Houqiang Li

article

Exploiting weak mask representation with convolutional neural networks for accurate object tracking

Jianglei Huang, Wengang Zhou, Qi Tian, Houqiang Li

Multimedia Tools and Applications > 2019 > 78 > 15 > 20961- 20985

Recent years have witnessed the popularity of Convolutional Neural Networks (CNN) in a variety of computer vision tasks, including video object tracking. Existing object tracking methods with CNN employ either a scalar score or a confidence map as CNN’s output, which suffer the infeasibility of estimating the object’s accurate scale and rotation angle. Specifically, as with other traditional methods,...

article

Scene text detection with fully convolutional neural networks

Zhandong Liu, Wengang Zhou, Houqiang Li

Multimedia Tools and Applications > 2019 > 78 > 13 > 18205- 18227

Text detection in scene image has become a hot topic in computer vision and artificial intelligence research, due to its wide range of applications and challenges. Most state-of-the-art methods for text detection based on deep learning rely on text bounding box regression. These methods can not well handle the case that if the scene text is curved. In this paper, we propose a new framework for arbitrarily...

article

Multi-tracker fusion via adaptive outlier detection

Chao Xie, Ning Wang, Wengang Zhou, Weiping Li, more

Multimedia Tools and Applications > 2019 > 78 > 2 > 2227-2250

In visual tracking task, due to the ubiquitous challenging attributes such as illumination changes, occlusion and target deformation, there hardly exists a tracker that works satisfactorily under various circumstances. To cope with different challenging factors, in this paper, we propose a fusion framework to absorb the strength of different tracking algorithms for robust object tracking. Our approach...

article

A General Framework for Linear Distance Preserving Hashing

Min Wang, Wengang Zhou, Qi Tian, Houqiang Li

IEEE Transactions on Image Processing > 2018 > 27 > 2 > 907 - 922

Binary hashing approaches the approximate nearest neighbor search problem by transferring the data to Hamming space with explicit or implicit distance preserving constraint. With compact data representation, binary hashing identifies the approximate nearest neighbors via very efficient Hamming distance computation. In this paper, we propose a generic hashing framework with a new linear pairwise distance...

article

Block-Composed Background Reference for High Efficiency Video Coding

Fangdong Chen, Houqiang Li, Li Li, Dong Liu, more

IEEE Transactions on Circuits and Systems for Video Technology > 2017 > 27 > 12 > 2639 - 2651

A block-composed background reference method is proposed in this paper for High Efficiency Video Coding (HEVC). For a group of picture (GoP), the first reconstructed picture is served as an initial background reference, which probably includes foreground content. In the subsequent coding, some background coding tree units (CTUs) in every picture are selected to be compressed with high quality. These...

article

Joint Source-Channel Secrecy Using Uncoded Schemes: Towards Secure Source Broadcast

Lei Yu, Houqiang Li, Weiping Li

IEEE Transactions on Information Theory > 2017 > 63 > 11 > 7442 - 7463

This paper investigates a joint source-channel secrecy problem for the Shannon cipher broadcast system. We suppose list secrecy is applied, i.e., a wiretapper is allowed to produce a list of reconstruction sequences and the secrecy is measured by the minimum distortion over the entire list. For discrete communication cases, we propose a permutation-based uncoded scheme, which cascades a random permutation...

article

Local residual similarity for image re-ranking

Shaoyan Sun, Ying Li, Wengang Zhou, Qi Tian, more

Information Sciences > 2017 > 417 > C > 143-153

Similarity measurement is an essential component in image retrieval systems. While previous work is focused on generic distance estimation, this paper investigates the problem of similarity estimation within a local neighborhood defined in the original feature space. Specifically, our method is characterized in two aspects, i.e., “local” and “residual”. First of all, we focus on a subset of the top-ranked...

chapter

CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training

Jianmin Bao, Dong Chen, Fang Wen, Houqiang Li, more

2017 IEEE International Conference on Computer Vision (ICCV) > 2764 - 2773

2017 IEEE International Conference on Computer Vision (ICCV)

We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a specific person or objects in a category. Our approach models an image as a composition of label and latent attributes in a probabilistic model. By varying the fine-grained...

article

Pseudo-Sequence-Based 2-D Hierarchical Coding Structure for Light-Field Image Compression

Li Li, Zhu Li, Bin Li, Dong Liu, more

IEEE Journal of Selected Topics in Signal Processing > 2017 > 11 > 7 > 1107 - 1119

In this paper, we propose a pseudo-sequence-based two-dimensional (2-D) hierarchical coding structure for light-field image compression. In the proposed scheme, we first decompose the light-field image into multiple views and organize them into a 2-D coding structure according to the spatial coordinates of the corresponding microlens. Then, we mainly develop three algorithms to optimize the 2-D coding...

chapter

Video Captioning with Transferred Semantic Attributes

Yingwei Pan, Ting Yao, Houqiang Li, Tao Mei

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 984 - 992

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Automatically generating natural language descriptions of videos plays a fundamental challenge for computer vision community. Most recent progress in this problem has been achieved through employing 2-D and/or 3-D Convolutional Neural Networks (CNNs) to encode video content and Recurrent Neural Networks (RNNs) to decode a sentence. In this paper, we present Long Short-Term Memory with Transferred...

chapter

Co-projection-plane based 3-D padding for polyhedron projection for 360-degree video

Li Li, Zhu Li, Xiang Ma, Haitao Yang, more

2017 IEEE International Conference on Multimedia and Expo (ICME) > 55 - 60

2017 IEEE International Conference on Multimedia and Expo (ICME)

The polyhedron projection for 360-degree video is becoming more and more popular since it can lead to much less geometry distortion compared with the equirectangular projection. However, in the polyhedron projection, we can observe very obvious texture discontinuity in the area near the face boundary. Such a texture discontinuity may lead to serious quality degradation when motion compensation crosses...

chapter

A convolutional neural network approach for half-pel interpolation in video coding

Ning Yan, Dong Liu, Houqiang Li, Feng Wu

2017 IEEE International Symposium on Circuits and Systems (ISCAS) > 1 - 4

2017 IEEE International Symposium on Circuits and Systems (ISCAS)

Motion compensation is a fundamental technology in video coding to remove the temporal redundancy between video frames. To further improve the coding efficiency, sub-pel motion compensation has been utilized, which requires interpolation of fractional samples. The video coding standards usually adopt fixed interpolation filters that are derived from the signal processing theory. However, as video...

chapter

Pseudo Sequence Based 2-D Hierarchical Coding Structure for Light-Field Image Compression

Li Li, Zhu Li, Bin Li, Dong Liu, more

2017 Data Compression Conference (DCC) > 131 - 140

2017 Data Compression Conference (DCC)

In this paper, we present a novel pseudo sequence based 2-D hierarchical reference structure for light-field image compression. In the proposed scheme, we first decompose the light-field image into multiple views and organize them into a 2-D coding structure according to the spatial coordinates of the corresponding microlens. Then we mainly develop three technologies to optimize the 2-D coding structure...

article

Source-Channel Secrecy for Shannon Cipher System

Lei Yu, Houqiang Li, Weiping Li

IEEE Transactions on Information Theory > 2017 > 63 > 4 > 2596 - 2622

Recently, a secrecy measure based on list-reconstruction has been proposed, in which a wiretapper is allowed to produce a list of

$2^{mR_{L}}$

reconstruction sequences and the secrecy is measured by the minimum distortion over the entire list. In this paper, we show that this list secrecy problem is equivalent to the one with secrecy measured by a new quantity lossy equivocation, which is proved...

article

Video restoration based on a novel second order nonlocal total variation model

Zhenbo Lu, Qing Ling, Houqiang Li, Weiping Li

Signal Processing > 2017 > 133 > C > 79-96

Total variation and its variants have been widely used in the video/image restoration area in the past decades. Among them, the nonlocal total variation model introduces penalization on nonlocal gradients and demonstrates remarkable performance gain in many applications. However, this approach tends to suppress intensity-changes of visual contents, and hence cannot restore complicated visual contents...

article

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Dong Liu, Dandan Wang, Houqiang Li

Sensing and Imaging > 2017 > 18 > 1 > 1-20

Traditionally, image compression was optimized for the pixel-wise fidelity or the perceptual quality of the compressed images given a bit-rate budget. But recently, compressed images are more and more utilized for automatic semantic analysis tasks such as recognition and retrieval. For these tasks, we argue that the optimization target of compression is no longer perceptual quality, but the utility...

article

Subpixel Image Quality Assessment Syncretizing Local Subpixel and Global Pixel Features

Jin Zeng, Lu Fang, Jiahao Pang, Houqiang Li, more

IEEE Transactions on Image Processing > 2016 > 25 > 12 > 5841 - 5856

The subpixel rendering technology increases the apparent resolution of an LCD/OLED screen by exploiting the physical property that a pixel is composed of RGB individually addressable subpixels. Due to the intrinsic intercoordination between apparent luminance resolution and color fringing artifact, a common method of subpixel image assessment is subjective evaluation. In this paper, we propose a unified...

article

Similar Reference Image Quality Assessment: A New Database and A Trial with Local Feature Matching

Qingbo Lu, Wengang Zhou, Houqiang Li

Sensing and Imaging > 2016 > 17 > 1 > 1-20

Conventionally, the reference image for image quality assessment (IQA) is completely available (full-reference IQA) or unavailable (no-reference IQA). Even for reduced-reference IQA, the features that are used to predict image quality are still extracted from the pristine reference image. However, the pristine reference image is always unavailable in many real scenarios. In contrast, it is convenient...

article

A no-reference Image sharpness metric based on structural information using sparse representation

Qingbo Lu, Wengang Zhou, Houqiang Li

Information Sciences > 2016 > 369 > C > 334-346

As a ubiquitous image distortion, blur casts non-trivial influence on image visual quality. Many image sharpness assessment methods have been proposed in the views of edge information, gradient map, frequency spectrum, or other natural image statistics features. In this paper, we propose a no-reference image sharpness metric based on structural information using sparse representation (SR). We observe...

chapter

No-reference image quality assessment based on global and local content perception

Cuirong Sun, Houqiang Li, Weiping Li

2016 Visual Communications and Image Processing (VCIP) > 1 - 4

2016 Visual Communications and Image Processing (VCIP)

Existing no-reference image quality assessment (NR-IQA) methods mainly focus on designing the low-level features related to image degradation. However, the evaluation of image quality is the human visual perception of image content, involving the integrated analysis of global high-level semantics and local low-level characteristics. From this perspective, we propose a NR-IQA framework based on global...

INFONA - science communication portal

Search results for: Houqiang Li

Exploiting weak mask representation with convolutional neural networks for accurate object tracking

Scene text detection with fully convolutional neural networks

Multi-tracker fusion via adaptive outlier detection

A General Framework for Linear Distance Preserving Hashing

Block-Composed Background Reference for High Efficiency Video Coding

Joint Source-Channel Secrecy Using Uncoded Schemes: Towards Secure Source Broadcast

Local residual similarity for image re-ranking

CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training

Pseudo-Sequence-Based 2-D Hierarchical Coding Structure for Light-Field Image Compression

Video Captioning with Transferred Semantic Attributes

Co-projection-plane based 3-D padding for polyhedron projection for 360-degree video

A convolutional neural network approach for half-pel interpolation in video coding

Pseudo Sequence Based 2-D Hierarchical Coding Structure for Light-Field Image Compression

Source-Channel Secrecy for Shannon Cipher System

Video restoration based on a novel second order nonlocal total variation model

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Subpixel Image Quality Assessment Syncretizing Local Subpixel and Global Pixel Features

Similar Reference Image Quality Assessment: A New Database and A Trial with Local Feature Matching

A no-reference Image sharpness metric based on structural information using sparse representation

No-reference image quality assessment based on global and local content perception

Filter options

Publication date

Content availability

Publication type

Keywords

Data set

Journal

INFONA - science communication portal

Search results for: Houqiang Li

Add recipient

Sending message cancelled

Are you sure you want to cancel sending this message?

Send message

Filter options

Publication date

Date range setting

Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.

Content availability

Publication type

Keywords

Data set

Journal

Reporting an error / abuse

Sending the report failed

Accessibility options