolution

no code implementations30 Sep 2020 Yingxue Pang, Xin Li, Xin Jin, Yaojun Wu, Jianzhao Liu, Sen Liu, Zhibo Chen

Specifically, we extract different frequencies of the LR image and pass them to a channel attention-grouped residual dense network (CA-GRDB) individually to output corresponding feature maps.

Image Super-Resolution SSIM

Enhancing Dialogue Generation via Multi-Level Contrastive Learning

no code implementations19 Sep 2020 Xin Li, Piji Li, Yan Wang, Xiaojiang Liu, Wai Lam

Most of the existing works for dialogue generation are data-driven models trained directly on corpora crawled from websites.

Contrastive Learning Dialogue Generation

Efficiency in Real-time Webcam Gaze Tracking

no code implementations2 Sep 2020 Amogh Gudi, Xin Li, Jan van Gemert

To do so, we evaluate the computational speed/accuracy trade-off for the CNN and the calibration effort/accuracy trade-off for screen calibration.

Detection of Genuine and Posed Facial Expressions of Emotion: A Review

no code implementations26 Aug 2020 Shan Jia, Shuo Wang, Chuanbo Hu, Paula Webster, Xin Li

Facial expressions of emotion play an important role in human social interactions.

Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation

no code implementations21 Aug 2020 Xu He, Bo An, Yanghua Li, Haikai Chen, Qingyu Guo, Xin Li, Zhirong Wang

First, since we concern the reward of a set of recommended items, we model the online recommendation as a contextual combinatorial bandit problem and define the reward of a recommended set.

LIRA: Lifelong Image Restoration from Unknown Blended Distortions

no code implementations ECCV 2020 Jianzhao Liu, Jianxin Lin, Xin Li, Wei Zhou, Sen Liu, Zhibo Chen

Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task.

Image Restoration SSIM

MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification

1 code implementation10 Aug 2020 Hongchen Tan, Xiuping Liu, BaoCai Yin, Xin Li

This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images.

Person Re-Identification

Cascade Graph Neural Networks for RGB-D Salient Object Detection

1 code implementation ECCV 2020 Ao Luo, Xin Li, Fan Yang, Zhicheng Jiao, Hong Cheng, Siwei Lyu

Current works either simply distill prior knowledge from the corresponding depth map for handling the RGB-image or blindly fuse color and geometric information to generate the coarse depth-aware representations, hindering the performance of RGB-D saliency detectors. In this work, we introduceCascade Graph Neural Networks(Cas-Gnn), a unified framework which is capable of comprehensively distilling and reasoning the mutual benefits between these two data sources through a set of cascade graphs, to learn powerful representations for RGB-D salient object detection.

RGB-D Salient Object Detection RGB Salient Object Detection +1

LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark

1 code implementation3 Aug 2020 Qiao Liu, Xin Li, Zhenyu He, Chenglong Li, Jun Li, Zikun Zhou, Di Yuan, Jing Li, Kai Yang, Nana Fan, Feng Zheng

We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance.

Frame Thermal Infrared Object Tracking

Multi-node Bert-pretraining: Cost-efficient Approach

no code implementations1 Aug 2020 Jiahuang Lin, Xin Li, Gennady Pekhimenko

As a result, to train these models within a reasonable time, machine learning (ML) programmers often require advanced hardware setups such as the premium GPU-enabled NVIDIA DGX workstations or specialized accelerators such as Google's TPU Pods.

Predicting heave and surge motions of a semi-submersible with neural networks

no code implementations31 Jul 2020 Xiaoxian Guo, Xiantao Zhang, Xinliang Tian, Xin Li, Wenyue Lu

With the help of measured waves, the prediction extended 46. 5 s into future with an average accuracy close to 90%.

Motion Compensation motion prediction

Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

no code implementations12 Jul 2020 Deng Pan, Xiangrui Li, Xin Li, Dongxiao Zhu

Latent factor collaborative filtering (CF) has been a widely used technique for recommender system by learning the semantic representations of users and items.

Collaborative Filtering Recommendation Systems

Defending against adversarial attacks on medical imaging AI system, classification or detection?

1 code implementation24 Jun 2020 Xin Li, Deng Pan, Dongxiao Zhu

Medical imaging AI systems such as disease classification and segmentation are increasingly inspired and transformed from computer vision based AI systems.

Adversarial Defense General Classification

Robust Trajectory Forecasting for Multiple Intelligent Agents in Dynamic Scene

no code implementations27 May 2020 Yanliang Zhu, Dongchun Ren, Mingyu Fan, Deheng Qian, Xin Li, Huaxia Xia

Trajectory forecasting, or trajectory prediction, of multiple interacting agents in dynamic scenes, is an important problem for many applications, such as robotic systems and autonomous driving.

Autonomous Driving Trajectory Forecasting

Multi-scale Grouped Dense Network for VVC Intra Coding

no code implementations16 May 2020 Xin Li, Simeng Sun, Zhizheng Zhang, Zhibo Chen

Versatile Video Coding (H. 266/VVC) standard achieves better image quality when keeping the same bits than any other conventional image codec, such as BPG, JPEG, and etc.

3D Face Anti-spoofing with Factorized Bilinear Coding

no code implementations12 May 2020 Shan Jia, Xin Li, Chuanbo Hu, Guodong Guo, Zhengquan Xu

We have witnessed rapid advances in both face presentation attack models and presentation attack detection (PAD) in recent years.

Face Anti-Spoofing Face Presentation Attack Detection +1

Training Recurrent Neural Networks Online by Learning Explicit State Variables

no code implementations ICLR 2020 Somjit Nath, Vincent Liu, Alan Chan, Xin Li, Adam White, Martha White

Recurrent neural networks (RNNs) allow an agent to construct a state-representation from a stream of experience, which is essential in partially observable problems.

Context-aware Helpfulness Prediction for Online Product Reviews

no code implementations27 Apr 2020 Iyiola E. Olatunji, Xin Li, Wai Lam

In this paper, we propose a neural deep learning model that predicts the helpfulness score of a review.

A Chinese Corpus for Fine-grained Entity Typing

1 code implementation LREC 2020 Chin Lee, Hongliang Dai, Yangqiu Song, Xin Li

In this paper, we introduce a corpus for Chinese fine-grained entity typing that contains 4, 800 mentions manually labeled through crowdsourcing.

Cross-Lingual Transfer Entity Typing +1

Leveraging Planar Regularities for Point Line Visual-Inertial Odometry

no code implementations16 Apr 2020 Xin Li, Yijia He, Jinlong Lin, Xiao Liu

To improve the accuracy of 3D mesh generation and localization, we propose a tightly-coupled monocular VIO system, PLP-VIO, which exploits point features and line features as well as plane regularities.

Towards Evaluating the Robustness of Chinese BERT Classifiers

no code implementations7 Apr 2020 Boxin Wang, Boyuan Pan, Xin Li, Bo Li

Recent advances in large-scale language representation models such as BERT have improved the state-of-the-art performances in many NLP tasks.

COVID-MobileXpert: On-Device COVID-19 Patient Triage and Follow-up using Chest X-rays

1 code implementation6 Apr 2020 Xin Li, Chengyin Li, Dongxiao Zhu

We design and implement a novel three-player knowledge transfer and distillation (KTD) framework including a pre-trained attending physician (AP) network that extracts CXR imaging features from a large scale of lung disease CXR images, a fine-tuned resident fellow (RF) network that learns the essential CXR imaging features to discriminate COVID-19 from pneumonia and/or normal cases with a small amount of COVID-19 cases, and a trained lightweight medical student (MS) network to perform on-device COVID-19 patient triage and follow-up.

Computed Tomography (CT) Trajectory Prediction +1

Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

3 code implementations22 Mar 2020 Yao Qiang, Xin Li, Dongxiao Zhu

Existing aspect based sentiment analysis (ABSA) approaches leverage various neural network models to extract the aspect sentiments via learning aspect-specific feature representations.

Aspect-Based Sentiment Analysis TAG

Impact of Temperature and Relative Humidity on the Transmission of COVID-19: A Modeling Study in China and the United States

no code implementations9 Mar 2020 Jingyuan Wang, Ke Tang, Kai Feng, Xin Li, Weifeng Lv, Kun Chen, Fei Wang

Primary outcome measures: Regression analysis of the impact of temperature and relative humidity on the effective reproductive number (R value).

On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

1 code implementation4 Mar 2020 Xiangrui Li, Xin Li, Deng Pan, Dongxiao Zhu

Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made significant advancement in visual recognition tasks in computer vision.

Classification General Classification +1

Contextual-Bandit Based Personalized Recommendation with Time-Varying User Interests

no code implementations29 Feb 2020 Xiao Xu, Fang Dong, Yanghua Li, Shaojian He, Xin Li

A contextual bandit problem is studied in a highly non-stationary environment, which is ubiquitous in various recommender systems due to the time-varying interests of users.

Recommendation Systems

Improve SGD Training via Aligning Mini-batches

no code implementations23 Feb 2020 Xiangrui Li, Deng Pan, Xin Li, Dongxiao Zhu

In each iteration of SGD, a mini-batch from the training data is sampled and the true gradient of the loss function is estimated as the noisy gradient calculated on this mini-batch.

A Real-Time Deep Network for Crowd Counting

1 code implementation16 Feb 2020 Xiaowen Shi, Xin Li, Caili Wu, Shuchen Kong, Jing Yang, Liang He

Automatic analysis of highly crowded people has attracted extensive attention from computer vision research.

Crowd Counting

Exploiting Semantic Relations for Fine-grained Entity Typing

1 code implementation AKBC 2020 Hongliang Dai, Yangqiu Song, Xin Li

We find that, in some cases, existing neural fine-grained entity typing models may ignore the semantic information in the context that is important for typing.

Entity Typing TAG

Hybrid Graph Neural Networks for Crowd Counting

no code implementations31 Jan 2020 Ao Luo, Fan Yang, Xin Li, Dong Nie, Zhicheng Jiao, Shangchen Zhou, Hong Cheng

In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph.

Crowd Counting

Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling

no code implementations23 Dec 2019 Wenkai Han, Chenglu Wen, Cheng Wang, Xin Li, Qing Li

Point2Node can dynamically explore correlation among all graph nodes from different levels, and adaptively aggregate the learned features.

Face Beautification: Beyond Makeup Transfer

1 code implementation8 Dec 2019 Xudong Liu, Ruizhe Wang, Chih-Fan Chen, Minglei Yin, Hao Peng, Shukhan Ng, Xin Li

Inspired by the latest advances in style-based synthesis and face beauty prediction, we propose a novel framework of face beautification.


Digital Twin: Acquiring High-Fidelity 3D Avatar from a Single Image

no code implementations7 Dec 2019 Ruizhe Wang, Chih-Fan Chen, Hao Peng, Xudong Liu, Oliver Liu, Xin Li

We present an approach to generate high fidelity 3D face avatar with a high-resolution UV texture map from a single image.

Face Model

Relevance-Promoting Language Model for Short-Text Conversation

no code implementations26 Nov 2019 Xin Li, Piji Li, Wei Bi, Xiaojiang Liu, Wai Lam

In this paper, we propose to formulate the STC task as a language modeling problem and tailor-make a training strategy to adapt a language model for response generation.

Language Modelling Response Generation +1

Multi-Task Driven Feature Models for Thermal Infrared Tracking

1 code implementation26 Nov 2019 Qiao Liu, Xin Li, Zhenyu He, Nana Fan, Di Yuan, Wei Liu, Yonsheng Liang

These two feature models are learned using a multi-task matching framework and are jointly optimized on the TIR tracking task.

Thermal Infrared Object Tracking

Sparse estimation via $\ell_q$ optimization method in high-dimensional linear regression

no code implementations12 Nov 2019 Xin Li, Yaohua Hu, Chong Li, Xiaoqi Yang, Tianzi Jiang

In this paper, we discuss the statistical properties of the $\ell_q$ optimization methods $(0<q\leq 1)$, including the $\ell_q$ minimization method and the $\ell_q$ regularization method, for estimating a sparse parameter from noisy observations in high-dimensional linear regression with either a deterministic or random design.

Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology

1 code implementation1 Nov 2019 Chen Zhao, Jiaqi Yang, Xin Xiong, Angfan Zhu, Zhiguo Cao, Xin Li

To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis.

General Classification Point Cloud Classification

Anion charge-lattice volume dependent Li ion migration in compounds with the face-centered cubic anion frameworks

no code implementations25 Oct 2019 Zhenming Xu, Xin Chen, Ronghan Chen, Xin Li, Hong Zhu

In this work, the face-centered cubic (fcc) anion frameworks were creatively constructed to study the effects of anion charge and lattice volume on the stability of lithium ion occupation and lithium ion migration.

Applied Physics

Spoofing and Anti-Spoofing with Wax Figure Faces

no code implementations12 Oct 2019 Shan Jia, Xin Li, Chuanbo Hu, Zhengquan Xu

In this work, we introduce a wax figure face database (WFFD) as a novel and super-realistic 3D face presentation attack.

Face Detection Face Recognition +1

Exploiting BERT for End-to-End Aspect-based Sentiment Analysis

1 code implementation WS 2019 Xin Li, Lidong Bing, Wenxuan Zhang, Wai Lam

In this paper, we investigate the modeling power of contextualized embeddings from pre-trained language models, e. g. BERT, on the E2E-ABSA task.

Aspect-Based Sentiment Analysis Model Selection

Improving Fine-grained Entity Typing with Entity Linking

1 code implementation IJCNLP 2019 Hongliang Dai, Donghong Du, Xin Li, Yangqiu Song

Fine-grained entity typing is a challenging problem since it usually involves a relatively large tag set and may require to understand the context of the entity mention.

Entity Linking Entity Typing +1

Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence

no code implementations3 Sep 2019 Chen Zhao, Jiaqi Yang, Ke Xian, Zhiguo Cao, Xin Li

Matching corresponding features between two images is a fundamental task to computer vision with numerous applications in object recognition, robotics, and 3D reconstruction.

3D Reconstruction Object Recognition

Small and Practical BERT Models for Sequence Labeling

no code implementations IJCNLP 2019 Henry Tsai, Jason Riesa, Melvin Johnson, Naveen Arivazhagan, Xin Li, Amelia Archer

We propose a practical scheme to train a single multilingual sequence labeling model that yields state of the art results and is small and fast enough to run on a single CPU.

Part-Of-Speech Tagging

Deep Concept-wise Temporal Convolutional Networks for Action Localization

2 code implementations26 Aug 2019 Xin Li, Tianwei Lin, Xiao Liu, Chuang Gan, WangMeng Zuo, Chao Li, Xiang Long, Dongliang He, Fu Li, Shilei Wen

In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution.

Action Classification Action Localization

Domain-adversarial Network Alignment

no code implementations15 Aug 2019 Huiting Hong, Xin Li, Yuangang Pan, Ivor Tsang

Network alignment is a critical task to a wide variety of fields.

Network Embedding

BMN: Boundary-Matching Network for Temporal Action Proposal Generation

10 code implementations ICCV 2019 Tianwei Lin, Xiao Liu, Xin Li, Errui Ding, Shilei Wen

To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.

Action Detection Action Recognition +1

GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving

3 code implementations arXiv preprint 2020 Xin Li, Xiaowen Ying, Mooi Choo Chuah

Despite the advancement in the technology of autonomous driving cars, the safety of a self-driving car is still a challenging problem that has not been well studied.

Autonomous Driving motion prediction +1

Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning

no code implementations27 Jun 2019 Ziqi Ren, Jie Li, Xuetong Xue, Xin Li, Fan Yang, Zhicheng Jiao, Xinbo Gao

In addition, we introduce a novel three-stage learning approach which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process.

Image Reconstruction Knowledge Distillation +1

Vispi: Automatic Visual Perception and Interpretation of Chest X-rays

no code implementations MIDL 2019 Xin Li, Rui Cao, Dongxiao Zhu

Medical imaging contains the essential information for rendering diagnostic and treatment decisions.

Image Captioning

Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking

1 code implementation9 Jun 2019 Qiao Liu, Xin Li, Zhenyu He, Nana Fan, Di Yuan, Hongpeng Wang

These two similarities complement each other and hence enhance the discriminative capacity of the network for handling distractors.

Semantic Similarity Thermal Infrared Object Tracking

STN-Homography: estimate homography parameters directly

no code implementations6 Jun 2019 Qiang Zhou, Xin Li

In this paper, we introduce the STN-Homography model to directly estimate the homography matrix between image pair.

Homography Estimation

RF-Net: An End-to-End Image Matching Network based on Receptive Field

1 code implementation CVPR 2019 Xuelun Shen, Cheng Wang, Xin Li, Zenglei Yu, Jonathan Li, Chenglu Wen, Ming Cheng, Zijian He

This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images.

Keypoint Detection

LO-Net: Deep Real-time Lidar Odometry

no code implementations CVPR 2019 Qing Li, Shaoyang Chen, Cheng Wang, Xin Li, Chenglu Wen, Ming Cheng, Jonathan Li

We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation.

Pose Estimation

Target-Aware Deep Tracking

no code implementations CVPR 2019 Xin Li, Chao Ma, Baoyuan Wu, Zhenyu He, Ming-Hsuan Yang

Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep features for visual tracking are not as significant as that for object recognition.

Object Recognition Visual Tracking

NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences

1 code implementation CVPR 2019 Chen Zhao, Zhiguo Cao, Chi Li, Xin Li, Jiaqi Yang

Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision.

Pyramid Mask Text Detector

1 code implementation28 Mar 2019 Jingchao Liu, Xuebo Liu, Jie Sheng, Ding Liang, Xin Li, Qingjie Liu

Scene text detection, an essential step of scene text recognition system, is to locate text instances in natural scene images automatically.

Instance Segmentation Scene Text Detection +2

Iris R-CNN: Accurate Iris Segmentation in Non-cooperative Environment

no code implementations25 Mar 2019 Chunyang Feng, Yufeng Sun, Xin Li

Despite the significant advances in iris segmentation, accomplishing accurate iris segmentation in non-cooperative environment remains a grand challenge.

Iris Segmentation Region Proposal

Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

2 code implementations CVPR 2019 Xin Li, Yiming Zhou, Zheng Pan, Jiashi Feng

It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off.

Neural Architecture Search

CONet: A Cognitive Ocean Network

no code implementations9 Jan 2019 Huimin Lu, Dong Wang, Yujie Li, Jianru Li, Xin Li, Hyoungseop Kim, Seiichi Serikawa, Iztok Humar

The Cognitive Ocean Network (CONet) will become the mainstream of future ocean science and engineering developments.

DAC: Data-free Automatic Acceleration of Convolutional Networks

1 code implementation20 Dec 2018 Xin Li, Shuai Zhang, Bolan Jiang, Yingyong Qi, Mooi Choo Chuah, Ning Bi

A complex deep learning model with high accuracy runs slowly on resource-limited devices, while a light-weight model that runs much faster loses accuracy.

Image Classification Multi-Person Pose Estimation +1