期刊：
Journal of Computational and Applied Mathematics,2018年329:57-67 ISSN：0377-0427
通讯作者：
Zhang, Jie
作者机构：
[Liu, Xiuping; Li, Yujiao; Cao, Junjie; Chen, He] Dalian Univ Technol, Sch Math Sci, Dalian, Peoples R China.;[Cao, Junjie] Nanchang Hangkong Univ, Coll Math & Informat Sci, Nanchang, Jiangxi, Peoples R China.;[Zhang, Jie] Liaoning Normal Univ, Sch Math, Dalian, Peoples R China.;[Zou, Changqing] Hengyang Normal Univ, Hengyang, Hunan, Peoples R China.
通讯机构：
[Zhang, Jie] L;Liaoning Normal Univ, Sch Math, Dalian, Peoples R China.
会议名称：
International Conference on Information and Computational Science (ICICS)
会议时间：
AUG 02-06, 2016
会议地点：
Dalian Univ Technol, Dalian, PAKISTAN
会议主办单位：
Dalian Univ Technol
关键词：
Normal estimation;Point cloud;Neighborhood shift
摘要：
For accurately estimating the normal of a point, the structure of its neighborhood has to be analyzed. All the previous methods use some neighborhood centering at the point, which is prone to be sampled from different surface patches when the point is near sharp features. Then more inaccurate normals or higher computation cost may be unavoidable. To conquer this problem, we present a fast and quality normal estimator based on neighborhood shift. Instead of using the neighborhood centered at the point, we wish to locate a neighborhood containing the point but clear of sharp features, which is usually not centering at the point. Two specific neighborhood shift techniques are designed in view of the complex structure of sharp features and the characteristic of raw point clouds. The experiments show that our method out-performs previous normal estimators in either quality or running time, even in the presence of noise and anisotropic sampling. (C) 2017 Elsevier B.V. All rights reserved.
摘要：
This paper presents a multi-modal feature fusion based framework to improve the geographic image annotation. To achieve effective representations of geographic images, the method leverages a low-to-high learning flow for both the deep and shallow modality features. It first extracts low-level features for each input image pixel, such as shallow modality features (SIFT, Color, and LBP) and deep modality features (CNNs). It then constructs mid-level features for each superpixel from low-level features. Finally it harvests high-level features from mid-level features by using deep belief networks (DBN). It uses a restricted Boltzmann machine (RBM) to mine deep correlations between high-level features from both shallow and deep modalities to achieve a final representation for geographic images. Comprehensive experiments show that this feature fusion based method achieves much better performances compared to traditional methods. (C) 2017 Published by Elsevier Ltd.
作者机构：
[Wan, Lili] Beijing Jiaotong Univ, Inst Informat Sci, Beijing, Peoples R China.;[Zou, Changqing] Hengyang Normal Univ, Hengyang, Peoples R China.;[Zou, Changqing; Zhang, Hao] Simon Fraser Univ, Burnaby, BC, Canada.
通讯机构：
[Wan, Lili] B;[Zou, Changqing] H;[Zou, Changqing] S;Beijing Jiaotong Univ, Inst Informat Sci, Beijing, Peoples R China.;Hengyang Normal Univ, Hengyang, Peoples R China.
关键词：
Full and partial shape similarity;Incomplete shapes;Shape retrieval;Sparse dictionary learning;Sparse reconstruction
摘要：
We introduce a novel approach to measuring similarity between two shapes based on sparse reconstruction of shape descriptors. The main feature of our approach is its applicability in situations where either of the two shapes may have moderate to significant portions of its data missing. Let the two shapes be A and B. Without loss of generality, we characterize A by learning a sparse dictionary from its local descriptors. The similarity between A and B is defined by the error incurred when reconstructing B's descriptor set using the basis signals from A's dictionary. Benefits of using sparse dictionary learning and reconstruction are twofold. First, sparse dictionary learning reduces data redundancy and facilitates similarity computations. More importantly, the reconstruction error is expected to be small as long as B is similar to A, regardless of whether the similarity is full or partial. Our proposed approach achieves significant improvements over previous works when retrieving non-rigid shapes with missing data, and it is also comparable to state-of-the-art methods on the retrieval of complete non-rigid shapes. We introduce a novel approach to measuring similarity between two shapes based on sparse reconstruction of shape descriptors. The main feature of our approach is its applicability in situations where either of the two shapes may have moderate to significant portions of its data missing. Let the two shapes be A and B. Without loss of generality, we characterize A by learning a sparse dictionary from its local descriptors. The similarity between A and B is defined by the error incurred when reconstructing B's descriptor set using the basis signals from A's dictionary. Benefits of using sparse dictionary learning and reconstruction are twofold. First, sparse dictionary learning reduces data redundancy and facilitates similarity computations. More importantly, the reconstruction error is expected to be small as long as B is similar to A, regardless of whether the similarity is full or partial. Our proposed approach achieves significant improvements over previous works when retrieving non-rigid shapes with missing data, and it is also comparable to state-of-the-art methods on the retrieval of complete non-rigid shapes.
作者机构：
[Wang, Dong] South China Agr Univ, Coll Math & Informat, Guangzhou, Guangdong, Peoples R China.;[Zou, Changqing] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.;[Tan, Ping; Zou, Changqing] Simon Fraser Univ, Sch Comp Sci, Burnaby, BC, Canada.;[Li, Guiqing] South China Univ Technol, Sch Comp Sci & Engn, Guangzhou, Guangdong, Peoples R China.;[Su, Zhuo; Gao, Chengying] Sun Yat Sen Univ, Natl Engn Res Ctr Digital Life, Sch Data & Comp Sci, Guangzhou, Guangdong, Peoples R China.
会议名称：
25th Pacific Conference on Computer Graphics and Applications (Pacific Graphics)
会议时间：
OCT 16-19, 2017
会议地点：
Taipei, TAIWAN
会议主办单位：
[Wang, Dong] South China Agr Univ, Coll Math & Informat, Guangzhou, Guangdong, Peoples R China.^[Zou, Changqing] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.^[Zou, Changqing;Tan, Ping] Simon Fraser Univ, Sch Comp Sci, Burnaby, BC, Canada.^[Li, Guiqing] South China Univ Technol, Sch Comp Sci & Engn, Guangzhou, Guangdong, Peoples R China.^[Gao, Chengying;Su, Zhuo] Sun Yat Sen Univ, Natl Engn Res Ctr Digital Life, Sch Data & Comp Sci, Guangzhou, Guangdong, Peoples R China.
摘要：
This paper presents a new two-step color transfer method which includes color mapping and detail preservation. To map source colors to target colors, which are from an image or palette, the proposed similarity-preserving color mapping algorithm uses the similarities between pixel color and dominant colors as existing algorithms and emphasizes the similarities between source image pixel colors. Detail preservation is performed by an L0 gradient-preserving algorithm. It relaxes the large gradients of the sparse pixels along color region boundaries and preserves the small gradients of pixels within color regions. The proposed method preserves source image color similarity and image details well. Extensive experiments demonstrate that the proposed approach has achieved a state-of-art visual performance.
摘要：
We propose a mesh saliency detection approach using absorbing Markov chain. Unlike most of the existing methods based on some center-surround operator, our method employs feature variance to obtain insignificant regions and considers both background and foreground cues. Firstly, we partition an input mesh into a set of segments using Ncuts algorithm and then each segment is over segmented into patches based on Zernike coefficients. Afterwards, some background patches are selected by computing feature variance within the segments. Secondly, the absorbed time of each node is calculated via absorbing Markov chain with the background patches as absorbing nodes, which gives a preliminary saliency measure. Thirdly, a refined saliency result is generated in a similar way but with foreground nodes extracted from the preliminary saliency map as absorbing nodes, which inhibits the background and efficiently enhances salient foreground regions. Finally, a Laplacian-based smoothing procedure is utilized to spread the patch saliency to each vertex. Experimental results demonstrate that our scheme performs competitively against the state-of-the-art approaches.
作者：
Lei Li;Zhe Huang;Changqing Zou;Chiew-Lan Tai;Rynson W. H. Lau;...
期刊：
,2016年:1–4
作者机构：
[Lei Li; Chiew-Lan Tai] Hong Kong UST;[Changqing Zou] Simon Fraser University and Hengyang Normal University;[Zhe Huang; Rynson W. H. Lau; Hongbo Fu] City University of Hong Kong;[Hao Zhang; Ping Tan] Simon Fraser University
关键词：
3D sketch;mesh deformation;sketch interpretation;sketch-based shape retrieval;structure matching;user interface
摘要：
We propose an interactive system that aims at lifting a 2D sketch into a 3D sketch with the help of existing models in shape collections. The key idea is to exploit part structure for shape retrieval and sketch reconstruction. We adopt sketch-based shape retrieval and develop a novel matching algorithm which considers structure in addition to traditional shape features. From a list of retrieved models, users select one to serve as a 3D proxy, providing abstract 3D information. Then our reconstruction method transforms the sketch into 3D geometry by back-projection, followed by an optimization procedure based on the Laplacian mesh deformation framework. Preliminary evaluations show that our retrieval algorithm is more effective than a state-of-the-art method and users can create interesting 3D forms of sketches without precise drawing skills.
摘要：
In this paper, we focus on the problem of similarity assessment of isometric 3D shapes, which is of great relevance in improving the effectiveness of retrieval tasks. We first present an effective shape representation technique by proposing a partial aggregation model based on the bag-of-words paradigm. This technique can effectively encode our multiscale local features and has a good discriminatory ability. We then develop a parameter-free distance mapping approach to re-evaluate the similarity results based on intrinsic analysis of a well organized reciprocal k-nearest neighborhood graph. Different from the existing methods which determine k manually and globally, the proposed method can automatically adjust k to a reliable local domain, which therefore ensures a more accurate similarity measurement. We fully study our shape representation technique and evaluate the performance of the proposed distance mapping approach on several popular public shape benchmarks. Experiment results have demonstrated the state-of-the-art performance of our approach. (C) 2016 Elsevier B.V. Allrightsreserved.
期刊：
IEEE Transactions on Visualization and Computer Graphics,2015年21(2):252-263 ISSN：1077-2626
通讯作者：
Zou, Changqing
作者机构：
[Zou, Changqing] Hengyang Normal Univ, Dept Phys & Elect Informat Sci, Hengyang, Peoples R China.;[Chen, Shifeng; Zou, Changqing] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China.;[Fu, Hongbo] City Univ Hong Kong, Sch Creat Media, Hong Kong, Hong Kong, Peoples R China.;[Liu, Jianzhuang] Huawei Technol Co Ltd, Media Lab, Shenzhen, Peoples R China.;[Liu, Jianzhuang] Chinese Univ Hong Kong, Dept Informat Engn, Hong Kong, Hong Kong, Peoples R China.
通讯机构：
[Zou, Changqing] H;Hengyang Normal Univ, Dept Phys & Elect Informat Sci, Hengyang, Peoples R China.
关键词：
3D reconstruction;degree of reconstruction freedom;decomposition;line drawing;optimization-based
摘要：
This paper presents an approach for reconstructing polyhedral objects from single-view line drawings. Our approach separates a complex line drawing representing a manifold object into a series of simpler line drawings, based on the degree of reconstruction freedom (DRF). We then progressively reconstruct a complete 3D model from these simpler line drawings. Our experiments show that our decomposition algorithm is able to handle complex drawings which are challenging for the state of the art. The advantages of the presented progressive 3D reconstruction method over the existing reconstruction methods in terms of both robustness and efficiency are also demonstrated.
作者机构：
[Zou, Changqing; Peng, Xiaojiang] Hengyang Normal Univ, Dept Phys & Elect Informat Sci, Hengyang, Peoples R China.;[Chen, Shifeng; Zou, Changqing; Lv, Hao] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab CVPR, Shenzhen, Peoples R China.;[Zou, Changqing] Univ Chinese Acad Sci, Shenzhen Coll Adv Technol, Beijing, Peoples R China.;[Fu, Hongbo] City Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China.;[Liu, Jianzhuang] Chinese Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China.
摘要：
3-D object modeling from single images has many applications in computer graphics and multimedia. Most previous 3-D modeling methods which directly recover 3-D geometry from single images require user interactions during the whole modeling process. In this paper, we propose a semi-automatic 3-D modeling approach to recover accurate 3-D geometry from a single image of a piecewise planar object with less user interaction. Our approach concentrates on these three aspects: (1) requiring rough sketch input only, (2) accurate modeling for a large class of objects, and (3) automatically recovering the invisible part of an object and providing a complete 3-D model. Experimental results on various objects show that the proposed approach provides a good solution to these three problems. (C) 2014 Elsevier Ltd. All rights reserved.
摘要：
In this study, we propose a regression forests-based cascaded method for face alignment. We build on the cascaded pose regression (CPR) framework and propose to use the regression forest as a primitive regressor. The regression forests are easier to train and naturally handle the over-fitting problem via averaging the outputs of the trees at each stage. We address the fact that the CPR approaches are sensitive to the shape initialisation; in contrast to using a number of blind initialisations and selecting the median values, we propose an intelligent shape initialisation scheme. More specifically, a large number of initialisations are propagated to a few early stages in the cascade, then only a proportion of them are propagated to the remaining cascades according to their convergence measurement. We evaluate the performance of the proposed approach on the challenging face alignment in the wild database and obtain superior or comparable performance with the state-of-the-art, in spite of the fact that we have utilised only the freely available public training images. More importantly, we show that the intelligent initialisation scheme makes the CPR framework more robust to unreliable initialisations that are typically produced by different face detections.
关键词：
3D reconstruction;Line drawing decomposition;Line drawing separation;Split face
摘要：
Reconstructing 3D objects from single line drawings is often desirable in computer vision and graphics applications. If the line drawing of a complex 3D object is decomposed into primitives of simple shape, the object can be easily reconstructed. We propose an effective method to conduct the line drawing separation and turn a complex line drawing into parametric 3D models. This is achieved by recursively separating the line drawing using two types of split faces. Our experiments show that the proposed separation method can generate more basic and simple line drawings, and its combination with the example-based reconstruction can robustly recover wider range of complex parametric 3D objects than previous methods.
摘要：
In this letter, we propose a method for facial landmarks localization in face sketch images. As recent approaches and the corresponding datasets are designed for ordinary face photos, the performance of such models drop significantly when they are applied on face sketch images. We first propose a scheme to synthesize face sketches from face photos based on random-forests edge detection and local face region enhancement. Then we jointly train a Cascaded Pose Regression based method for facial landmarks localization for both face photos and sketches. We build an evaluation dataset, called Face Sketches in the Wild (FSW), with 450 face sketch images collected from the Internet and with the manual annotation of 68 facial landmark locations on each face sketch. The proposed multi-modality facial landmark localization method shows competitive performance on both face sketch images (the FSW dataset) and face photo images (the Labeled Face Parts in the Wild dataset), despite the fact that we do not use extra annotation of face sketches for model building.
期刊：
Proceedings - International Conference on Pattern Recognition,2014年:4570-4575 ISSN：1051-4651
通讯作者：
Wen, Yafei
作者机构：
[Chen, Shifeng; Wen, Yafei; Zou, Changqing; Liu, Jianzhuang] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Comp Vis & Pat Rec, Shenzhen, Peoples R China.;[Du, Shuze] Chinese Acad Sci, Chengdu Inst Comp Applicat, Chengdu, Peoples R China.;[Du, Shuze; Wen, Yafei; Zou, Changqing] Univ Chinese Acad Sci, Beijing, Peoples R China.;[Zou, Changqing] Hengyang Normal Univ, Dept Phys & Elect Informat Sci, Hengyang, Peoples R China.;[Chen, Shifeng; Wen, Yafei; Zou, Changqing; Liu, Jianzhuang] Chinese Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China.
通讯机构：
[Wen, Yafei] C;Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Comp Vis & Pat Rec, Shenzhen, Peoples R China.
会议名称：
2014 22nd International Conference on Pattern Recognition (ICPR)
关键词：
3D model retrieval;bag-of-features;feature fusion;shape descriptor
摘要：
Sketch-based 3D model retrieval provides a convenient way for users to search for 3D models by sketches. Traditionally, this task is converted to a sketch-based 2D shape retrieval problem by projecting 3D models to 2D images. Local invariant features have been widely used to tackle this problem. However, it suffers from the lack of global context and easily fails when images of different 3D models share multiple similar regions. In this paper, we propose a joint description by fusing local statistical structures and global spatial features. Our description is invariant to scale, translate and rotation. An improved bag-of-features retrieval framework is applied to explore semantic visual word representations. Besides, a novel relevance feedback scheme which combines weight balancing and query modification is designed to further improve the retrieval performance. We conduct various experiments on the common sketch-based watertight model benchmark. The comparative results show that our approach significantly outperforms three state-of-the-art methods, demonstrating its effectiveness and robustness for sketch-based 3D model retrieval.
关键词：
3D model retrieval;junction-based local feature;query-to-model distance;viewpoint-aware representation
摘要：
We study the problem of sketch-based 3D model retrieval, and propose a solution powered by a new query-to-model distance metric and a powerful feature descriptor based on the bag-of-features framework. The main idea of the proposed query-to-model distance metric is to represent a query sketch using a compact set of sample views (called basic views) of each model, and to rank the models in ascending order of the representation errors. To better differentiate between relevant and irrelevant models, the representation is constrained to be essentially a combination of basic views with similar viewpoints. In another aspect, we propose a mid-level descriptor (called BOF-JESC) which robustly characterizes the edge information within junction-centered patches, to extract the salient shape features from sketches or model views. The combination of the query-to-model distance metric and the BOF-JESC descriptor achieves effective results on two latest benchmark datasets.
