Search Results for author: Li Liu

Found 177 papers, 70 papers with code

Region Graph Embedding Network for Zero-Shot Learning

no code implementations ECCV 2020 Guo-Sen Xie, Li Liu, Fan Zhu, Fang Zhao, Zheng Zhang, Yazhou Yao, Jie Qin, Ling Shao

To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.

Graph Embedding Zero-Shot Learning

RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision

no code implementations18 Sep 2023 Mingjie Pan, Jiaming Liu, Renrui Zhang, Peixiang Huang, Xiaoqi Li, Li Liu, Shanghang Zhang

3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels.

Autonomous Driving

Grouping Boundary Proposals for Fast Interactive Image Segmentation

no code implementations8 Sep 2023 Li Liu, Da Chen, Minglei Shu, Laurent D. Cohen

These boundary proposals are then incorporated into the proposed image segmentation model, such that the target segmentation contours are made up of a set of selected boundary proposals and the corresponding geodesic paths linking them.

Image Segmentation Semantic Segmentation

A Survey on Deep Multi-modal Learning for Body Language Recognition and Generation

1 code implementation17 Aug 2023 Li Liu, Lufei Gao, Wentao Lei, Fengji Ma, Xiaotian Lin, Jinting Wang

In summary, this survey paper provides a comprehensive understanding of deep multi-modal learning for various BL generations and recognitions for the first time.

Domain Adaptation Self-Supervised Learning

Few-shot Class-incremental Learning: A Survey

no code implementations13 Aug 2023 Jinghua Zhang, Li Liu, Olli Silven, Matti Pietikäinen, Dewen Hu

In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of incremental learning and few-shot learning.

class-incremental learning Few-Shot Class-Incremental Learning +4

Pareto Invariant Representation Learning for Multimedia Recommendation

no code implementations9 Aug 2023 Shanshan Huang, Haoxuan Li, Qingsong Li, Chunyuan Zheng, Li Liu

Multimedia recommendation involves personalized ranking tasks, where multimedia content is usually represented using a generic encoder.

Representation Learning

SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation

1 code implementation24 Jul 2023 YiQing Wang, Zihan Li, Jieru Mei, Zihao Wei, Li Liu, Chen Wang, Shengtian Sang, Alan Yuille, Cihang Xie, Yuyin Zhou

To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis.

Contrastive Learning Image Reconstruction +4

ROFusion: Efficient Object Detection using Hybrid Point-wise Radar-Optical Fusion

1 code implementation17 Jul 2023 Liu Liu, Shuaifeng Zhi, Zhenhua Du, Li Liu, Xinyu Zhang, Kai Huo, Weidong Jiang

In this paper, we propose a hybrid point-wise Radar-Optical fusion approach for object detection in autonomous driving scenarios.

Autonomous Driving object-detection +2

Unbiased Scene Graph Generation via Two-stage Causal Modeling

no code implementations11 Jul 2023 Shuzhou Sun, Shuaifeng Zhi, Qing Liao, Janne Heikkilä, Li Liu

To remedy this, we propose Two-stage Causal Modeling (TsCM) for the SGG task, which takes the long-tailed distribution and semantic confusion as confounders to the Structural Causal Model (SCM) and then decouples the causal intervention into two stages.

Causal Inference Graph Generation +2

All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment

no code implementations7 Jul 2023 Chunhui Zhang, Xin Sun, Li Liu, Yiqian Yang, Qiong Liu, Xi Zhou, Yanfeng Wang

This approach achieves feature integration in a unified backbone, removing the need for carefully-designed fusion modules and resulting in a more effective and efficient VL tracking framework.

Revisiting Computer-Aided Tuberculosis Diagnosis

no code implementations6 Jul 2023 Yun Liu, Yu-Huan Wu, Shi-Chen Zhang, Li Liu, Min Wu, Ming-Ming Cheng

This dataset enables the training of sophisticated detectors for high-quality CTD.

Image Classification

UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering

no code implementations15 Jun 2023 Mingjie Pan, Li Liu, Jiaming Liu, Peixiang Huang, Longlong Wang, Shanghang Zhang, Shaoqing Xu, Zhiyi Lai, Kuiyuan Yang

In this technical report, we present our solution, named UniOCC, for the Vision-Centric 3D occupancy prediction track in the nuScenes Open Dataset Challenge at CVPR 2023.

Prediction Of Occupancy Grid Maps

SplatFlow: Learning Multi-frame Optical Flow via Splatting

no code implementations15 Jun 2023 Bo wang, Yifan Zhang, Jian Li, Yang Yu, Zhenping Sun, Li Liu, Dewen Hu

Occlusion problem remains a key challenge in Optical Flow Estimation (OFE) despite the recent significant progress brought by deep learning in the field.

Optical Flow Estimation

Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks

no code implementations6 Jun 2023 Jianrong Wang, Yaxin Zhao, Li Liu, Tianyi Xu, Qi Li, Sen Li

Given an audio clip and a reference face image, the goal of the talking head generation is to generate a high-fidelity talking head video.

Talking Head Generation

A Novel Interpretable and Generalizable Re-synchronization Model for Cued Speech based on a Multi-Cuer Corpus

1 code implementation5 Jun 2023 Lufei Gao, Shan Huang, Li Liu

Cued Speech (CS) is a multi-modal visual coding system combining lip reading with several hand cues at the phonetic level to make the spoken language visible to the hearing impaired.

Lip Reading

MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information

1 code implementation4 Jun 2023 Jianrong Wang, Yuchen Huo, Li Liu, Tianyi Xu, Qi Li, Sen Li

Audio-visual speech recognition (AVSR) gains increasing attention from researchers as an important part of human-computer interaction.

Audio-Visual Speech Recognition speech-recognition +1

Robust Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers

no code implementations1 Jun 2023 Ruotong Wang, Hongrui Chen, Zihao Zhu, Li Liu, Yong Zhang, Yanbo Fan, Baoyuan Wu

These triggers have demonstrated strong attack performance even under backdoor defense, which aims to eliminate or suppress the backdoor effect in the model.

Backdoor Attack backdoor defense

X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Models

1 code implementation18 May 2023 Yixiong Chen, Li Liu, Chris Ding

This paper introduces a novel explainable image quality evaluation approach called X-IQE, which leverages visual large language models (LLMs) to evaluate text-to-image generation methods by generating textual explanations.


FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learning

no code implementations15 May 2023 Penghui Wei, Hongjian Dou, Shaoguo Liu, Rongjun Tang, Li Liu, Liang Wang, Bo Zheng

We introduce FedAds, the first benchmark for CVR estimation with vFL, to facilitate standardized and systematical evaluations for vFL algorithms.

Federated Learning Privacy Preserving

A Comprehensive Survey on Segment Anything Model for Vision and Beyond

1 code implementation14 May 2023 Chunhui Zhang, Li Liu, Yawen Cui, Guanjie Huang, Weilin Lin, Yiqian Yang, Yuehong Hu

As the first to comprehensively review the progress of segmenting anything task for vision and beyond based on the foundation model of SAM, this work focuses on its applications to various tasks and data types by discussing its historical development, recent progress, and profound impact on broad applications.

Deep Intellectual Property Protection: A Survey

no code implementations28 Apr 2023 Yuchen Sun, Tianpeng Liu, Panhe Hu, Qing Liao, Shaojing Fu, Nenghai Yu, Deke Guo, Yongxiang Liu, Li Liu

Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made revolutionary progress in recent years, and are widely used in various fields.

Few-shot Class-incremental Pill Recognition

no code implementations24 Apr 2023 Jinghua Zhang, Li Liu, Kai Gao, Dewen Hu

In practice, the expensive cost of data annotation and the continuously increasing categories of new pills make it meaningful to develop a few-shot class-incremental pill recognition system.

class-incremental learning Few-Shot Class-Incremental Learning +3

Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution

1 code implementation13 Apr 2023 Zhuo Su, Jiehua Zhang, Tianpeng Liu, Zhen Liu, Shuanghui Zhang, Matti Pietikäinen, Li Liu

This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution.

Image Classification object-detection +1

Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition

no code implementations4 Apr 2023 Bowen Peng, Jianyue Xie, Bo Peng, Li Liu

The proposed method contributes a mixed clutter variants generation strategy and a new inference branch equipped with channel-weighted mean square error (CWMSE) loss for invariant representation learning.

Contrastive Learning Representation Learning

Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision

1 code implementation CVPR 2023 Xinyi Ying, Li Liu, Yingqian Wang, Ruojing Li, Nuo Chen, Zaiping Lin, Weidong Sheng, Shilin Zhou

Interestingly, during the training phase supervised by point labels, we discover that CNNs first learn to segment a cluster of pixels near the targets, and then gradually converge to predict groundtruth point labels.

Discovering and Explaining the Non-Causality of Deep Learning in SAR ATR

2 code implementations3 Apr 2023 Weijie Li, Wei Yang, Li Liu, Wenpeng Zhang, Yongxiang Liu

Therefore, the degree of overfitting for clutter reflects the non-causality of deep learning in SAR ATR.

Selection bias

FER-former: Multi-modal Transformer for Facial Expression Recognition

no code implementations23 Mar 2023 Yande Li, Mingjie Wang, Minglun Gong, Yonggang Lu, Li Liu

The ever-increasing demands for intuitive interactions in Virtual Reality has triggered a boom in the realm of Facial Expression Recognition (FER).

Facial Expression Recognition Facial Expression Recognition (FER)

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

no code implementations15 Mar 2023 Huali Xu, Shuaifeng Zhi, Shuzhou Sun, Vishal M. Patel, Li Liu

Deep learning has been highly successful in computer vision with large amounts of labeled data, but struggles with limited labeled training data.

cross-domain few-shot learning

Spatio-Temporal Structure Consistency for Semi-supervised Medical Image Classification

no code implementations3 Mar 2023 Wentao Lei, Lei Liu, Li Liu

Experiments on two medical image datasets (i. e., ISIC 2018 challenge and ChestX-ray14) show that our method outperforms state-of-the-art SSL methods.

Image Classification Medical Diagnosis +1

Adversarial Machine Learning: A Systematic Survey of Backdoor Attack, Weight Attack and Adversarial Example

no code implementations19 Feb 2023 Baoyuan Wu, Li Liu, Zihao Zhu, Qingshan Liu, Zhaofeng He, Siwei Lyu

Some paradigms have been recently developed to explore this adversarial phenomenon occurring at different stages of a machine learning system, such as training-time adversarial attack (i. e., backdoor attack), deployment-time adversarial attack (i. e., weight attack), and inference-time adversarial attack (i. e., adversarial example).

Backdoor Attack

Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters

1 code implementation12 Feb 2023 Yawen Cui, Zitong Yu, Rizhao Cai, Xun Wang, Alex C. Kot, Li Liu

The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.

Continual Learning Contrastive Learning +2

Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning

1 code implementation24 Jan 2023 Yawen Cui, Wanxia Deng, Haoyu Chen, Li Liu

Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophically forgetting all encountered classes previously.

class-incremental learning Few-Shot Class-Incremental Learning +2

Enabling Augmented Segmentation and Registration in Ultrasound-Guided Spinal Surgery via Realistic Ultrasound Synthesis from Diagnostic CT Volume

no code implementations5 Jan 2023 Ang Li, Jiayi Han, Yongjian Zhao, Keyu Li, Li Liu

While the US is not a standard paradigm for spinal surgery, the scarcity of intra-operative clinical US data is an insurmountable bottleneck in training a neural network.

WL-Align: Weisfeiler-Lehman Relabeling for Aligning Users across Networks via Regularized Representation Learning

1 code implementation29 Dec 2022 Li Liu, Penggang Chen, Xin Li, William K. Cheung, Youmin Zhang, Qun Liu, Guoyin Wang

Aligning users across networks using graph representation learning has been found effective where the alignment is accomplished in a low-dimensional embedding space.

Graph Representation Learning

TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning

1 code implementation28 Dec 2022 Peixiang Huang, Li Liu, Renrui Zhang, Song Zhang, Xinli Xu, Baichao Wang, Guoyi Liu

In this paper, we propose the learning scheme of Target Inner-Geometry from the LiDAR modality into camera-based BEV detectors for both dense depth and BEV features, termed as TiG-BEV.

3D Object Detection object-detection

AMDET: Attention based Multiple Dimensions EEG Transformer for Emotion Recognition

no code implementations23 Dec 2022 Yongling Xu, Yang Du, Jing Zou, Tianying Zhou, Lushan Xiao, Li Liu, Pengcheng

In this paper, we propose a deep model called Attention-based Multiple Dimensions EEG Transformer (AMDET), which can exploit the complementarity among the spectral-spatial-temporal features of EEG data by employing the multi-dimensional global attention mechanism.

EEG Electroencephalogram (EEG) +1

Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning

1 code implementation8 Dec 2022 Yixiong Chen, Chunhui Zhang, Chris H. Q. Ding, Li Liu

In this work, we pre-train DNNs on ultrasound (US) domains instead of ImageNet to reduce the domain gap in medical US applications.

Contrastive Learning Meta-Learning +2

Rethinking Two Consensuses of the Transferability in Deep Learning

no code implementations1 Dec 2022 Yixiong Chen, Jingxian Li, Chris Ding, Li Liu

Deep transfer learning (DTL) has formed a long-term quest toward enabling deep neural networks (DNNs) to reuse historical experiences as efficiently as humans.

General Knowledge Image Classification +2

TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks

no code implementations25 Nov 2022 Taoyong Cui, Jianze Li, Yuhan Dong, Li Liu

In the first stage, we propose a novel algorithm called polar decomposition-based orthogonal initialization (PDOI) to find a good initialization for the orthogonal optimization.

Boosting Binary Neural Networks via Dynamic Thresholds Learning

no code implementations4 Nov 2022 Jiehua Zhang, Xueyang Zhang, Zhuo Su, Zitong Yu, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu

For ViTs, DyBinaryCCT presents the superiority of the convolutional embedding layer in fully binarized ViTs and achieves 56. 1% on the ImageNet dataset, which is nearly 9% higher than the baseline.


HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretraining

1 code implementation10 Oct 2022 Chunhui Zhang, Yixiong Chen, Li Liu, Qiong Liu, Xi Zhou

This work proposes a hierarchical contrastive learning (HiCo) method to improve the transferability for the US video model pretraining.

Contrastive Learning

On Clustering Trend in Language Evolution Based on Dynamical Behaviors of Multi-Agent Model

no code implementations3 Oct 2022 Yu Zhang, Li Liu, Chen Diao, Ning Cai

Computer model has been extensively adopted to overcome the time limitation of language evolution by transforming language theory into physical modeling mechanism, which helps to explore the general laws of the evolution.


SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation

1 code implementation13 Sep 2022 Zhuo Su, Max Welling, Matti Pietikäinen, Li Liu

Precisely, the presence of scalar features makes the major part of the network binarizable, while vector features serve to retain rich structural information and ensure SO(3) equivariance.

Autonomous Driving Binarization

Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense

no code implementations11 Sep 2022 Bowen Peng, Bo Peng, Jie zhou, Jianyue Xie, Li Liu

Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers).

Adversarial Attack Adversarial Robustness

Bag of Tricks for FGSM Adversarial Training

no code implementations6 Sep 2022 Zichao Li, Li Liu, Zeyu Wang, Yuyin Zhou, Cihang Xie

Adversarial training (AT) with samples generated by Fast Gradient Sign Method (FGSM), also known as FGSM-AT, is a computationally simple method to train robust networks.

Cross-Domain Few-Shot Classification via Inter-Source Stylization

no code implementations17 Aug 2022 Huali Xu, Shuaifeng Zhi, Li Liu

The goal of Cross-Domain Few-Shot Classification (CDFSC) is to accurately classify a target dataset with limited labelled data by exploiting the knowledge of a richly labelled auxiliary dataset, despite the differences between the domains of the two datasets.

Classification Cross-Domain Few-Shot +2

KL-divergence Based Deep Learning for Discrete Time Model

no code implementations10 Aug 2022 Li Liu, Xiangeng Fang, Di Wang, Weijing Tang, Kevin He

Neural Network (Deep Learning) is a modern model in Artificial Intelligence and it has been exploited in Survival Analysis.

Survival Analysis Survival Prediction

Data-free Backdoor Removal based on Channel Lipschitzness

2 code implementations5 Aug 2022 Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu

Pruning these channels was then shown to be effective in mitigating the backdoor behaviors.

Graph Signal Processing for Heterogeneous Change Detection Part II: Spectral Domain Analysis

no code implementations3 Aug 2022 Yuli Sun, Lin Lei, Dongdong Guan, Gangyao Kuang, Li Liu

Then, we propose a regression model for the HCD, which decomposes the source signal into the regressed signal and changed signal, and requires the regressed signal have the same spectral property as the target signal on the same graph.

Change Detection regression

Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation

no code implementations26 Jul 2022 Ye Wang, Jingbo Liao, Hong Yu, Guoyin Wang, Xiaoxia Zhang, Li Liu

Particularly, the model integrates the macro-level guided-category knowledge and micro-level open-domain dialogue data for the training, leveraging the priori knowledge into the latent space, which enables the model to disentangle the latent variables within the mesoscopic scale.


Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometry

no code implementations20 Jul 2022 Yawen Cui, Zitong Yu, Wei Peng, Li Liu

Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding the overfitting and catastrophic forgetting simultaneously.

class-incremental learning Few-Shot Class-Incremental Learning +3

HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints

no code implementations16 Jul 2022 Wei Wu, Junlin He, Yu Qiao, Guoheng Fu, Li Liu, Jin Yu

The in-memory approximate nearest neighbor search (ANNS) algorithms have achieved great success for fast high-recall query processing, but are extremely inefficient when handling hybrid queries with unstructured (i. e., feature vectors) and structured (i. e., related attributes) constraints.

MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging

1 code implementation3 Jun 2022 Yixiong Chen, Li Liu, Jingxian Li, Hua Jiang, Chris Ding, Zongwei Zhou

In this work, we propose a meta-learning-based LR tuner, named MetaLR, to make different layers automatically co-adapt to downstream tasks based on their transferabilities across domains.

Meta-Learning Transfer Learning

Median Pixel Difference Convolutional Network for Robust Face Recognition

no code implementations30 May 2022 Jiehua Zhang, Zhuo Su, Li Liu

Face recognition is one of the most active tasks in computer vision and has been widely used in the real world.

Face Recognition Robust Face Recognition

Deep Learning for Visual Speech Analysis: A Survey

no code implementations22 May 2022 Changchong Sheng, Gangyao Kuang, Liang Bai, Chenping Hou, Yulan Guo, Xin Xu, Matti Pietikäinen, Li Liu

Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment.

speech-recognition Visual Speech Recognition

Acoustic-to-articulatory Inversion based on Speech Decomposition and Auxiliary Feature

no code implementations2 Apr 2022 Jianrong Wang, Jinyu Liu, Longxuan Zhao, Shanyu Wang, Ruiguo Yu, Li Liu

Acoustic-to-articulatory inversion (AAI) is to obtain the movement of articulators from speech signals.

Residual-guided Personalized Speech Synthesis based on Face Image

no code implementations1 Apr 2022 Jianrong Wang, Zixuan Wang, Xiaosheng Hu, XueWei Li, Qiang Fang, Li Liu

Experimental results show that the speech synthesized by our model is comparable to the personalized speech synthesized by training a large amount of audio data in previous works.

Speech Synthesis

Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation

1 code implementation8 Feb 2022 Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang

Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation.

Knowledge Distillation

WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking

1 code implementation19 Jan 2022 Chunhui Zhang, Guanjie Huang, Li Liu, Shan Huang, Yinan Yang, Xiang Wan, Shiming Ge, DaCheng Tao

In this work, we propose WebUAV-3M, the largest public UAV tracking benchmark to date, to facilitate both the development and evaluation of deep UAV trackers.

Attentional Feature Refinement and Alignment Network for Aircraft Detection in SAR Imagery

no code implementations18 Jan 2022 Yan Zhao, Lingjun Zhao, Zhong Liu, Dewen Hu, Gangyao Kuang, Li Liu

Aircraft detection in Synthetic Aperture Radar (SAR) imagery is a challenging task in SAR Automatic Target Recognition (SAR ATR) areas due to aircraft's extremely discrete appearance, obvious intraclass variation, small size and serious background's interference.

Improved (Related-key) Differential-based Neural Distinguishers for SIMON and SIMECK Block Ciphers

1 code implementation11 Jan 2022 Jinyu Lu, Guoqiang Liu, Bing Sun, Chao Li, Li Liu

In CRYPTO 2019, Gohr made a pioneering attempt and successfully applied deep learning to the differential cryptanalysis against NSA block cipher SPECK32/64, achieving higher accuracy than the pure differential distinguishers.


Decoupling Makes Weakly Supervised Local Feature Better

1 code implementation CVPR 2022 Kunhong Li, Longguang Wang, Li Liu, Qing Ran, Kai Xu, Yulan Guo

Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences.

Camera Localization Image Matching +1

Local Motion and Contrast Priors Driven Deep Network for Infrared Small Target Super-Resolution

1 code implementation4 Jan 2022 Xinyi Ying, Yingqian Wang, Longguang Wang, Weidong Sheng, Li Liu, Zaiping Lin, Shilin Zhou

Specifically, motivated by the local motion prior in the spatio-temporal dimension, we propose a local spatio-temporal attention module to perform implicit frame alignment and incorporate the local spatio-temporal information to enhance the local features (especially for small targets).


Learnable Lookup Table for Neural Network Quantization

1 code implementation CVPR 2022 Longguang Wang, Xiaoyu Dong, Yingqian Wang, Li Liu, Wei An, Yulan Guo

Since a linear quantizer (i. e., round(*) function) cannot well fit the bell-shaped distributions of weights and activations, many existing methods use pre-defined functions (e. g., exponential function) with learnable parameters to build the quantizer for joint optimization.

Image Classification Image Super-Resolution +2

Efficient Video Transformers with Spatial-Temporal Token Selection

1 code implementation23 Nov 2021 Junke Wang, Xitong Yang, Hengduo Li, Li Liu, Zuxuan Wu, Yu-Gang Jiang

Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost.

Video Recognition

Image-Guided Navigation of a Robotic Ultrasound Probe for Autonomous Spinal Sonography Using a Shadow-aware Dual-Agent Framework

no code implementations3 Nov 2021 Keyu Li, Yangxin Xu, Jian Wang, Dong Ni, Li Liu, Max Q. -H. Meng

Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers.

Anatomy Decision Making +2

Transient Synchronization Stability Analysis of Wind Farms with MMC-HVDC Integration Under Offshore AC Grid Fault

no code implementations25 Oct 2021 Yu Zhang, Chen Zhang, Renxin Yang, Jing Lyu, Li Liu, Xu Cai

The MMC-HVDC connected offshore wind farms (OWFs) could suffer short circuit fault (SCF), whereas their transient stability is not well analysed.

Unsupervised cross-user adaptation in taste sensation recognition based on surface electromyography with conformal prediction and domain regularized component analysis

no code implementations20 Oct 2021 Hengyang Wang, Xianghao Zhan, Li Liu, Asif Ullah, Huiyan Li, Han Gao, You Wang, Guang Li

The results show that DRCA improved the classification accuracy on six subjects (p < 0. 05), compared with the baseline models trained only with the source domain data;, while CPSC did not guarantee the accuracy improvement.

Conformal Prediction Data Augmentation

Dynamic Binary Neural Network by learning channel-wise thresholds

no code implementations8 Oct 2021 Jiehua Zhang, Zhuo Su, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu

The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs.

J-Score: A Robust Measure of Clustering Accuracy

no code implementations3 Sep 2021 Navid Ahmadinejad, Li Liu

It then computes two weighted sums of Jaccard indices measuring the reconciliation from classes to clusters and vice versa.

Clustering set matching

Pixel Difference Networks for Efficient Edge Detection

1 code implementation ICCV 2021 Zhuo Su, Wenzhe Liu, Zitong Yu, Dewen Hu, Qing Liao, Qi Tian, Matti Pietikäinen, Li Liu

A faster version of PiDiNet with less than 0. 1M parameters can still achieve comparable performance among state of the arts with 200 FPS.

Edge Detection

Investigate the Essence of Long-Tailed Recognition from a Unified Perspective

1 code implementation8 Jul 2021 Lei Liu, Li Liu

Specifically, we demonstrate that long-tailed recognition suffers from both sample number and category similarity.

Self-Supervised Learning

Multi-modal Entity Alignment in Hyperbolic Space

no code implementations7 Jun 2021 Hao Guo, Jiuyang Tang, Weixin Zeng, Xiang Zhao, Li Liu

To mitigate this problem, a viable approach is to integrate complementary knowledge from other MMKGs.

Knowledge Graphs Multi-modal Entity Alignment

Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification

1 code implementation CVPR 2020 Yichao Yan, Jie Qin1, Jiaxin Chen, Li Liu, Fan Zhu, Ying Tai, Ling Shao

In each hypergraph, different temporal granularities are captured by hyperedges that connect a set of graph nodes (i. e., part-based features) across different temporal ranges.

Video-Based Person Re-Identification

Learning Multi-Attention Context Graph for Group-Based Re-Identification

1 code implementation29 Apr 2021 Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei-Shi Zheng, Xiaokang Yang, Ling Shao

Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.

Person Re-Identification

Classifying herbal medicine origins by temporal and spectral data mining of electronic nose

1 code implementation14 Apr 2021 Li Liu, Xianghao Zhan, Ziheng Duan, Yi Wu, Rumeng Wu, Xiaoqing Guan, Zhan Wang, You Wang, Guang Li

In this study, we classified different origins of three categories of herbal medicines with different feature extraction methods: manual feature extraction, mathematical transformation, deep learning algorithms.

Dimensionality Reduction

Anchor-Free Person Search

1 code implementation CVPR 2021 Yichao Yan, Jinpeng Li, Jie Qin, Song Bai, Shengcai Liao, Li Liu, Fan Zhu, Ling Shao

Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id).

Pedestrian Detection Person Re-Identification +1

Deep Learning for Instance Retrieval: A Survey

no code implementations27 Jan 2021 Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew

In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.

Content-Based Image Retrieval Instance Search +1

Deep Learning for Scene Classification: A Survey

no code implementations26 Jan 2021 Delu Zeng, Minyu Liao, Mohammad Tavakolian, Yulan Guo, Bolei Zhou, Dewen Hu, Matti Pietikäinen, Li Liu

Scene classification, aiming at classifying a scene image to one of the predefined scene categories by comprehending the entire image, is a longstanding, fundamental and challenging problem in computer vision.

Classification General Classification +1

How to Train Your Agent to Read and Write

1 code implementation4 Jan 2021 Li Liu, Mengge He, Guanghui Xu, Mingkui Tan, Qi Wu

Typically, this requires an agent to fully understand the knowledge from the given text materials and generate correct and fluent novel paragraphs, which is very challenging in practice.

KG-to-Text Generation Knowledge Graphs

The Unreasonable Effectiveness of the Class-reversed Sampling in Tail Sample Memorization

no code implementations1 Jan 2021 Benyi Hu, Chi Zhang, Yuehu Liu, Le Wang, Li Liu

Long-tailed visual class recognition poses significant challenges to traditional machine learning and emerging deep networks due to its inherent class imbalance.


One-Pass Multi-View Clustering for Large-Scale Data

no code implementations ICCV 2021 Jiyuan Liu, Xinwang Liu, Yuexiang Yang, Li Liu, Siqi Wang, Weixuan Liang, Jiangyong Shi

In this way, the generated partition can guide multi-view matrix factorization to produce more purposive coefficient matrix which, as a feedback, improves the quality of partition.


Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge Distillation

1 code implementation ICCV 2021 Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang

Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation.

Knowledge Distillation

Localized Simple Multiple Kernel K-Means

1 code implementation ICCV 2021 Xinwang Liu, Sihang Zhou, Li Liu, Chang Tang, Siwei Wang, Jiyuan Liu, Yi Zhang

After that, we theoretically show that the objective of SimpleMKKM is a special case of this local kernel alignment criterion with normalizing each base kernel matrix.


Distributed Fusion Estimation for Stochastic Uncertain Systems with Network-Induced Complexity and Multiple Noise

no code implementations24 Dec 2020 Li Liu, Wenju Zhou, Minrui Fei, Zhile Yang, Hongyong Yang, Huiyu Zhou

This paper investigates an issue of distributed fusion estimation under network-induced complexity and stochastic parameter uncertainties.

Learning Class Unique Features in Fine-Grained Visual Classification

no code implementations22 Nov 2020 Runkai Zheng, Zhijia Yu, Yinqi Zhang, Chris Ding, Hei Victor Cheng, Li Liu

A major challenge in Fine-Grained Visual Classification (FGVC) is distinguishing various categories with high inter-class similarity by learning the feature that differentiate the details.

Classification Fine-Grained Image Classification +1

Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog

no code implementations5 Nov 2020 Shen Gao, Xiuying Chen, Li Liu, Dongyan Zhao, Rui Yan

Hence, in this paper, we propose to recommend an appropriate sticker to user based on multi-turn dialog context and sticker using history of user.

Multi-Modal Active Learning for Automatic Liver Fibrosis Diagnosis based on Ultrasound Shear Wave Elastography

no code implementations2 Nov 2020 Lufei Gao, Ruisong Zhou, Changfeng Dong, Cheng Feng, Zhen Li, Xiang Wan, Li Liu

With the development of radiomics, noninvasive diagnosis like ultrasound (US) imaging plays a very important role in automatic liver fibrosis diagnosis (ALFD).

Active Learning

Developing Univariate Neurodegeneration Biomarkers with Low-Rank and Sparse Subspace Decomposition

no code implementations26 Oct 2020 Gang Wang, Qunxi Dong, Jianfeng Wu, Yi Su, Kewei Chen, Qingtang Su, Xiaofeng Zhang, Jinguang Hao, Tao Yao, Li Liu, Caiming Zhang, Richard J Caselli, Eric M Reiman, Yalin Wang

With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25$\%$ reduction in the mean annual change with 80$\%$ power and two-tailed $P=0. 05$ are 116, 279 and 387 for the longitudinal $A\beta+$ AD, $A\beta+$ mild cognitive impairment (MCI) and $A\beta+$ CU groups, respectively.

FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond

1 code implementation19 Oct 2020 Zhuo Su, Linpu Fang, Deke Guo, Dewen Hu, Matti Pietikäinen, Li Liu

Binary neural networks (BNNs), where both weights and activations are binarized into 1 bit, have been widely studied in recent years due to its great benefit of highly accelerated computation and substantially reduced memory footprint that appeal to the development of resource constrained devices.

Image Classification Quantization

New Ideas and Trends in Deep Multimodal Content Understanding: A Review

no code implementations16 Oct 2020 Wei Chen, Weiping Wang, Li Liu, Michael S. Lew

The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text.

Cross-Modal Retrieval Image Captioning +5

Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition

1 code implementation13 Oct 2020 Jianrong Wang, Tong Wu, Shanyu Wang, Mei Yu, Qiang Fang, Ju Zhang, Li Liu

To this end, in this work, we present a novel end-to-end 3D lip motion Network (3LMNet) by utilizing the sentence-level 3D lip motion (S3DLM) to recognize speakers in both the text-independent and text-dependent contexts.

Speaker Recognition Text-Independent Speaker Recognition

A Real-time Contribution Measurement Method for Participants in Federated Learning

no code implementations28 Sep 2020 Bingjie Yan, Yize Zhou, Boyi Liu, Jun Wang, Yuhan Zhang, Li Liu, Xiaolan Nie, Zhiwei Fan, Zhixuan Liang

However, there is a lack of a sufficiently reasonable contribution measurement mechanism to distribute the reward for each agent.

Federated Learning

Group Whitening: Balancing Learning Efficiency and Representational Capacity

1 code implementation CVPR 2021 Lei Huang, Yi Zhou, Li Liu, Fan Zhu, Ling Shao

Results show that GW consistently improves the performance of different architectures, with absolute gains of $1. 02\%$ $\sim$ $1. 49\%$ in top-1 accuracy on ImageNet and $1. 82\%$ $\sim$ $3. 21\%$ in bounding box AP on COCO.

Normalization Techniques in Training DNNs: Methodology, Analysis and Application

no code implementations27 Sep 2020 Lei Huang, Jie Qin, Yi Zhou, Fan Zhu, Li Liu, Ling Shao

Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications.

Counterfactual-based minority oversampling for imbalanced classification

no code implementations21 Aug 2020 Hao Luo, Li Liu

A key challenge of oversampling in imbalanced classification is that the generation of new minority samples often neglects the usage of majority classes, resulting in most new minority sampling spreading the whole minority space.

Classification General Classification +1

Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection

1 code implementation13 Jul 2020 Cong Chen, Shouyang Dong, Ye Tian, Kunlin Cao, Li Liu, Yuanhao Guo

(1) The teacher model serves a dual role as a teacher and a student, such that the teacher predictions on unlabeled images may be very close to those of student, which limits the upper-bound of the student.

Knowledge Distillation object-detection +4

Attention-based Residual Speech Portrait Model for Speech to Face Generation

no code implementations9 Jul 2020 Jianrong Wang, Xiaosheng Hu, Li Liu, Wei Liu, Mei Yu, Tianyi Xu

Given a speaker's speech, it is interesting to see if it is possible to generate this speaker's face.

Face Generation

JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image

1 code implementation ECCV 2020 Linpu Fang, Xingyan Liu, Li Liu, Hang Xu, Wenxiong Kang

The key ideas are two-fold: a) explicitly modeling the dependencies among joints and the relations between the pixels and the joints for better local feature representation learning; b) unifying the dense pixel-wise offset predictions and direct joint regression for end-to-end training.

3D Hand Pose Estimation regression +1

Dynamic Group Convolution for Accelerating Convolutional Neural Networks

1 code implementation ECCV 2020 Zhuo Su, Linpu Fang, Wenxiong Kang, Dewen Hu, Matti Pietikäinen, Li Liu

In this paper, we propose dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly.

Image Classification

Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues

no code implementations17 Jun 2020 Jianrong Wang, Ge Zhang, Zhen-Yu Wu, XueWei Li, Li Liu

Compared with static views, abundant dynamic properties between video frames are beneficial to refined depth estimation, especially for dynamic objects.

Monocular Depth Estimation

Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution

1 code implementation CVPR 2022 Yan Feng, Baoyuan Wu, Yanbo Fan, Li Liu, Zhifeng Li, Shutao Xia

This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown.

Adversarial Attack

Improved Residual Networks for Image and Video Recognition

2 code implementations10 Apr 2020 Ionut Cosmin Duta, Li Liu, Fan Zhu, Ling Shao

We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths.

Action Recognition Image Classification +4

Controllable Orthogonalization in Training DNNs

1 code implementation CVPR 2020 Lei Huang, Li Liu, Fan Zhu, Diwen Wan, Zehuan Yuan, Bo Li, Ling Shao

Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation.

Image Classification

An Investigation into the Stochasticity of Batch Whitening

1 code implementation CVPR 2020 Lei Huang, Lei Zhao, Yi Zhou, Fan Zhu, Li Liu, Ling Shao

Our work originates from the observation that while various whitening transformations equivalently improve the conditioning, they show significantly different behaviors in discriminative scenarios and training Generative Adversarial Networks (GANs).

Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog

1 code implementation10 Mar 2020 Shen Gao, Xiuying Chen, Chang Liu, Li Liu, Dongyan Zhao, Rui Yan

Stickers with vivid and engaging expressions are becoming increasingly popular in online messaging apps, and some works are dedicated to automatically select sticker response by matching text labels of stickers with previous utterances.

Trajectory Grouping with Curvature Regularization for Tubular Structure Tracking

no code implementations8 Mar 2020 Li Liu, Da Chen, Ming-Lei Shu, Baosheng Li, Huazhong Shu, Michel Paques, Laurent D. Cohen

Tubular structure tracking is a crucial task in the fields of computer vision and medical image analysis.

Auto-Encoding Twin-Bottleneck Hashing

2 code implementations CVPR 2020 Yuming Shen, Jie Qin, Jiaxin Chen, Mengyang Yu, Li Liu, Fan Zhu, Fumin Shen, Ling Shao

One bottleneck (i. e., binary codes) conveys the high-level intrinsic data structure captured by the code-driven graph to the other (i. e., continuous variables for low-level detail information), which in turn propagates the updated network feedback for the encoder to learn more discriminative binary codes.

graph construction Retrieval

Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs

no code implementations ECCV 2020 Lei Huang, Jie Qin, Li Liu, Fan Zhu, Ling Shao

To this end, we propose layer-wise conditioning analysis, which explores the optimization landscape with respect to each layer independently.

Deep Video Super-Resolution using HR Optical Flow Estimation

2 code implementations6 Jan 2020 Longguang Wang, Yulan Guo, Li Liu, Zaiping Lin, Xinpu Deng, Wei An

The key challenge for video SR lies in the effective exploitation of temporal dependency between consecutive frames.

Motion Compensation Optical Flow Estimation +1

Deep Learning for 3D Point Clouds: A Survey

3 code implementations27 Dec 2019 Yulan Guo, Hanyun Wang, Qingyong Hu, Hao liu, Li Liu, Mohammed Bennamoun

To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.

3D Object Detection 3D Shape Classification +3

Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test

no code implementations NeurIPS 2019 Lizhong Ding, Mengyang Yu, Li Liu, Fan Zhu, Yong liu, Yu Li, Ling Shao

DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution.

Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Network

1 code implementation6 Nov 2019 Junfeng Hu, Zhencheng Fan, Jun Liao, Li Liu

The primary goal of skeletal motion prediction is to generate future motion by observing a sequence of 3D skeletons.

motion prediction

Fast Large-Scale Discrete Optimization Based on Principal Coordinate Descent

no code implementations16 Sep 2019 Huan Xiong, Mengyang Yu, Li Liu, Fan Zhu, Fumin Shen, Ling Shao

Binary optimization, a representative subclass of discrete optimization, plays an important role in mathematical optimization and has various applications in computer vision and machine learning.


Embarrassingly Simple Binary Representation Learning

1 code implementation26 Aug 2019 Yuming Shen, Jie Qin, Jiaxin Chen, Li Liu, Fan Zhu

Recent binary representation learning models usually require sophisticated binary optimization, similarity measure or even generative models as auxiliaries.

Representation Learning

RANet: Ranking Attention Network for Fast Video Object Segmentation

2 code implementations ICCV 2019 Ziqin Wang, Jun Xu, Li Liu, Fan Zhu, Ling Shao

Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner.

Semantic Segmentation Semi-Supervised Video Object Segmentation +1

NLH: A Blind Pixel-level Non-local Method for Real-world Image Denoising

1 code implementation17 Jun 2019 Yingkun Hou, Jun Xu, Mingxia Liu, Guanghai Liu, Li Liu, Fan Zhu, Ling Shao

This is motivated by the fact that finding closely similar pixels is more feasible than similar patches in natural images, which can be used to enhance image denoising performance.

Image Denoising

Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image

1 code implementation17 Jun 2019 Jun Xu, Yuan Huang, Ming-Ming Cheng, Li Liu, Fan Zhu, Zhou Xu, Ling Shao

A simple but useful observation on our NAC is: as long as the noise is weak, it is feasible to learn a self-supervised network only with the corrupted image, approximating the optimal parameters of a supervised network learned with pairs of noisy and clean images.

Image Denoising

STAR: A Structure and Texture Aware Retinex Model

1 code implementation16 Jun 2019 Jun Xu, Yingkun Hou, Dongwei Ren, Li Liu, Fan Zhu, Mengyang Yu, Haoqian Wang, Ling Shao

A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image.

Low-Light Image Enhancement

Dynamically Visual Disambiguation of Keyword-based Image Search

no code implementations27 May 2019 Yazhou Yao, Zeren Sun, Fumin Shen, Li Liu, Li-Min Wang, Fan Zhu, Lizhong Ding, Gangshan Wu, Ling Shao

To address this issue, we present an adaptive multi-model framework that resolves polysemy by visual disambiguation.

General Classification Image Retrieval

Iterative Normalization: Beyond Standardization towards Efficient Whitening

5 code implementations CVPR 2019 Lei Huang, Yi Zhou, Fan Zhu, Li Liu, Ling Shao

With the support of SND, we provide natural explanations to several phenomena from the perspective of optimization, e. g., why group-wise whitening of DBN generally outperforms full-whitening and why the accuracy of BN degenerates with reduced batch sizes.

Approach for Semi-automatic Construction of Anti-infective Drug Ontology Based on Entity Linking

no code implementations5 Dec 2018 Ying Shen, Yang Deng, Kaiqi Yuan, Li Liu, Yong liu

Experiments show that our selected features have achieved a precision rate of 86. 77%, a recall rate of 89. 03% and an F1 score of 87. 89%.

Entity Linking

Generative Model for Material Experiments Based on Prior Knowledge and Attention Mechanism

no code implementations16 Nov 2018 Mincong Luo, Xinfu He, Li Liu

In this paper, we propose a generative adversarial model based on prior knowledge and attention mechanism to achieve the generation of irradiated material images (data-to-image model), and a prediction model for corresponding industrial performance (image-to-data model).

Deep Learning for Generic Object Detection: A Survey

no code implementations6 Sep 2018 Li Liu, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, Matti Pietikäinen

Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images.

object-detection Object Proposal Generation

TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights

no code implementations ECCV 2018 Diwen Wan, Fumin Shen, Li Liu, Fan Zhu, Jie Qin, Ling Shao, Heng Tao Shen

Despite the remarkable success of Convolutional Neural Networks (CNNs) on generalized visual tasks, high computational and memory costs restrict their comprehensive applications on consumer electronics (e. g., portable or smart wearable devices).

object-detection Object Detection

Generative Domain-Migration Hashing for Sketch-to-Image Retrieval

1 code implementation ECCV 2018 Jingyi Zhang, Fumin Shen, Li Liu, Fan Zhu, Mengyang Yu, Ling Shao, Heng Tao Shen, Luc van Gool

The generative model learns a mapping that the distributions of sketches can be indistinguishable from the distribution of natural images using an adversarial loss, and simultaneously learns an inverse mapping based on the cycle consistency loss in order to enhance the indistinguishability.

Multi-Task Learning Retrieval +1

Automatic Derivation Of Formulas Using Reforcement Learning

no code implementations15 Aug 2018 MinZhong Luo, Li Liu

First, the formula is abstractly expressed as a multiway tree model, and then each step of the formula derivation transformation is abstracted as a mapping of multiway trees.


Pixel-level Semantics Guided Image Colorization

no code implementations5 Aug 2018 Jiaojiao Zhao, Li Liu, Cees G. M. Snoek, Jungong Han, Ling Shao

While many image colorization algorithms have recently shown the capability of producing plausible color versions from gray-scale photographs, they still suffer from the problems of context confusion and edge color bleeding.

Colorization Image Colorization +1

Fractional Wavelet Scattering Network and Applications

no code implementations30 Jun 2018 Li Liu, Jiasong Wu, Dengwang Li, Lotfi Senhadji, Huazhong Shu

Results: The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is significantly improved in fractional scattering domain.

General Classification Image Classification

SCAN: Sliding Convolutional Attention Network for Scene Text Recognition

no code implementations2 Jun 2018 Yi-Chao Wu, Fei Yin, Xu-Yao Zhang, Li Liu, Cheng-Lin Liu

Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications.

Scene Text Recognition

Ro-SOS: Metric Expression Network (MEnet) for Robust Salient Object Segmentation

1 code implementation15 May 2018 Delu Zeng, Yixuan He, Li Liu, Zhihong Chen, Jiabin Huang, Jie Chen, John Paisley

In this paper, we propose an end-to-end generic salient object segmentation model called Metric Expression Network (MEnet) to deal with saliency detection with the tolerance of distortion.

Saliency Detection Semantic Segmentation

Zero-Shot Sketch-Image Hashing

1 code implementation CVPR 2018 Yuming Shen, Li Liu, Fumin Shen, Ling Shao

As an important part of ZSIH, we formulate a generative hashing scheme in reconstructing semantic knowledge representations for zero-shot retrieval.

Representation Learning Retrieval +1

Texture Classification in Extreme Scale Variations using GANet

no code implementations13 Feb 2018 Li Liu, Jie Chen, Guoying Zhao, Paul Fieguth, Xilin Chen, Matti Pietikäinen

Because extreme scale variations are not necessarily present in most standard texture databases, to support the proposed extreme-scale aspects of texture understanding we are developing a new dataset, the Extreme Scale Variation Textures (ESVaT), to test the performance of our framework.

Classification General Classification +1

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

no code implementations31 Jan 2018 Li Liu, Jie Chen, Paul Fieguth, Guoying Zhao, Rama Chellappa, Matti Pietikainen

Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention.

General Classification Texture Classification

Quantifying Facial Age by Posterior of Age Comparisons

1 code implementation31 Aug 2017 Yunxuan Zhang, Li Liu, Cheng Li, Chen Change Loy

We introduce a novel approach for annotating large quantity of in-the-wild facial images with high-quality posterior age distribution as labels.

Ranked #6 on Age Estimation on MORPH Album2 (using extra training data)

Age And Gender Classification Age Estimation

Towards Automatic Construction of Diverse, High-quality Image Dataset

no code implementations22 Aug 2017 Yazhou Yao, Jian Zhang, Fumin Shen, Li Liu, Fan Zhu, Dongxiang Zhang, Heng-Tao Shen

To eliminate manual annotation, in this work, we propose a novel image dataset construction framework by employing multiple textual queries.

Image Classification object-detection +2

Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval

no code implementations ICCV 2017 Yuming Shen, Li Liu, Ling Shao, Jingkuan Song

Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching.

Cross-Modal Retrieval Descriptive +1

Fast Person Re-Identification via Cross-Camera Semantic Binary Transformation

no code implementations CVPR 2017 Jiaxin Chen, Yunhong Wang, Jie Qin, Li Liu, Ling Shao

Numerous methods have been proposed for person re-identification, most of which however neglect the matching efficiency.

Person Re-Identification