Semisupervised Feature Analysis by Mining Correlations Among Multiple Tasks
TL;DR: A novel semisupervised feature selection framework by mining correlations among multiple tasks and apply it to different multimedia applications is proposed, which outperforms the other state-of-the-art feature selection algorithms.
Abstract: In this paper, we propose a novel semisupervised feature selection framework by mining correlations among multiple tasks and apply it to different multimedia applications. Instead of independently computing the importance of features for each task, our algorithm leverages shared knowledge from multiple related tasks, thus improving the performance of feature selection. Note that the proposed algorithm is built upon an assumption that different tasks share some common structures. The proposed algorithm selects features in a batch mode, by which the correlations between various features are taken into consideration. Besides, considering the fact that labeling a large amount of training data in real world is both time-consuming and tedious, we adopt manifold learning, which exploits both labeled and unlabeled training data for a feature space analysis. Since the objective function is nonsmooth and difficult to solve, we propose an iteractive algorithm with fast convergence. Extensive experiments on different applications demonstrate that our algorithm outperforms the other state-of-the-art feature selection algorithms.
Citations
More filters
TL;DR: Li et al. as mentioned in this paper proposed a Siamese network that simultaneously computes the identification loss and verification loss, and the network learns a discriminative embedding and a similarity measurement at the same time.
Abstract: In this article, we revisit two popular convolutional neural networks in person re-identification (re-ID): verification and identification models. The two models have their respective advantages and limitations due to different loss functions. Here, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a Siamese network that simultaneously computes the identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two input images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations. Our method can be easily applied on different pretrained networks. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show that our architecture can also be applied to image retrieval. The code is available at https://github.com/layumi/2016_person_re-ID.
662 citations
TL;DR: A novel image fusion scheme based on image cartoon-texture decomposition and sparse representation is proposed, which outperforms the state-of-art methods, in terms of visual and quantitative evaluations.
287 citations
TL;DR: A novel semisupervised feature selection method from a new perspective that incorporates the exploration of the local structure into the procedure of joint feature selection so as to learn the optimal graph simultaneously and an adaptive loss function is exploited to measure the label fitness.
Abstract: Video semantic recognition usually suffers from the curse of dimensionality and the absence of enough high-quality labeled instances, thus semisupervised feature selection gains increasing attentions for its efficiency and comprehensibility. Most of the previous methods assume that videos with close distance (neighbors) have similar labels and characterize the intrinsic local structure through a predetermined graph of both labeled and unlabeled data. However, besides the parameter tuning problem underlying the construction of the graph, the affinity measurement in the original feature space usually suffers from the curse of dimensionality. Additionally, the predetermined graph separates itself from the procedure of feature selection, which might lead to downgraded performance for video semantic recognition. In this paper, we exploit a novel semisupervised feature selection method from a new perspective. The primary assumption underlying our model is that the instances with similar labels should have a larger probability of being neighbors. Instead of using a predetermined similarity graph, we incorporate the exploration of the local structure into the procedure of joint feature selection so as to learn the optimal graph simultaneously. Moreover, an adaptive loss function is exploited to measure the label fitness, which significantly enhances model’s robustness to videos with a small or substantial loss. We propose an efficient alternating optimization algorithm to solve the proposed challenging problem, together with analyses on its convergence and computational complexity in theory. Finally, extensive experimental results on benchmark datasets illustrate the effectiveness and superiority of the proposed approach on video semantic recognition related tasks.
255 citations
Proceedings Article•
12 Feb 2016TL;DR: This work scientifically and systematically study the feasibility of career path prediction from social network data and seamlessly fuse information from multiple social networks to comprehensively describe a user and characterize progressive properties of his or her career path.
Abstract: People go to fortune tellers in hopes of learning things about their future. A future career path is one of the topics most frequently discussed. But rather than rely on "black arts" to make predictions, in this work we scientifically and systematically study the feasibility of career path prediction from social network data. In particular, we seamlessly fuse information from multiple social networks to comprehensively describe a user and characterize progressive properties of his or her career path. This is accomplished via a multi-source learning framework with fused lasso penalty, which jointly regularizes the source and career-stage relatedness. Extensive experiments on real-world data confirm the accuracy of our model.
234 citations
Cites background from "Semisupervised Feature Analysis by ..."
...Multi-task learning is a learning paradigm that jointly learns multiple related tasks and has demonstrated its advantages in handling dynamic progression problems in many domains, such as medical science and transportation (Zhang and Yeung 2010; Chang and Yang 2014; Zhou et al. 2011; 2012; Liu et al. 2015; Zheng and Ni 2013)....
[...]
...…paradigm that jointly learns multiple related tasks and has demonstrated its advantages in handling dynamic progression problems in many domains, such as medical science and transportation (Zhang and Yeung 2010; Chang and Yang 2014; Zhou et al. 2011; 2012; Liu et al. 2015; Zheng and Ni 2013)....
[...]
TL;DR: This work reconstructs the high-dimensional features of Android applications (apps) and employ multiple CNN to detect Android malware and proposes a hybrid model based on deep autoencoder (DAE) and convolutional neural network (CNN), which shows powerful ability in feature extraction and malware detection.
Abstract: Android security incidents occurred frequently in recent years. To improve the accuracy and efficiency of large-scale Android malware detection, in this work, we propose a hybrid model based on deep autoencoder (DAE) and convolutional neural network (CNN). First, to improve the accuracy of malware detection, we reconstruct the high-dimensional features of Android applications (apps) and employ multiple CNN to detect Android malware. In the serial convolutional neural network architecture (CNN-S), we use Relu, a non-linear function, as the activation function to increase sparseness and “dropout” to prevent over-fitting. The convolutional layer and pooling layer are combined with the full-connection layer to enhance feature extraction capability. Under these conditions, CNN-S shows powerful ability in feature extraction and malware detection. Second, to reduce the training time, we use deep autoencoder as a pre-training method of CNN. With the combination, deep autoencoder and CNN model (DAE-CNN) can learn more flexible patterns in a short time. We conduct experiments on 10,000 benign apps and 13,000 malicious apps. CNN-S demonstrates a significant improvement compared with traditional machine learning methods in Android malware detection. In details, compared with SVM, the accuracy with the CNN-S model is improved by 5%, while the training time using DAE-CNN model is reduced by 83% compared with CNN-S model.
212 citations
References
More filters
TL;DR: A generic approach to cancer classification based on gene expression monitoring by DNA microarrays is described and applied to human acute leukemias as a test case and suggests a general strategy for discovering and predicting cancer classes for other types of cancer, independent of previous biological knowledge.
Abstract: Although cancer classification has improved over the past 30 years, there has been no general approach for identifying new cancer classes (class discovery) or for assigning tumors to known classes (class prediction). Here, a generic approach to cancer classification based on gene expression monitoring by DNA microarrays is described and applied to human acute leukemias as a test case. A class discovery procedure automatically discovered the distinction between acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL) without previous knowledge of these classes. An automatically derived class predictor was able to determine the class of new leukemia cases. The results demonstrate the feasibility of cancer classification based solely on gene expression monitoring and suggest a general strategy for discovering and predicting cancer classes for other types of cancer, independent of previous biological knowledge.
12,530 citations
"Semisupervised Feature Analysis by ..." refers background or methods in this paper
...We use four different data sets in the experiment, including one video data sets, the Columbia Consumer Video (CCV) data set [43], one image data sets, the NUSWIDE data set [44], one human motion data set, the HMDB data set [45], one 3-D motion skeleton data set, the HumanEva data set [46], and three gene expression data sets [47]–[49]....
[...]
...all/aml [47], lymphoma [48], and global cancer map [49]....
[...]
01 Jan 2005
4,189 citations
"Semisupervised Feature Analysis by ..." refers background in this paper
...Semisupervised learning has shown its promising performance in different applications [24]–[30]....
[...]
...According to [6] and [24], Fl can be obtained as follows:...
[...]
06 Nov 2011
TL;DR: This paper uses the largest action video database to-date with 51 action categories, which in total contain around 7,000 manually annotated clips extracted from a variety of sources ranging from digitized movies to YouTube, to evaluate the performance of two representative computer vision systems for action recognition and explore the robustness of these methods under various conditions.
Abstract: With nearly one billion online videos viewed everyday, an emerging new frontier in computer vision research is recognition and search in video. While much effort has been devoted to the collection and annotation of large scalable static image datasets containing thousands of image categories, human action datasets lag far behind. Current action recognition databases contain on the order of ten different action categories collected under fairly controlled conditions. State-of-the-art performance on these datasets is now near ceiling and thus there is a need for the design and creation of new benchmarks. To address this issue we collected the largest action video database to-date with 51 action categories, which in total contain around 7,000 manually annotated clips extracted from a variety of sources ranging from digitized movies to YouTube. We use this database to evaluate the performance of two representative computer vision systems for action recognition and explore the robustness of these methods under various conditions such as camera motion, viewpoint, video quality and occlusion.
3,533 citations
"Semisupervised Feature Analysis by ..." refers methods in this paper
...We use four different data sets in the experiment, including one video data sets, the Columbia Consumer Video (CCV) data set [43], one image data sets, the NUSWIDE data set [44], one human motion data set, the HMDB data set [45], one 3-D motion skeleton data set, the HumanEva data set [46], and three gene expression data sets [47]–[49]....
[...]
...We use the HMDB video data set [45] to compare the algorithms in terms of human motion recognition....
[...]
01 Dec 2013
TL;DR: Dense trajectories were shown to be an efficient video representation for action recognition and achieved state-of-the-art results on a variety of datasets are improved by taking into account camera motion to correct them.
Abstract: Recently dense trajectories were shown to be an efficient video representation for action recognition and achieved state-of-the-art results on a variety of datasets. This paper improves their performance by taking into account camera motion to correct them. To estimate camera motion, we match feature points between frames using SURF descriptors and dense optical flow, which are shown to be complementary. These matches are, then, used to robustly estimate a homography with RANSAC. Human motion is in general different from camera motion and generates inconsistent matches. To improve the estimation, a human detector is employed to remove these matches. Given the estimated camera motion, we remove trajectories consistent with it. We also use this estimation to cancel out camera motion from the optical flow. This significantly improves motion-based descriptors, such as HOF and MBH. Experimental results on four challenging action datasets (i.e., Hollywood2, HMDB51, Olympic Sports and UCF50) significantly outperform the current state of the art.
3,487 citations
"Semisupervised Feature Analysis by ..." refers methods in this paper
...Wang and Schmid [54] claim that motion boundary histograms are an efficient way to suppress camera motion, and thus, it is used to process the videos....
[...]