Search Results for author: Jian Cheng

Found 99 papers, 45 papers with code

ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices

no code implementations ECCV 2020 Xiangyu He, Zitao Mo, Ke Cheng, Weixiang Xu, Qinghao Hu, Peisong Wang, Qingshan Liu, Jian Cheng

The matrix composed of basis vectors is referred to as the proxy matrix, and auxiliary variables serve as the coefficients of this linear combination.

Binarization Quantization

Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition

1 code implementation ECCV 2020 Ke Cheng, Yifan Zhang, Congqi Cao, Lei Shi, Jian Cheng, Hanqing Lu

Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment.

Action Recognition Skeleton Based Action Recognition

Towards Accurate Post-training Network Quantization via Bit-Split and Stitching

1 code implementation ICML 2020 Peisong Wang, Qiang Chen, Xiangyu He, Jian Cheng

Network quantization is essential for deploying deep models to IoT devices due to the high efficiency, no matter on special hardware like TPU or general hardware like CPU and GPU.

Image Classification Instance Segmentation +4

Spiking NeRF: Making Bio-inspired Neural Networks See through the Real World

no code implementations20 Sep 2023 Xingting Yao, Qinghao Hu, Tielong Liu, Zitao Mo, Zeyu Zhu, Zhengyang Zhuge, Jian Cheng

We propose the temporal condensing-and-padding (TCP) strategy to tackle the masked samples to maintain regular temporal length, i. e., regular tensors, for hardware-friendly computation.

Enhancing Your Trained DETRs with Box Refinement

1 code implementation21 Jul 2023 Yiqun Chen, Qiang Chen, Peize Sun, Shoufa Chen, Jingdong Wang, Jian Cheng

We hope our work will bring the attention of the detection community to the localization bottleneck of current DETR-like models and highlight the potential of the RefineBox framework.

FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation

no code implementations26 Apr 2023 Yan Wang, Jian Cheng, Yixin Chen, Shuai Shao, Lanyun Zhu, Zhenzhou Wu, Tao Liu, Haogang Zhu

In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model.

Image Segmentation Medical Image Segmentation +3

HPN: Personalized Federated Hyperparameter Optimization

no code implementations11 Apr 2023 Anda Cheng, Zhen Wang, Yaliang Li, Jian Cheng

The client encoding is calculated with a random projection-based procedure to protect each client's privacy.

Federated Learning Hyperparameter Optimization

$\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks

1 code implementation1 Feb 2023 Zeyu Zhu, Fanrong Li, Zitao Mo, Qinghao Hu, Gang Li, Zejian Liu, Xiaoyao Liang, Jian Cheng

Through an in-depth analysis of the topology of GNNs, we observe that the topology of the graph leads to significant differences between nodes, and most of the nodes in a graph appear to have a small aggregation value.


Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once

no code implementations CVPR 2023 Tao Xie, Shiguang Wang, Ke Wang, Linqi Yang, Zhiqiang Jiang, Xingcheng Zhang, Kun Dai, Ruifeng Li, Jian Cheng

In this work, we show that it is feasible to perform multiple tasks concurrently on point cloud with a straightforward yet effective multi-task network.

Incremental Learning Multi-Task Learning

MDL-NAS: A Joint Multi-Domain Learning Framework for Vision Transformer

no code implementations CVPR 2023 Shiguang Wang, Tao Xie, Jian Cheng, Xingcheng Zhang, Haijun Liu

Technically, MDL-NAS constructs a coarse-to-fine search space, where the coarse search space offers various optimal architectures for different tasks while the fine search space provides fine-grained parameter sharing to tackle the inherent obstacles of multi-domain learning.

Image Classification Incremental Learning

DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection

1 code implementation25 Nov 2022 Yiqun Chen, Qiang Chen, Qinghao Hu, Jian Cheng

In this paper, we revisit these two assignment methods and find that bringing one-to-many assignment back to end-to-end fully convolutional detectors helps with model convergence.

object-detection Object Detection

GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks

1 code implementation25 Oct 2022 Xingting Yao, Fanrong Li, Zitao Mo, Jian Cheng

In this paper, we propose GLIF, a unified spiking neuron, to fuse different bio-features in different neuronal behaviors, enlarging the representation space of spiking neurons.

PalQuant: Accelerating High-precision Networks on Low-precision Accelerators

1 code implementation3 Aug 2022 Qinghao Hu, Gang Li, Qiman Wu, Jian Cheng

In this paper, we propose the PArallel Low-precision Quantization (PalQuant) method that approximates high-precision computations via learning parallel low-precision representations from scratch.

Quantization Vocal Bursts Intensity Prediction

PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient

1 code implementation5 Jul 2022 Weihan Cao, Yifan Zhang, Jianfei Gao, Anda Cheng, Ke Cheng, Jian Cheng

First, the difference in feature magnitude between the teacher and the student could enforce overly strict constraints on the student.

Knowledge Distillation object-detection +1

Learning the policy for mixed electric platoon control of automated and human-driven vehicles at signalized intersection: a random search approach

no code implementations24 Jun 2022 Xia Jiang, Jian Zhang, Xiaoyu Shi, Jian Cheng

Meanwhile, the simulation results demonstrate the effectiveness of the delay reward, which is designed to outperform distributed reward mechanism} Compared with normal car-following behavior, the sensitivity analysis reveals that the energy can be saved to different extends (39. 27%-82. 51%) by adjusting the relative importance of the optimization goal.

reinforcement-learning Reinforcement Learning (RL)

Soft Threshold Ternary Networks

1 code implementation4 Apr 2022 Weixiang Xu, Xiangyu He, Tianli Zhao, Qinghao Hu, Peisong Wang, Jian Cheng

The latest STTN shows that ResNet-18 with ternary weights and ternary activations achieves up to 68. 2% Top-1 accuracy on ImageNet.


Efficient Virtual View Selection for 3D Hand Pose Estimation

1 code implementation29 Mar 2022 Jian Cheng, Yanguang Wan, Dexin Zuo, Cuixia Ma, Jian Gu, Ping Tan, Hongan Wang, Xiaoming Deng, yinda zhang

3D hand pose estimation from single depth is a fundamental problem in computer vision, and has wide applications. However, the existing methods still can not achieve satisfactory hand pose estimation results due to view variation and occlusion of human hand.

3D Hand Pose Estimation

Differentially Private Federated Learning with Local Regularization and Sparsification

no code implementations CVPR 2022 Anda Cheng, Peisong Wang, Xi Sheryl Zhang, Jian Cheng

User-level differential privacy (DP) provides certifiable privacy guarantees to the information that is specific to any user's data in federated learning.

Federated Learning

Network resilience in the aging brain

no code implementations3 Feb 2022 Tao Liu, Shu Guo, Hao liu, Rui Kang, Mingyang Bai, Jiyang Jiang, Wei Wen, Xing Pan, Jun Tai, JianXin Li, Jian Cheng, Jing Jing, Zhenzhou Wu, Haijun Niu, Haogang Zhu, Zixiao Li, Yongjun Wang, Henry Brodaty, Perminder Sachdev, Daqing Li

Degeneration and adaptation are two competing sides of the same coin called resilience in the progressive processes of brain aging or diseases.

Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond

no code implementations25 Jan 2022 Xiangyu He, Jian Cheng

Super-resolution as an ill-posed problem has many high-resolution candidates for a low-resolution input.

Image Restoration Super-Resolution

Q-ViT: Fully Differentiable Quantization for Vision Transformer

no code implementations19 Jan 2022 Zhexin Li, Tong Yang, Peisong Wang, Jian Cheng

In this paper, we propose a fully differentiable quantization method for vision transformer (ViT) named as Q-ViT, in which both of the quantization scales and bit-widths are learnable parameters.


APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers

1 code implementation CVPR 2022 Jiahao Lu, Xi Sheryl Zhang, Tianli Zhao, Xiangyu He, Jian Cheng

Showing how vision Transformers are at the risk of privacy leakage via gradients, we urge the significance of designing privacy-safer Transformer models and defending schemes.

Federated Learning

DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy

1 code implementation16 Oct 2021 Anda Cheng, Jiaxing Wang, Xi Sheryl Zhang, Qiang Chen, Peisong Wang, Jian Cheng

In light of this missing, we propose the very first framework that employs neural architecture search to automatic model design for private deep learning, dubbed as DPNAS.

Neural Architecture Search

Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices

1 code implementation15 Oct 2021 Tianli Zhao, Xi Sheryl Zhang, Wentao Zhu, Jiaxing Wang, Sen yang, Ji Liu, Jian Cheng

In this paper, we present a unified framework with Joint Channel pruning and Weight pruning (JCW), and achieves a better Pareto-frontier between the latency and accuracy than previous model compression approaches.

Model Compression

Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization

no code implementations ICCV 2021 Weihan Chen, Peisong Wang, Jian Cheng

Finally, based on the above simplification, we show that the original problem can be reformulated as a Multiple-Choice Knapsack Problem (MCKP) and propose a greedy search algorithm to solve it efficiently.

Multiple-choice Quantization

Improving Binary Neural Networks through Fully Utilizing Latent Weights

no code implementations12 Oct 2021 Weixiang Xu, Qiang Chen, Xiangyu He, Peisong Wang, Jian Cheng

Binary Neural Networks (BNNs) rely on a real-valued auxiliary variable W to help binary training.

Revisiting Quantization Error in Face Alignment

no code implementations ICCV Workshop 2021 Xing Lan, Qinghao Hu, Jian Cheng

The statistical re- sults show the NME generated by quantization error is even larger than 1/3 of the SOTA item, which is a serious obsta- cle for making a new breakthrough in face alignment.

Face Alignment Quantization

Architecture Aware Latency Constrained Sparse Neural Networks

no code implementations1 Sep 2021 Tianli Zhao, Qinghao Hu, Xiangyu He, Weixiang Xu, Jiaxing Wang, Cong Leng, Jian Cheng

Acceleration of deep neural networks to meet a specific latency constraint is essential for their deployment on mobile devices.

IntraLoss: Further Margin via Gradient-Enhancing Term for Deep Face Recognition

no code implementations7 Jul 2021 Chengzhi Jiang, Yanzhou Su, Wen Wang, Haiwei Bai, Haijun Liu, Jian Cheng

This method, named IntraLoss, explicitly performs gradient enhancement in the anisotropic region so that the intra-class distribution continues to shrink, resulting in isotropic and more compact intra-class distribution and further margin between identities.

Face Recognition

Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss

1 code implementation6 Jun 2021 Jian Cheng, Ziyang Liu, Hao Guan, Zhenzhou Wu, Haogang Zhu, Jiyang Jiang, Wei Wen, DaCheng Tao, Tao Liu

In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data.

Age Estimation

HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap

1 code implementation7 Apr 2021 Xing Lan, Qinghao Hu, Qiang Chen, Jian Xue, Jian Cheng

In particular, our HIH reaches 4. 08 NME (Normalized Mean Error) on WFLW, and 3. 21 on COFW, which exceeds previous methods by a significant margin.

Face Alignment regression

AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition

no code implementations ICCV 2021 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered.

Action Recognition Skeleton Based Action Recognition

You Only Look One-level Feature

6 code implementations CVPR 2021 Qiang Chen, Yingming Wang, Tong Yang, Xiangyu Zhang, Jian Cheng, Jian Sun

From the perspective of optimization, we introduce an alternative way to address the problem instead of adopting the complex feature pyramids - {\em utilizing only one-level feature for detection}.

object-detection Object Detection

Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing

no code implementations4 Mar 2021 Zejian Liu, Gang Li, Jian Cheng

BERT is the most recent Transformer-based model that achieves state-of-the-art performance in various NLP tasks.


Generative Zero-shot Network Quantization

no code implementations21 Jan 2021 Xiangyu He, Qinghao Hu, Peisong Wang, Jian Cheng

Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration.

Data Free Quantization Image Generation

Dynamic Dual Gating Neural Networks

1 code implementation ICCV 2021 Fanrong Li, Gang Li, Xiangyu He, Jian Cheng

In particular, dynamic dual gating can provide 59. 7% saving in computing of ResNet50 with 76. 41% top-1 accuracy on ImageNet, which has advanced the state-of-the-art.

Taking Modality-free Human Identification as Zero-shot Learning

no code implementations2 Oct 2020 Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu, Shuai Zheng, Yao Zhao, Jian Cheng

There have been numerous methods proposed for human identification, such as face identification, person re-identification, and gait identification.

Event Detection Face Identification +3

Faster Person Re-Identification

1 code implementation ECCV 2020 Guan'an Wang, Shaogang Gong, Jian Cheng, Zeng-Guang Hou

In this work, we introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine (CtF) hashing code search strategy, which complementarily uses short and long codes, achieving both faster speed and better accuracy.

Code Search Person Re-Identification +1

Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition

1 code implementation7 Jul 2020 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Besides, from the data aspect, we introduce a skeletal data decoupling technique to emphasize the specific characteristics of space/time and different motion scales, resulting in a more comprehensive understanding of the human actions. To test the effectiveness of the proposed method, extensive experiments are conducted on four challenging datasets for skeleton-based gesture and action recognition, namely, SHREC, DHG, NTU-60 and NTU-120, where DSTA-Net achieves state-of-the-art performance on all of them.

Action Recognition Skeleton Based Action Recognition +1

What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition

no code implementations7 Apr 2020 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

The two perspectives are orthogonal and complementary to each other; and by fusing them in a unified framework, our method achieves a more comprehensive understanding of the skeleton data.

Action Recognition Gesture Recognition +2

From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition

no code implementations10 Feb 2020 Fuzhen Li, Zhenfeng Zhu, Xingxing Zhang, Jian Cheng, Yao Zhao

In zero-shot learning (ZSL), the samples to be classified are usually projected into side information templates such as attributes.

Zero-Shot Learning

Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification

2 code implementations10 Feb 2020 Guan-An Wang, Tianzhu Zhang. Yang Yang, Jian Cheng, Jianlong Chang, Xu Liang, Zeng-Guang Hou

Second, given cross-modality unpaired-images of a person, our method can generate cross-modality paired images from exchanged images.

Person Re-Identification

A Comprehensive Study on Temporal Modeling for Online Action Detection

1 code implementation21 Jan 2020 Wen Wang, Xiaojiang Peng, Yu Qiao, Jian Cheng

Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years.

Online Action Detection

Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks

3 code implementations15 Dec 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.

Action Recognition graph construction +2

Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning

1 code implementation CVPR 2020 Shuai Zheng, Zhenfeng Zhu, Xingxing Zhang, Zhizhe Liu, Jian Cheng, Yao Zhao

Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks.

Graph Representation Learning

Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision

no code implementations28 Nov 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action recognition.

Action Recognition Skeleton Based Action Recognition +1

A Discriminative Learned CNN Embedding for Remote Sensing Image Scene Classification

no code implementations28 Nov 2019 Wen Wang, Lijun Du, Yinxing Gao, Yanzhou Su, Feng Wang, Jian Cheng

Concretely, for remote sensing image scene classification, we would like to map images from the same scene to feature vectors that are close, and map images from different scenes to feature vectors that are widely separated.

Classification General Classification +2

Location-aware Upsampling for Semantic Segmentation

1 code implementation13 Nov 2019 Xiangyu He, Zitao Mo, Qiang Chen, Anda Cheng, Peisong Wang, Jian Cheng

Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks.

Semantic Segmentation

Convolutional Prototype Learning for Zero-Shot Recognition

no code implementations22 Oct 2019 Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu, Shuai Zheng, Yao Zhao, Jian Cheng

The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors.

Image Captioning Object Recognition +2

SpatialFlow: Bridging All Tasks for Panoptic Segmentation

1 code implementation19 Oct 2019 Qiang Chen, Anda Cheng, Xiangyu He, Peisong Wang, Jian Cheng

Object location is fundamental to panoptic segmentation as it is related to all things and stuff in the image scene.

Instance Segmentation Object Detection +1

A System-Level Solution for Low-Power Object Detection

no code implementations24 Sep 2019 Fanrong Li, Zitao Mo, Peisong Wang, Zejian Liu, Jiayun Zhang, Gang Li, Qinghao Hu, Xiangyu He, Cong Leng, Yang Zhang, Jian Cheng

As a case study, we evaluate our object detection system on a real-world surveillance video with input size of 512x512, and it turns out that the system can achieve an inference speed of 18 fps at the cost of 6. 9W (with display) with an mAP of 66. 4 verified on the PASCAL VOC 2012 dataset.

object-detection Object Detection +1

Compact Global Descriptor for Neural Networks

1 code implementation23 Jul 2019 Xiangyu He, Ke Cheng, Qiang Chen, Qinghao Hu, Peisong Wang, Jian Cheng

Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks.

Audio Classification Deep Attention +2

Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification

no code implementations23 Jul 2019 Haijun Liu, Jian Cheng

To address these two issues, we propose focusing on enhancing the discriminative feature learning (EDFL) with two extreme simple means from two core aspects, (1) skip-connection for mid-level features incorporation to improve the person features with more discriminability and robustness, and (2) dual-modality triplet loss to guide the training procedures by simultaneously considering the cross-modality discrepancy and intra-modality variations.

Cross-Modality Person Re-identification Person Re-Identification

Edge Heuristic GAN for Non-uniform Blind Deblurring

no code implementations11 Jul 2019 Shuai Zheng, Zhenfeng Zhu, Jian Cheng, Yandong Guo, Yao Zhao

Non-uniform blur, mainly caused by camera shake and motions of multiple objects, is one of the most common causes of image quality degradation.


Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition

1 code implementation arXiv 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

However, the topology of the graph is set by hand and fixed over all layers, which may be not optimal for the action recognition task and the hierarchical CNN structures.

Action Recognition Skeleton Based Action Recognition

Overcoming the bottleneck in traditional assessments of verbal memory: Modeling human ratings and classifying clinical group membership

no code implementations WS 2019 Ch, Chelsea ler, Peter W. Foltz, Jian Cheng, Jared C. Bernstein, Elizabeth P. Rosenfeld, Alex S. Cohen, Terje B. Holmlund, Brita Elvev{\aa}g

A final set of three features were used to both predict expert human ratings with a ridge regression model (r = 0. 88) and to differentiate patients from healthy individuals with an ensemble of logistic regression classifiers (accuracy = 76{\%}).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

The General Pair-based Weighting Loss for Deep Metric Learning

no code implementations30 May 2019 Haijun Liu, Jian Cheng, Wen Wang, Yanzhou Su

A large amount of loss functions based on pair distances have been presented in the literature for guiding the training of deep metric learning.

Image Retrieval Metric Learning +1

Attention: A Big Surprise for Cross-Domain Person Re-Identification

no code implementations30 May 2019 Haijun Liu, Jian Cheng, Shiguang Wang, Wen Wang

Unlike existing cross-domain Re-ID methods, leveraging the auxiliary information of those unlabeled target-domain data, we aim at enhancing the model generalization and adaptation by discriminative feature learning, and directly exploiting a pre-trained model to new domains (datasets) without any utilization of the information from target domains.

Person Re-Identification

Semi-supervised Learning with Contrastive Predicative Coding

no code implementations25 May 2019 Jiaxing Wang, Yin Zheng, Xiaoshuang Chen, Junzhou Huang, Jian Cheng

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain.

Temporal Action Detection by Joint Identification-Verification

no code implementations19 Oct 2018 Wen Wang, Yongjian Wu, Haijun Liu, Shiguang Wang, Jian Cheng

Temporal action detection aims at not only recognizing action category but also detecting start time and end time for each action instance in an untrimmed video.

Action Detection

Graph Convolutional Neural Networks based on Quantum Vertex Saliency

no code implementations4 Sep 2018 Lu Bai, Yuhang Jiao, Luca Rossi, Lixin Cui, Jian Cheng, Edwin R. Hancock

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes.

General Classification Graph Classification

Training Binary Weight Networks via Semi-Binary Decomposition

no code implementations ECCV 2018 Qinghao Hu, Gang Li, Peisong Wang, Yifan Zhang, Jian Cheng

In this paper, we propose a novel semi-binary decomposition method which decomposes a matrix into two binary matrices and a diagonal matrix.

Semi-Supervised Generative Adversarial Hashing for Image Retrieval

no code implementations ECCV 2018 Guan'an Wang, Qinghao Hu, Jian Cheng, Zeng-Guang Hou

Secondly, we design novel structure of the generative model and the discriminative model to learn the distribution of triplet-wise information in a semi-supervised way.

Image Retrieval Retrieval +2

Two-Step Quantization for Low-Bit Neural Networks

1 code implementation CVPR 2018 Peisong Wang, Qinghao Hu, Yifan Zhang, Chunjie Zhang, Yang Liu, Jian Cheng

In this paper, we propose a simple yet effective Two-Step Quantization (TSQ) framework, by decomposing the network quantization problem into two steps: code learning and transformation function learning based on the learned codes.

Quantization Vocal Bursts Valence Prediction

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

4 code implementations CVPR 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.

graph construction Skeleton Based Action Recognition +1

PCN: Part and Context Information for Pedestrian Detection with CNNs

no code implementations12 Apr 2018 Shiguang Wang, Jian Cheng, Haijun Liu, Ming Tang

To take advantage of the body parts and context information for pedestrian detection, we propose the part and context network (PCN) in this work.

Occlusion Handling Pedestrian Detection

From Hashing to CNNs: Training BinaryWeight Networks via Hashing

no code implementations8 Feb 2018 Qinghao Hu, Peisong Wang, Jian Cheng

To achieve this goal, we propose a novel approach named BWNH to train Binary Weight Networks via Hashing.

Recent Advances in Efficient Computation of Deep Convolutional Neural Networks

no code implementations3 Feb 2018 Jian Cheng, Peisong Wang, Gang Li, Qinghao Hu, Hanqing Lu

As for hardware implementation of deep neural networks, a batch of accelerators based on FPGA/ASIC have been proposed in recent years.

Network Pruning Quantization

Additive Margin Softmax for Face Verification

9 code implementations17 Jan 2018 Feng Wang, Weiyang Liu, Haijun Liu, Jian Cheng

In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works.

Face Verification Metric Learning

Director Field Analysis (DFA): Exploring Local White Matter Geometric Structure in diffusion MRI

no code implementations6 Jun 2017 Jian Cheng, Peter J. Basser

2) We propose Orientational Order (OO) and Orientational Dispersion (OD) indices to describe the degree of alignment and dispersion of a spherical function in a single voxel or in a region, respectively; 3) We also show how to construct a local orthogonal coordinate frame in each voxel exhibiting anisotropic diffusion; 4) Finally, we define three indices to describe three types of orientational distortion (splay, bend, and twist) in a local spatial neighborhood, and a total distortion index to describe distortions of all three types.

NormFace: L2 Hypersphere Embedding for Face Verification

3 code implementations21 Apr 2017 Feng Wang, Xiang Xiang, Jian Cheng, Alan L. Yuille

We show that both strategies, and small variants, consistently improve performance by between 0. 2% to 0. 4% on the LFW dataset based on two models.

Face Verification Metric Learning

Fixed-point Factorized Networks

no code implementations CVPR 2017 Peisong Wang, Jian Cheng

In recent years, Deep Neural Networks (DNN) based methods have achieved remarkable performance in a wide range of tasks and have been among the most powerful and widely used techniques in computer vision.

General Classification

Quantized Convolutional Neural Networks for Mobile Devices

1 code implementation CVPR 2016 Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, Jian Cheng

Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks.

General Classification

Online Sketching Hashing

no code implementations CVPR 2015 Cong Leng, Jiaxiang Wu, Jian Cheng, Xiao Bai, Hanqing Lu

Recently, hashing based approximate nearest neighbor (ANN) search has attracted much attention.

Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction

no code implementations CVPR 2014 Jian Cheng, Cong Leng, Jiaxiang Wu, Hainan Cui, Hanqing Lu

Image matching is one of the most challenging stages in 3D reconstruction, which usually occupies half of computational cost and inaccurate matching may lead to failure of reconstruction.

3D Reconstruction

Regularized Spherical Polar Fourier Diffusion MRI with Optimal Dictionary Learning

no code implementations2 Jul 2013 Jian Cheng, Tianzi Jiang, Rachid Deriche, Dinggang Shen, Pew-Thian Yap

Compared with the start-of-the-art CR-DL and DR-DL methods proposed by Merlet et al. and Bilgic et al., espectively, our work offers the following advantages.

Dictionary Learning

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