547 citations · 846 across the 24 of their papers we have counts for
24 papers
Block Convolution: Towards Memory-Efficient Inference of Large-Scale CNNs on FPGA
Gang Li, Zejian Liu, Fanrong Li +1
Deep convolutional neural networks have achieved remarkable progress in recent years. However, the large volume of intermediate results generated during inference poses a significa…
AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition
Lei Shi, Yifan Zhang, Jian Cheng +1
Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered. Recently, there…
Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing
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. In this paper, we investigate the hardware acceleration of BERT on…
Generative Zero-shot Network Quantization
Xiangyu He, Qinghao Hu, Peisong Wang +1
Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration. We show that, for high-level im…
BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh
Ming Qian, Congyu Qiao, Jiamin Lin +4
A photo captured with bokeh effect often means objects in focus are sharp while the out-of-focus areas are all blurred. DSLR can easily render this kind of effect naturally. Howeve…
Faster Person Re-Identification
Guan'an Wang, Shaogang Gong, Jian Cheng +1
Fast person re-identification (ReID) aims to search person images quickly and accurately. The main idea of recent fast ReID methods is the hashing algorithm, which learns compact b…
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition
Lei Shi, Yifan Zhang, Jian Cheng +1
Dynamic skeletal data, represented as the 2D/3D coordinates of human joints, has been widely studied for human action recognition due to its high-level semantic information and env…
What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition
Lei Shi, Yifan Zhang, Jian Cheng +1
Skeleton data, which consists of only the 2D/3D coordinates of the human joints, has been widely studied for human action recognition. Existing methods take the semantics as prior…
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
Guan-An Wang, Tianzhu Zhang. Yang Yang, Jian Cheng +3
RGB-Infrared (IR) person re-identification is very challenging due to the large cross-modality variations between RGB and IR images. The key solution is to learn aligned features t…
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
Lei Shi, Yifan Zhang, Jian Cheng +1
Graph convolutional networks (GCNs), which generalize CNNs to more generic non-Euclidean structures, have achieved remarkable performance for skeleton-based action recognition. How…
Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
Shuai Zheng, Zhenfeng Zhu, Xingxing Zhang +3
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. However, most existing algorit…
Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
Lei Shi, Yifan Zhang, Jian Cheng +1
Pose-based action recognition has drawn considerable attention recently. Existing methods exploit the joint positions to extract the body-part features from the activation map of t…
Location-aware Upsampling for Semantic Segmentation
Xiangyu He, Zitao Mo, Qiang Chen +3
Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond these semantic metrics,…
RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
Guan'an Wang, Tianzhu Zhang, Jian Cheng +3
RGB-Infrared (IR) person re-identification is an important and challenging task due to large cross-modality variations between RGB and IR images. Most conventional approaches aim t…
A System-Level Solution for Low-Power Object Detection
Fanrong Li, Zitao Mo, Peisong Wang +8
Object detection has made impressive progress in recent years with the help of deep learning. However, state-of-the-art algorithms are both computation and memory intensive. Though…
Convolutional Prototype Learning for Zero-Shot Recognition
Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu +3
Zero-shot learning (ZSL) has received increasing attention in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. The key to ZSL i…
Compact Global Descriptor for Neural Networks
Xiangyu He, Ke Cheng, Qiang Chen +3
Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks. Yet neither stacks of convo…
A Quantum-inspired Similarity Measure for the Analysis of Complete Weighted Graphs
Lu Bai, Luca Rossi, Lixin Cui +2
We develop a novel method for measuring the similarity between complete weighted graphs, which are probed by means of discrete-time quantum walks. Directly probing complete graphs…
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
Lei Shi, Yifan Zhang, Jian Cheng +1
In skeleton-based action recognition, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have achieved remarkable performance. Howe…
PCN: Part and Context Information for Pedestrian Detection with CNNs
Shiguang Wang, Jian Cheng, Haijun Liu +1
Pedestrian detection has achieved great improvements in recent years, while complex occlusion handling is still one of the most important problems. To take advantage of the body pa…
Recent Advances in Efficient Computation of Deep Convolutional Neural Networks
Jian Cheng, Peisong Wang, Gang Li +2
Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems. At the same time, the computational c…
From Hashing to CNNs: Training BinaryWeight Networks via Hashing
Qinghao Hu, Peisong Wang, Jian Cheng
Deep convolutional neural networks (CNNs) have shown appealing performance on various computer vision tasks in recent years. This motivates people to deploy CNNs to realworld appli…
Fixed-point Factorized Networks
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 techni…
Quantized Convolutional Neural Networks for Mobile Devices
Jiaxiang Wu, Cong Leng, Yuhang Wang +2
Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensab…