Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining

Zhang, Dingwen; Han, Junwei; Han, Jungong; Shao, Ling

doi:10.1109/tnnls.2015.2495161

Cited by 156 publications

(66 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the kNNaverage pooling is very generic and can be potentially applied to various applications over sets, where some severe noise or extreme cases occur caused by capturing conditions in real world. Such applications include person-reidentification [47], object recognition, saliency detection [48], [49] and image retrieval [50].…”

Section: Discussionmentioning

confidence: 99%

Unconstrained Face Recognition Using a Set-to-Set Distance Measure on Deep Learned Features

Zhao

Han

Shao

2018

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

Abstract-Recently considerable efforts have been dedicated to unconstrained face recognition, which requires to identify faces "in the wild" for a set of images and/or video frames captured without human intervention. Unlike traditional face recognition that compares one-to-one media (either a single image or a video frame) only, we encounter a problem of matching sets with heterogeneous contents containing both images and videos. In this paper, we propose a novel Set-to-Set (S2S) distance measure to calculate the similarity between two sets with the aim to improve the recognition accuracy for faces with real-world challenges such as extreme poses or severe illumination conditions. Our S2S distance adopts the kNN-average pooling for the similarity scores computed on all the media in two sets, making the identification far less susceptible to the poor representations (outliers) than traditional feature-average pooling and score-average pooling. Furthermore, we show that various metrics can be embedded into our S2S distance framework, including both predefined and learned ones. This allows to choose the appropriate metric depending on the recognition task in order to achieve the best results. To evaluate the proposed S2S distance, we conduct extensive experiments on the challenging set-based IJB-A face dataset, which demonstrate that our algorithm achieves the stateof-the-art results and is clearly superior to the baselines including several deep learning based face recognition algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

Unconstrained Face Recognition Using a Set-to-Set Distance Measure on Deep Learned Features

Zhao

Han

Shao

2018

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, different methods were proposed applying such techniques: Stacked Denoising AutoEncoders (SDAEs) were introduced in [14], [50], [51] for building background models with deep learning architectures. Afterwards, salient object extraction was performed as a separation step by measuring the reconstruction residuals of deep autoencoders.…”

Section: Related Workmentioning

confidence: 99%

Direction Selective Contour Detection for Salient Objects

Manno-Kovacs

2019

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-The active contour model is a widely used technique for automatic object contour extraction. Existing methods based on this model can perform with high accuracy even in case of complex contours, but challenging issues remain, like the need for precise contour initialization for high curvature boundary segments or the handling of cluttered backgrounds. To deal with such issues, this paper presents a salient object extraction method, the first step of which is the introduction of an improved edge map that incorporates edge direction as a feature. The direction information in the small neighborhoods of image feature points are extracted, and the images' prominent orientations are defined for direction-selective edge extraction. Using such improved edge information, we provide a highly accurate shape contour representation, which we also combine with texture features. The principle of the paper is to interpret an object as the fusion of its components: its extracted contour and its inner texture. Our goal in fusing textural and structural information is twofold: it is applied for automatic contour initialization, and it is also used to establish an improved external force field. This fusion then produces highly accurate salient object extractions. We performed extensive evaluations which confirm that the presented object extraction method outperforms parametric active contour models and achieves higher efficiency than the majority of the evaluated automatic saliency methods.

show abstract

“…With the great success of CNNs on tasks such as image classification [22]- [25], natural language processing [26], [27], object detection [28]- [30], and image segmentation [31], [32], several trackers based on CNNs have been proposed. Fan et al [33] pre-train a network using the location and the appearance information of the object of interest to extract both spatial and temporal features.…”

Section: Related Workmentioning

confidence: 99%

Point-to-Set Distance Metric Learning on Deep Representations for Visual Tracking

Zhang

Jiang

et al. 2018

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Abstract-For autonomous driving application, a car shall be able to track objects in the scene in order to estimate where and how they will move such that the tracker embedded in the car can efficiently alert the car for effective collisionavoidance. Traditional discriminative object tracking methods usually train a binary classifier via a support vector machine (SVM) scheme to distinguish the target from its background. Despite demonstrated success, the performance of the SVM based trackers is limited because the classification is carried out only depending on support vectors (SVs) but the target's dynamic appearance may look similar to the training samples that have not been selected as SVs, especially when the training samples are not linearly classifiable. In such cases, the tracker may drift to the background and fail to track the target eventually. To address this problem, in this paper, we propose to integrate the point-toset/image-to-imageSet distance metric learning (DML) into visual tracking tasks and take full advantage of all the training samples when determining the best target candidate. The point-to-set DML is conducted on convolutional neural network features of the training data extracted from the starting frames. When a new frame comes, target candidates are first projected to the common subspace using the learned mapping functions, and then the candidate having the minimal distance to the target template sets is selected as the tracking result. Extensive experimental results show that even without model update the proposed method is able to achieve favourable performance on challenging image sequences compared to several state-of-the-art trackers.Index Terms-metric learning, point to set, visual tracking.

show abstract

Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining

Cited by 156 publications

References 47 publications

Unconstrained Face Recognition Using a Set-to-Set Distance Measure on Deep Learned Features

Unconstrained Face Recognition Using a Set-to-Set Distance Measure on Deep Learned Features

Direction Selective Contour Detection for Salient Objects

Point-to-Set Distance Metric Learning on Deep Representations for Visual Tracking

Contact Info

Product

Resources

About