Huchuan Lu

article

Online visual tracking via cross‐similarity‐based siamese network

Luyao Wang, Huchuan Lu, Pingping Zhang

Concurrency and Computation: Practice and Experience > 33 > 15 > n/a - n/a

Among deep‐learning‐based trackers, the siamese‐based method inspires many researchers due to its effectiveness and simplicity. However, the traditional siamese tracker has not achieved satisfactory performance due to the limited representation ability and the lack of appropriate model update strategy. To cover the shortage of siamese models, we proposed a cross‐similarity‐based siamese network with...

article

Deep multi-level networks with multi-task learning for saliency detection

Lihe Zhang, Xiang Fang, Hongguang Bo, Tiantian Wang, more

Neurocomputing > 2018 > 312 > C > 229-238

Category-independent region proposals have been utilized for salient objects detection in recent works. However, these works may fail when the extracted proposals have poor overlap with salient objects. In this paper, we demonstrate segment-level saliency prediction can provide these methods with complementary information to improve detection results. In addition, classification loss (i.e., softmax)...

article

Deep visual tracking: Review and experimental comparison

Peixia Li, Dong Wang, Lijun Wang, Huchuan Lu

Pattern Recognition > 2018 > 76 > C > 323-338

Recently, deep learning has achieved great success in visual tracking. The goal of this paper is to review the state-of-the-art tracking methods based on deep learning. First, we introduce the background of deep visual tracking, including the fundamental concepts of visual tracking and related deep learning algorithms. Second, we categorize the existing deep-learning-based trackers into three classes...

article

Cross-view semantic projection learning for person re-identification

Ju Dai, Ying Zhang, Huchuan Lu, Hongyu Wang

Pattern Recognition > 2018 > 75 > C > 63-76

Feature transformation is of great importance to strengthen the descriptive power of feature representation for many classification and recognition tasks. In this paper, we propose a novel cross-view semantic projection learning method for extracting latent semantics from the hand-crafted features. Specifically, the shared latent basis matrix, the view-specific semantic projection functions and the...

article

Hierarchical Cellular Automata for Visual Saliency

Yao Qin, Mengyang Feng, Huchuan Lu, Garrison W. Cottrell

International Journal of Computer Vision > 2018 > 126 > 7 > 751-770

Saliency detection, finding the most important parts of an image, has become increasingly popular in computer vision. In this paper, we introduce Hierarchical Cellular Automata (HCA)—a temporally evolving model to intelligently detect salient objects. HCA consists of two main components: Single-layer Cellular Automata (SCA) and Cuboid Cellular Automata (CCA). As an unsupervised propagation mechanism,...

article

Saliency Detection via Absorbing Markov Chain With Learnt Transition Probability

Lihe Zhang, Jianwu Ai, Bowen Jiang, Huchuan Lu, more

IEEE Transactions on Image Processing > 2018 > 27 > 2 > 987 - 998

In this paper, we propose a bottom–up saliency model based on absorbing Markov chain (AMC). First, a sparsely connected graph is constructed to capture the local context information of each node. All image boundary nodes and other nodes are, respectively, treated as the absorbing nodes and transient nodes in the absorbing Markov chain. Then, the expected number of times from each transient node to...

article

Human body segmentation in static images by models with shape as guidance

Shifeng Li, Chunxiao Liu, Huchuan Lu

Neurocomputing > 2018 > 275 > C > 1734-1743

In this paper, a hierarchical method for human body segmentation in static images is proposed. Based on the face detection, a torso model is developed to locate the torso to provide the foreground seeds for torso segmentation with graph cuts. Similarly, an upper leg model is designed for lower body segmentation based on the segmented torso. Besides, a general method which combines shape information...

article

Visual Tracking via Joint Discriminative Appearance Learning

Chong Sun, Fu Li, Huchuan Lu, Gang Hua

IEEE Transactions on Circuits and Systems for Video Technology > 2017 > 27 > 12 > 2567 - 2577

In this paper, we present a discriminative tracking method based on dictionary learning and support vector machine (SVM) classification, where the dictionary and the classifier are jointly learned within a unified objective function. A discriminative differential tracking method is proposed, which estimates the motion parameters iteratively by the gradient-based method to maximize the SVM classification...

chapter

Stepwise Metric Promotion for Unsupervised Video Person Re-identification

Zimo Liu, Dong Wang, Huchuan Lu

2017 IEEE International Conference on Computer Vision (ICCV) > 2448 - 2457

2017 IEEE International Conference on Computer Vision (ICCV)

The intensive annotation cost and the rich but unlabeled data contained in videos motivate us to propose an unsupervised video-based person re-identification (re-ID) method. We start from two assumptions: 1) different video tracklets typically contain different persons, given that the tracklets are taken at distinct places or with long intervals; 2) within each tracklet, the frames are mostly of the...

chapter

A Stagewise Refinement Model for Detecting Salient Objects in Images

Tiantian Wang, Ali Borji, Lihe Zhang, Pingping Zhang, more

2017 IEEE International Conference on Computer Vision (ICCV) > 4039 - 4048

2017 IEEE International Conference on Computer Vision (ICCV)

Deep convolutional neural networks (CNNs) have been successfully applied to a wide variety of problems in computer vision, including salient object detection. To detect and segment salient objects accurately, it is necessary to extract and combine high-level semantic features with low-levelfine details simultaneously. This happens to be a challenge for CNNs as repeated subsampling operations such...

chapter

Learning Uncertain Convolutional Features for Accurate Saliency Detection

Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, more

2017 IEEE International Conference on Computer Vision (ICCV) > 212 - 221

2017 IEEE International Conference on Computer Vision (ICCV)

Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key contribution of this work is to learn deep uncertain convolutional features (UCF), which encourage the robustness and accuracy of saliency detection. We achieve this via introducing...

chapter

Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, more

2017 IEEE International Conference on Computer Vision (ICCV) > 202 - 211

2017 IEEE International Conference on Computer Vision (ICCV)

Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. One key pillar of these successes is mining relevant information from features in convolutional layers. However, how to better aggregate multi-level convolutional feature maps for salient object detection is underexplored. In this work, we present Amulet, a generic aggregating multi-level...

article

Ranking Saliency

Lihe Zhang, Chuanr Yang, Huchuan Lu, Xiang Ruan, more

IEEE Transactions on Pattern Analysis and Machine Intelligence > 2017 > 39 > 9 > 1892 - 1904

Most existing bottom-up algorithms measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects. Instead of only considering the contrast between salient objects and their surrounding regions, we consider both foreground and background cues in this...

article

Medical Image Fusion and Denoising with Alternating Sequential Filter and Adaptive Fractional Order Total Variation

Wenda Zhao, Huchuan Lu

IEEE Transactions on Instrumentation and Measurement > 2017 > 66 > 9 > 2283 - 2294

Medical image fusion aims at integrating information from multimodality medical images to obtain a more complete and accurate description of the same object, which provides an easy access for image-guided medical diagnostic and treatment. Unfortunately, medical images are often corrupted by noise in acquisition or transmission, and the noise signal is easily mistaken for a useful characterization...

article

Interactive Video Segmentation via Local Appearance Model

Chong Sun, Huchuan Lu

IEEE Transactions on Circuits and Systems for Video Technology > 2017 > 27 > 7 > 1491 - 1501

In numerous video segmentation algorithms, shape and color priors from previous frames are propagated to successive frames for processing. One prime issue of the existing algorithms is how priors are modeled and propagated effectively. This paper proposes a novel algorithm for accurate and robust foreground prediction via a local appearance model based on shape and color. In the shape estimation process,...

chapter

Learning to Detect Salient Objects with Image-Level Supervision

Lijun Wang, Huchuan Lu, Yifan Wang, Mengyang Feng, more

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 3796 - 3805

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

Deep Neural Networks (DNNs) have substantially improved the state-of-the-art in salient object detection. However, training DNNs requires costly pixel-level annotations. In this paper, we leverage the observation that image-level tags provide important cues of foreground salient objects, and develop a weakly supervised learning method for saliency detection using image-level tags only. The Foreground...

chapter

Co-saliency detection via partially absorbing random walk

Xing Sun, Lihe Zhang, Huchuan Lu

2017 Seventh International Conference on Information Science and Technology (ICIST) > 230 - 237

2017 Seventh International Conference on Information Science and Technology (ICIST)

Co-saliency detection aims at finding the common salient objects in multiple images. In this paper, we introduce a new co-saliency detection model, which includes two main parts: co-salient seed selection using the inter-object recurrence cues from multiple images and saliency label propagation using partially absorbing random walk. With the guidance of co-salient seeds, salient objects are individually...

article

Dual Deep Network for Visual Tracking

Zhizhen Chi, Hongyang Li, Huchuan Lu, Ming-Hsuan Yang

IEEE Transactions on Image Processing > 2017 > 26 > 4 > 2005 - 2015

Visual tracking addresses the problem of identifying and localizing an unknown target in a video given the target specified by a bounding box in the first frame. In this paper, we propose a dual network to better utilize features among layers for visual tracking. It is observed that features in higher layers encode semantic context while its counterparts in lower layers are sensitive to discriminative...

article

Salient Object Detection via Multiple Instance Learning

Fang Huang, Jinqing Qi, Huchuan Lu, Lihe Zhang, more

IEEE Transactions on Image Processing > 2017 > 26 > 4 > 1911 - 1922

Object proposals are a series of candidate segments containing the objects of interest, which are taken as preprocessing and widely applied in various vision tasks. However, most of existing saliency approaches only utilizes the proposals to compute a location prior. In this paper, we naturally take the proposals as the bags of instances of multiple instances learning (MIL), where the instances are...

article

Visual tracking with structured patch-based model

Fu Li, Xu Jia, Cheng Xiang, Huchuan Lu

Image and Vision Computing > 2017 > 60 > C > 124-133

In this paper, we present a novel structured patch-based visual tracking method, which models the appearance of individual patches and their structural relationships within a unified framework. Specifically, this framework is defined as an optimal patch selection task, and can be further formulated as a linear programming problem, tractable and efficient in tracking scenario. To account for the changing...

INFONA - science communication portal

Search results for: Huchuan Lu

Online visual tracking via cross‐similarity‐based siamese network

Deep multi-level networks with multi-task learning for saliency detection

Deep visual tracking: Review and experimental comparison

Cross-view semantic projection learning for person re-identification

Hierarchical Cellular Automata for Visual Saliency

Saliency Detection via Absorbing Markov Chain With Learnt Transition Probability

Human body segmentation in static images by models with shape as guidance

Visual Tracking via Joint Discriminative Appearance Learning

Stepwise Metric Promotion for Unsupervised Video Person Re-identification

A Stagewise Refinement Model for Detecting Salient Objects in Images

Learning Uncertain Convolutional Features for Accurate Saliency Detection

Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

Ranking Saliency

Medical Image Fusion and Denoising with Alternating Sequential Filter and Adaptive Fractional Order Total Variation

Interactive Video Segmentation via Local Appearance Model

Learning to Detect Salient Objects with Image-Level Supervision

Co-saliency detection via partially absorbing random walk

Dual Deep Network for Visual Tracking

Salient Object Detection via Multiple Instance Learning

Visual tracking with structured patch-based model

Filter options

Publication date

Publication type

Keywords

Data set

Journal

INFONA - science communication portal

Search results for: Huchuan Lu

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.

Publication type

Keywords

Data set

Journal

Reporting an error / abuse

Sending the report failed

Accessibility options