Recently, methods with learning procedure have been widely used to solve person re-identification (re-id) problem. However, most existing databases for re-id are small-scale, therefore, over-fitting is likely to occur...
详细信息
ISBN:
(纸本)9780769549903
Recently, methods with learning procedure have been widely used to solve person re-identification (re-id) problem. However, most existing databases for re-id are small-scale, therefore, over-fitting is likely to occur. To further improve the performance, we propose a novel method by fusing multiple local features and exploring their structural information on different levels. the proposed method is called Structural Constraints Enhanced Feature Accumulation (SCEFA). three local features (i.e., Hierarchical Weighted Histograms (HWH), Gabor Ternary pattern HSV (GTP-HSV), Maximally Stable Color Regions (MSCR)) are used. Structural information of these features are deeply explored in three levels: pixel, blob, and part. the matching algorithms corresponding to the features are also discussed. Extensive experiments conducted on three datasets: VIPeR, EthZ and our own challenging dataset MCSSH, show that our approach outperforms stat-of-the-art methods significantly.
the track 2 and track 3 of ChaLearn 2016 can be considered as Multi-Label Classification problems. We present a framework of learning deep binary encoding (DeepBE) to deal with multi-label problems by transforming mul...
详细信息
ISBN:
(纸本)9781509014378
the track 2 and track 3 of ChaLearn 2016 can be considered as Multi-Label Classification problems. We present a framework of learning deep binary encoding (DeepBE) to deal with multi-label problems by transforming multi-labels to single labels. the transformation of DeepBE is in a hidden pattern, which can be well addressed by deep convolutions neural networks (CNNs). Furthermore, we adopt an ensemble strategy to enhance the learning robustness. this strategy is inspired by its effectiveness in fine-grained image recognition (FGIR) problem, while most of face related tasks such as track 2 and track 3 are also FGIR problems. By DeepBE, we got 5.45% and 10.84% mean square error for track 2 and track 3 respectively. Additionally, we proposed an algorithm adaption method to treat the multiple labels of track 2 directly and got 6.84% mean square error.
In view selection, little work has been done for optimizing the search process;views must be densely distributed and checked individually. thus, evaluating poor views wastes much time, and a poor view may even be misi...
详细信息
ISBN:
(纸本)9781467388511
In view selection, little work has been done for optimizing the search process;views must be densely distributed and checked individually. thus, evaluating poor views wastes much time, and a poor view may even be misidentified as a best one. In this paper, we propose a search strategy by identifying the regions that are very likely to contain best views, referred to as canonical regions. It is by decomposing the model under investigation into meaningful parts, and using the canonical views of these parts to generate canonical regions. Applying existing view selection methods in the canonical regions can not only accelerate the search process but also guarantee the quality of obtained views. As a result, when our canonical regions are used for searching N-best views during comprehensive model analysis, we can attain greater search speed and reduce the number of views required. Experimental results show the effectiveness of our method.
Facial gender and smile classification in unconstrained environment is challenging due to the invertible and large variations of face images. In this paper, we propose a deep model composed of GNet and SNet for these ...
详细信息
ISBN:
(纸本)9781509014378
Facial gender and smile classification in unconstrained environment is challenging due to the invertible and large variations of face images. In this paper, we propose a deep model composed of GNet and SNet for these two tasks. We leverage the multi-task learning and the general-to-specific fine-tuning scheme to enhance the performance of our model. Our strategies exploit the inherent correlation between face identity, smile, gender and other face attributes to relieve the problem of over-fitting on small training set and improve the classification performance. We also propose the tasks-aware face cropping scheme to extract attribute-specific regions. the experimental results on the ChaLearn'16 FotW dataset for gender and smile classification demonstrate the effectiveness of our proposed methods.
We propose a dual decomposition and linear program relaxation of the NP-hard minimum cost multicut problem. Unlike other polyhedral relaxations of the multicut polytope, it is amenable to efficient optimization by mes...
详细信息
ISBN:
(纸本)9781538604571
We propose a dual decomposition and linear program relaxation of the NP-hard minimum cost multicut problem. Unlike other polyhedral relaxations of the multicut polytope, it is amenable to efficient optimization by message passing. Like other polyhedral relaxations, it can be tightened efficiently by cutting planes. We define an algorithm that alternates between message passing and efficient separation of cycle- and odd-wheel inequalities. this algorithm is more efficient than state-of-the-art algorithms based on linear programming, including algorithms written in the framework of leading commercial software, as we show in experiments with large instances of the problem from applications in computervision, biomedical image analysis and data mining.
Given a single outdoor image, this paper proposes a collaborative learning approach for labeling it as either sunny or cloudy. Never adequately addressed, this two-class classification problem is by no means trivial g...
详细信息
ISBN:
(纸本)9781479951178
Given a single outdoor image, this paper proposes a collaborative learning approach for labeling it as either sunny or cloudy. Never adequately addressed, this two-class classification problem is by no means trivial given the great variety of outdoor images. Our weather feature combines special cues after properly encoding them into feature vectors. they then work collaboratively in synergy under a unified optimization framework that is aware of the presence (or absence) of a given weather cue during learning and classification. Extensive experiments and comparisons are performed to verify our method. We build a new weather image dataset consisting of 10K sunny and cloudy images, which is available online together withthe executable.
When dealing with objects with complex structures, saliency detection confronts a critical problem - namely that detection accuracy could be adversely affected if salient foreground or background in an image contains ...
详细信息
ISBN:
(纸本)9780769549897
When dealing with objects with complex structures, saliency detection confronts a critical problem - namely that detection accuracy could be adversely affected if salient foreground or background in an image contains small-scale high-contrast patterns. this issue is common in natural images and forms a fundamental challenge for prior methods. We tackle it from a scale point of view and propose a multi-layer approach to analyze saliency cues. the final saliency map is produced in a hierarchical model. Different from varying patch sizes or downsizing images, our scale-based region handling is by finding saliency values optimally in a tree model. Our approach improves saliency detection on many images that cannot be handled well traditionally. A new dataset is also constructed.
暂无评论