Search For:

Displaying 1-44 out of 44 total
Online Robust Non-negative Dictionary Learning for Visual Tracking
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Naiyan Wang,Jingdong Wang,Dit-Yan Yeung
Issue Date:December 2013
pp. 657-664
This paper studies the visual tracking problem in video sequences and presents a novel robust sparse tracker under the particle filter framework. In particular, we propose an online robust non-negative dictionary learning algorithm for updating the object ...
 
Learning CRFs for Image Parsing with Adaptive Subgradient Descent
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Honghui Zhang,Jingdong Wang,Ping Tan,Jinglu Wang,Long Quan
Issue Date:December 2013
pp. 3080-3087
We propose an adaptive sub gradient descent method to efficiently learn the parameters of CRF models for image parsing. To balance the learning efficiency and performance of the learned CRF models, the parameter learning is iteratively carried out by solvi...
 
Fast approximate k-means via cluster closures
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Jing Wang, Jingdong Wang, Qifa Ke, Gang Zeng, Shipeng Li
Issue Date:June 2012
pp. 3037-3044
K-means, a simple and effective clustering algorithm, is one of the most widely used algorithms in computer vision community. Traditional k-means is an iterative algorithm - in each iteration new cluster centers are computed and each data point is re-assig...
 
Scalable k-NN graph construction for visual descriptors
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Jing Wang, Jingdong Wang, Gang Zeng, Zhuowen Tu, Rui Gan, Shipeng Li
Issue Date:June 2012
pp. 1106-1113
The k-NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to construct k-NN graphs remains a challenge, especially for large-scale high-dimensi...
 
Structure-sensitive superpixels via geodesic distance
Found in: Computer Vision, IEEE International Conference on
By Gang Zeng, Peng Wang,Jingdong Wang, Rui Gan, Hongbin Zha
Issue Date:November 2011
pp. 447-454
Over-segments (i.e. superpixels) have been commonly used as supporting regions for feature vectors and primitives to reduce computational complexity in various image analysis tasks. In this paper, we describe a structuresensitive over-segmentation techniqu...
 
Joint multi-label multi-instance learning for image classification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Zheng-Jun Zha, Xian-Sheng Hua, Tao Mei, Jingdong Wang, Guo-Jun Qi, Zengfu Wang
Issue Date:June 2008
pp. 1-8
In real world, an image is usually associated with multiple labels which are characterized by different regions in the image. Thus image classification is naturally posed as both a multi-label learning and multi-instance learning problem. Different from ex...
 
Semi-Supervised Classification Using Linear Neighborhood Propagation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Fei Wang, Changshui Zhang, Helen C. Shen, Jingdong Wang
Issue Date:June 2006
pp. 160-167
In this paper, we address the general problem of learning from both labeled and unlabeled data. Based on the reasonable assumption that the label of each data can be linearly reconstructed from its neighbors? labels, we develop a novel approach, called Lin...
 
Image search results refinement via outlier detection using deep contexts
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Junyang Lu, Jiazhen Zhou, Jingdong Wang, Tao Mei, Xian-Sheng Hua, Shipeng Li
Issue Date:June 2012
pp. 3029-3036
Visual reranking has become a widely-accepted method to improve traditional text-based image search results. The main principle is to exploit the visual aggregation property of relevant images among top results so as to boost ranking scores of relevant ima...
 
Multi-task low-rank affinity pursuit for image segmentation
Found in: Computer Vision, IEEE International Conference on
By Bin Cheng,Guangcan Liu,Jingdong Wang, Zhongyang Huang,Shuicheng Yan
Issue Date:November 2011
pp. 2439-2446
This paper investigates how to boost region-based image segmentation by pursuing a new solution to fuse multiple types of image features. A collaborative image segmentation framework, called multi-task low-rank affinity pursuit, is presented for such a pur...
 
Complementary hashing for approximate nearest neighbor search
Found in: Computer Vision, IEEE International Conference on
By Hao Xu,Jingdong Wang, Zhu Li,Gang Zeng, Shipeng Li, Nenghai Yu
Issue Date:November 2011
pp. 1631-1638
Recently, hashing based Approximate Nearest Neighbor (ANN) techniques have been attracting lots of attention in computer vision. The data-dependent hashing methods, e.g., Spectral Hashing, expects better performance than the data-blind counterparts, e.g., ...
 
A non-convex relaxation approach to sparse dictionary learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jianping Shi, Xiang Ren, Guang Dai, Jingdong Wang, Zhihua Zhang
Issue Date:June 2011
pp. 1809-1816
Dictionary learning is a challenging theme in computer vision. The basic goal is to learn a sparse representation from an overcomplete basis set. Most existing approaches employ a convex relaxation scheme to tackle this challenge due to the strong ability ...
 
Learning to combine multi-resolution spatially-weighted co-occurrence matrices for image representation
Found in: Multimedia and Expo, IEEE International Conference on
By Xiangang Cheng, Jingdong Wang, Liang-Tien Chia, Xian-Sheng Hua
Issue Date:July 2010
pp. 631-636
Bag-of-Words is widely used to describe images for image classification. However, this approach is limited because the spatial relation over visual words is not well exploited and also it is difficult to generate a single comprehensive vocabulary. In this ...
 
Optimizing kd-trees for scalable visual descriptor indexing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By You Jia, Jingdong Wang, Gang Zeng, Hongbin Zha, Xian-Sheng Hua
Issue Date:June 2010
pp. 3392-3399
In this paper, we attempt to scale up the kd-tree indexing methods for large-scale vision applications, e.g., indexing a large number of SIFT features and other types of visual descriptors. To this end, we propose an effective approach to generate near-opt...
 
Learning to Detect a Salient Object
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Tie Liu, Zejian Yuan, Jian Sun, Jingdong Wang, Nanning Zheng, Xiaoou Tang, Heung-Yeung Shum
Issue Date:February 2011
pp. 353-367
In this paper, we study the salient object detection problem for images. We formulate this problem as a binary labeling task where we separate the salient object from the background. We propose a set of novel features, including multiscale contrast, center...
 
Maximum Margin Clustering with Pairwise Constraints
Found in: Data Mining, IEEE International Conference on
By Yang Hu, Jingdong Wang, Nenghai Yu, Xian-Sheng Hua
Issue Date:December 2008
pp. 253-262
Maximum margin clustering (MMC), which extends the theory of support vector machine to unsupervised learning, has been attracting considerable attention recently. The existing approaches mainly focus on reducing the computational complexity of MMC. The acc...
 
Normalized tree partitioning for image segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jingdong Wang, Yangqing Jia, Xian-Sheng Hua, Changshui Zhang, Long Quan
Issue Date:June 2008
pp. 1-8
In this paper, we propose a novel graph based clustering approach with satisfactory clustering performance and low computational cost. It consists of two main steps: tree fitting and partitioning. We first introduce a probabilistic method to fit a tree to ...
 
Joint Affinity Propagation for Multiple View Segmentation
Found in: Computer Vision, IEEE International Conference on
By Jianxiong Xiao, Jingdong Wang, Ping Tan, Long Quan
Issue Date:October 2007
pp. 1-7
A joint segmentation is a simultaneous segmentation of registered 2D images and 3D points reconstructed from the multiple view images. It is fundamental in structuring the data for subsequent modeling applications. In this paper, we treat this joint segmen...
 
Picture Collage
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jingdong Wang, Long Quan, Jian Sun, Xiaoou Tang, Heung-Yeung Shum
Issue Date:June 2006
pp. 347-354
In this paper, we address a novel problem of automatically creating a picture collage from a group of images. Picture collage is a kind of visual image summary - to arrange all input images on a given canvas, allowing overlay, to maximize visible visual in...
 
Optimized Cartesian K-Means
Found in: IEEE Transactions on Knowledge and Data Engineering
By Jianfeng Wang,Jingdong Wang,Jingkuan Song,Xin-Shun Xu,Heng Tao Shen,Shipeng Li
Issue Date:May 2014
pp. 1
Product quantization-based approaches are effective to encode high-dimensional data points for approximate nearest neighbor search. The space is decomposed into a Cartesian product of low-dimensional subspaces, each of which generates a sub codebook. Data ...
 
Trinary-Projection Trees for Approximate Nearest Neighbor Search
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jingdong Wang, Naiyan Wang, You Jia, Jian Li, Gang Zeng, Hongbin Zha, Xian-Sheng Hua
Issue Date:February 2014
pp. 388-403
We address the problem of approximate nearest neighbor (ANN) search for visual descriptor indexing. Most spatial partition trees, such as KD trees, VP trees, and so on, follow the hierarchical binary space partitioning framework. The key effort is to desig...
 
Fast Neighborhood Graph Search Using Cartesian Concatenation
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jing Wang,Jingdong Wang,Gang Zeng,Rui Gan,Shipeng Li,Baining Guo
Issue Date:December 2013
pp. 2128-2135
In this paper, we propose a new data structure for approximate nearest neighbor search. This structure augments the neighborhood graph with a bridge graph. We propose to exploit Cartesian concatenation to produce a large set of vectors, called bridge vecto...
 
Supervised Kernel Descriptors for Visual Recognition
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Peng Wang,Jingdong Wang,Gang Zeng,Weiwei Xu,Hongbin Zha,Shipeng Li
Issue Date:June 2013
pp. 2858-2865
In visual recognition tasks, the design of low level image feature representation is fundamental. The advent of local patch features from pixel attributes such as SIFT and LBP, has precipitated dramatic progresses. Recently, a kernel view of these features...
 
Salient object detection for searched web images via global saliency
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Peng Wang, Jingdong Wang, Gang Zeng, Jie Feng, Hongbin Zha, Shipeng Li
Issue Date:June 2012
pp. 3194-3201
In this paper, we deal with the problem of detecting the existence and the location of salient objects for thumbnail images on which most search engines usually perform visual analysis in order to handle web-scale images. Different from previous techniques...
 
Salient Object Detection: A Discriminative Regional Feature Integration Approach
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Huaizu Jiang,Jingdong Wang,Zejian Yuan,Yang Wu,Nanning Zheng,Shipeng Li
Issue Date:June 2013
pp. 2083-2090
Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. In this paper, we regard saliency map computation as a regression problem. Our method, which is based on multi-level ima...
 
Clickage: towards bridging semantic and intent gaps via mining click logs of search engines
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Jin Li, Jing Wang, Jingdong Wang, Kuansan Wang, Linjun Yang, Ming Ye, Xian-Sheng Hua, Yong Rui
Issue Date:October 2013
pp. 243-252
The semantic gap between low-level visual features and high-level semantics has been investigated for decades but still remains a big challenge in multimedia. When "search" became one of the most frequently used applications, "intent gap", the gap between ...
     
Order preserving hashing for approximate nearest neighbor search
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Jianfeng Wang, Shipeng Li, Jingdong Wang, Nenghai Yu
Issue Date:October 2013
pp. 133-142
In this paper, we propose a novel method to learn similarity-preserving hash functions for approximate nearest neighbor (NN) search. The key idea is to learn hash functions by maximizing the alignment between the similarity orders computed from the origina...
     
Contextual image search
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Jingdong Wang, Shengjin Wang, Shipeng Li, Wenhao Lu, Xian-Sheng Hua
Issue Date:November 2011
pp. 513-522
In this paper, we propose a novel image search scheme, contextual image search. Different from conventional image search schemes that present a separate interface (e.g., text input box) to allow users to submit a query, the new search scheme enables users ...
     
JIGSAW: interactive mobile visual search with multimodal queries
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Houqiang Li, Jingdong Wang, Shipeng Li, Tao Mei, Yang Wang
Issue Date:November 2011
pp. 73-82
The traditional text-based visual search has not been sufficiently improved over the years to accommodate the new emerging demand of mobile users. While on the go, searching on one's phone is becoming pervasive. This paper presents an innovative applicatio...
     
Image search by graph-based label propagation with image representation from DNN
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Chong-Wah Ngo, Houqiang Li, Jingdong Wang, Yingwei Pan, Kuiyuan Yang, Tao Mei, Ting Yao
Issue Date:October 2013
pp. 397-400
Our objective is to estimate the relevance of an image to a query for image search purposes. We address two limitations of the existing image search engines in this paper. First, there is no straightforward way of bridging the gap between semantic textual ...
     
An interactive approach to semantic modeling of indoor scenes with an RGBD camera
Found in: ACM Transactions on Graphics (TOG)
By Baining Guo, Dongping Li, Jingdong Wang, Kun Zhou, Tianjia Shao, Weiwei Xu
Issue Date:November 2012
pp. 1-11
We present an interactive approach to semantic modeling of indoor scenes with a consumer-level RGBD camera. Using our approach, the user first takes an RGBD image of an indoor scene, which is automatically segmented into a set of regions with semantic labe...
     
Web-scale image search by color sketch
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Jingdong Wang, Xian-Sheng Hua
Issue Date:November 2011
pp. 751-752
Most existing image search engines rely on the associated texts or tags with images to index and retrieval images, which results in limited ability on searching images with visual requirement. In this demonstration, we present an image search system, which...
     
Robust visual reranking via sparsity and ranking constraints
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Jingdong Wang, Nobuyuki Morioka
Issue Date:November 2011
pp. 533-542
Visual reranking has become a widely-accepted method to improve traditional text-based image search engines. Its basic principle is that visually similar images should have similar ranking scores. While existing methods are different in specifics, almost a...
     
Hybrid image summarization
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Hao Xu, Jingdong Wang, Shipeng Li, Xian-Sheng Hua
Issue Date:November 2011
pp. 1217-1220
In this paper, we address a problem of managing tagged images with hybrid summarization. We formulate this problem as finding a few image exemplars to represent the image set semantically and visually and solve it in a hybrid way by exploiting both visual ...
     
Interactive Image Search by Color Map
Found in: ACM Transactions on Intelligent Systems and Technology (TIST)
By Jingdong Wang, Xian-Sheng Hua
Issue Date:October 2011
pp. 1-23
The availability of large-scale images from the Internet has made the research on image search attract a lot of attention. Text-based image search engines, for example, Google/Microsoft Bing/Yahoo! image search engines using the surrounding text, have been...
     
Document clustering with universum
Found in: Proceedings of the 34th international ACM SIGIR conference on Research and development in Information (SIGIR '11)
By Dan Zhang, Jingdong Wang, Luo Si
Issue Date:July 2011
pp. 873-882
Document clustering is a popular research topic, which aims to partition documents into groups of similar objects (i.e., clusters), and has been widely used in many applications such as automatic topic extraction, document organization and filtering. As a ...
     
Image search by concept map
Found in: Proceeding of the 33rd international ACM SIGIR conference on Research and development in information retrieval (SIGIR '10)
By Hao Xu, Jingdong Wang, Shipeng Li, Xian-Sheng Hua
Issue Date:July 2010
pp. 275-282
In this paper, we present a novel image search system, image search by concept map. This system enables users to indicate not only what semantic concepts are expected to appear but also how these concepts are spatially distributed in the desired images. To...
     
Tag refinement by regularized LDA
Found in: Proceedings of the seventeen ACM international conference on Multimedia (MM '09)
By Hao Xu, Jingdong Wang, Shipeng Li, Xian-Sheng Hua
Issue Date:October 2009
pp. 573-576
Tagging is nowadays the most prevalent and practical way to make images searchable. However, in reality many tags are irrelevant to image content. To refine the tags, previous solutions usually mine tag relevance relying on the tag similarity estimated rig...
     
Transductive multi-label learning for video concept detection
Found in: Proceeding of the 1st ACM international conference on Multimedia information retrieval (MIR '08)
By Jingdong Wang, Xian-Sheng Hua, Xiuqing Wu, Yinghai Zhao
Issue Date:October 2008
pp. 1-1
Transductive video concept detection is an effective way to handle the lack of sufficient labeled videos. However, another issue, the multi-label interdependence, is not essentially addressed in the existing transductive methods. Most solutions only applie...
     
Finding image exemplars using fast sparse affinity propagation
Found in: Proceeding of the 16th ACM international conference on Multimedia (MM '08)
By Changshui Zhang, Jingdong Wang, Xian-Sheng Hua, Yangqing Jia
Issue Date:October 2008
pp. 40-42
In this paper, we propose a novel approach to organize image search results obtained from state-of-the-art image search engines in order to improve user experience. We aim to discover exemplars from search results and simultaneously group the images. The e...
     
Bayesian video search reranking
Found in: Proceeding of the 16th ACM international conference on Multimedia (MM '08)
By Jingdong Wang, Linjun Yang, Xian-Sheng Hua, Xinmei Tian, Xiuqing Wu, Yichen Yang
Issue Date:October 2008
pp. 40-42
Content-based video search reranking can be regarded as a process that uses visual content to recover the "true" ranking list from the noisy one generated based on textual information. This paper explicitly formulates this problem in the Bayesian framework...
     
Image-based tree modeling
Found in: ACM Transactions on Graphics (TOG)
By Gang Zeng, Jingdong Wang, Long Quan, Ping Tan, Sing Bing Kang
Issue Date:July 2007
pp. 1-35
In this paper, we propose an approach for generating 3D models of natural-looking trees from images that has the additional benefit of requiring little user intervention. While our approach is primarily image-based, we do not model each leaf directly from ...
     
Image-based plant modeling: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: ACM SIGGRAPH 2006 Papers (SIGGRAPH '06)
By Gang Zeng, Jingdong Wang, Long Quan, Lu Yuan, Ping Tan, Sing Bing Kang
Issue Date:July 2006
pp. 14-es
In this paper, we propose a semi-automatic technique for modeling plants directly from images. Our image-based approach has the distinct advantage that the resulting model inherits the realistic shape and complexity of a real plant. We designed our modelin...
     
Image-based plant modeling: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: Material presented at the ACM SIGGRAPH 2006 conference (SIGGRAPH '06)
By Gang Zeng, Jingdong Wang, Long Quan, Lu Yuan, Ping Tan, Sing Bing Kang
Issue Date:July 2006
pp. 14-es
In this paper, we propose a semi-automatic technique for modeling plants directly from images. Our image-based approach has the distinct advantage that the resulting model inherits the realistic shape and complexity of a real plant. We designed our modelin...
     
Probabilistic tangent subspace: a unified view
Found in: Twenty-first international conference on Machine learning (ICML '04)
By Changshui Zhang, Jianguo Lee, Jingdong Wang, Zhaoqi Bian
Issue Date:July 2004
pp. 182-182
Tangent Distance (TD) is one classical method for invariant pattern classification. However, conventional TD need pre-obtain tangent vectors, which is difficult except for image objects. This paper extends TD to more general pattern classification tasks. T...
     
 1