We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other activities. To address this challenging issue, we exploit the effectiveness of deep networks in temporal action localization via three segment-based 3D ConvNets: (1) a proposal network identifies candidate segments in a long video that may contain actions; (2) a classification network learns one-vs-all action classification model to serve as initialization for the localization network; and (3) a localization network fine-tunes on the learned classification network to localize each action instance. We propose a novel loss function for the localization network to explicitly consider temporal overlap and therefore achieve high temporal localization accuracy. Only the proposal network and the localization network are used during prediction. On two large-scale benchmarks, our approach achieves significantly superior performances compared with other state-of-the-art systems: mAP increases from 1.7% to 7.4% on MEXaction2 and increases from 15.0% to 19.0% on THUMOS 2014, when the overlap threshold for evaluation is set to 0.5.
Despite the loss of semantic information, bag-of-ngram based methods still achieve state-of-the-art results for tasks such as sentiment classification of long movie reviews. Many document embeddings methods have been proposed to capture semantics, but they still can't outperform bag-of-ngram based methods on this task. In this paper, we modify the architecture of the recently proposed Paragraph Vector, allowing it to learn document vectors by predicting not only words, but n-gram features as well. Our model is able to capture both semantics and word order in documents while keeping the expressive power of learned vectors. Experimental results on IMDB movie review dataset shows that our model outperforms previous deep learning models and bag-of-ngram based models due to the above advantages. More robust results are also obtained when our model is combined with other models. The source code of our model will be also published together with this paper.
In general, the clustering problem is NP-hard, and global optimality cannot be established for non-trivial instances. For high-dimensional data, distance-based methods for clustering or classification face an additional difficulty, the unreliability of distances in very high-dimensional spaces. We propose a distance-based iterative method for clustering data in very high-dimensional space, using the $\ell_1$-metric that is less sensitive to high dimensionality than the Euclidean distance. For $K$ clusters in $\mathbb{R}^n$, the problem decomposes to $K$ problems coupled by probabilities, and an iteration reduces to finding $Kn$ weighted medians of points on a line. The complexity of the algorithm is linear in the dimension of the data space, and its performance was observed to improve significantly as the dimension increases.
We introduce the use of DCTNet, an efficient approximation and alternative to PCANet, for acoustic signal classification. In PCANet, the eigenfunctions of the local sample covariance matrix (PCA) are used as filterbanks for convolution and feature extraction. When the eigenfunctions are well approximated by the Discrete Cosine Transform (DCT) functions, each layer of of PCANet and DCTNet is essentially a time-frequency representation. We relate DCTNet to spectral feature representation methods, such as the the short time Fourier transform (STFT), spectrogram and linear frequency spectral coefficients (LFSC). Experimental results on whale vocalization data show that DCTNet improves classification rate, demonstrating DCTNet's applicability to signal processing problems such as underwater acoustics.
An epileptic seizure is a transient event of abnormal excessive neuronal discharge in the brain. This unwanted event can be obstructed by detection of electrical changes in the brain that happen before the seizure takes place. The automatic detection of seizures is necessary since the visual screening of EEG recordings is a time consuming task and requires experts to improve the diagnosis. Four linear least squares-based preprocessing models are proposed to extract key features of an EEG signal in order to detect seizures. The first two models are newly developed. The original signal (EEG) is approximated by a sinusoidal curve. Its amplitude is formed by a polynomial function and compared with the pre developed spline function.Different statistical measures namely classification accuracy, true positive and negative rates, false positive and negative rates and precision are utilized to assess the performance of the proposed models. These metrics are derived from confusion matrices obtained from classifiers. Different classifiers are used over the original dataset and the set of extracted features. The proposed models significantly reduce the dimension of the classification problem and the computational time while the classification accuracy is improved in most cases. The first and third models are promising feature extraction methods. Logistic, LazyIB1, LazyIB5 and J48 are the best classifiers. Their true positive and negative rates are $1$ while false positive and negative rates are zero and the corresponding precision values are $1$. Numerical results suggest that these models are robust and efficient for detecting epileptic seizure.
Machine learning models are frequently used to solve complex security problems, as well as to make decisions in sensitive situations like guiding autonomous vehicles or predicting financial market behaviors. Previous efforts have shown that numerous machine learning models were vulnerable to adversarial manipulations of their inputs taking the form of adversarial samples. Such inputs are crafted by adding carefully selected perturbations to legitimate inputs so as to force the machine learning model to misbehave, for instance by outputting a wrong class if the machine learning task of interest is classification. In fact, to the best of our knowledge, all previous work on adversarial samples crafting for neural network considered models used to solve classification tasks, most frequently in computer vision applications. In this paper, we contribute to the field of adversarial machine learning by investigating adversarial input sequences for recurrent neural networks processing sequential data. We show that the classes of algorithms introduced previously to craft adversarial samples misclassified by feed-forward neural networks can be adapted to recurrent neural networks. In a experiment, we show that adversaries can craft adversarial sequences misleading both categorical and sequential recurrent neural networks.
Background: In cognitive neuroscience the potential of Deep Neural Networks (DNNs) for solving complex classification tasks is yet to be fully exploited. The most limiting factor is that DNNs as notorious 'black boxes' do not provide insight into neurophysiological phenomena underlying a decision. Layer-wise Relevance Propagation (LRP) has been introduced as a novel method to explain individual network decisions. New Method: We propose the application of DNNs with LRP for the first time for EEG data analysis. Through LRP the single-trial DNN decisions are transformed into heatmaps indicating each data point's relevance for the outcome of the decision. Results: DNN achieves classification accuracies comparable to those of CSP-LDA. In subjects with low performance subject-to-subject transfer of trained DNNs can improve the results. The single-trial LRP heatmaps reveal neurophysiologically plausible patterns, resembling CSP-derived scalp maps. Critically, while CSP patterns represent class-wise aggregated information, LRP heatmaps pinpoint neural patterns to single time points in single trials. Comparison with Existing Method(s): We compare the classification performance of DNNs to that of linear CSP-LDA on two data sets related to motor-imaginery BCI. Conclusion: We have demonstrated that DNN is a powerful non-linear tool for EEG analysis. With LRP a new quality of high-resolution assessment of neural activity can be reached. LRP is a potential remedy for the lack of interpretability of DNNs that has limited their utility in neuroscientific applications. The extreme specificity of the LRP-derived heatmaps opens up new avenues for investigating neural activity underlying complex perception or decision-related processes.
In this paper, we present a novel approach that uses deep learning techniques for colorizing grayscale images. By utilizing a pre-trained convolutional neural network, which is originally designed for image classification, we are able to separate content and style of different images and recombine them into a single image. We then propose a method that can add colors to a grayscale image by combining its content with style of a color image having semantic similarity with the grayscale one. As an application, to our knowledge the first of its kind, we use the proposed method to colorize images of ukiyo-e a genre of Japanese painting?and obtain interesting results, showing the potential of this method in the growing field of computer assisted art.
Classification Ensemble, which uses the weighed polling of outputs, is the art of combining a set of basic classifiers for generating high-performance, robust and more stable results. This study aims to improve the results of identifying the Persian handwritten letters using Error Correcting Output Coding (ECOC) ensemble method. Furthermore, the feature selection is used to reduce the costs of errors in our proposed method. ECOC is a method for decomposing a multi-way classification problem into many binary classification tasks; and then combining the results of the subtasks into a hypothesized solution to the original problem. Firstly, the image features are extracted by Principal Components Analysis (PCA). After that, ECOC is used for identification the Persian handwritten letters which it uses Support Vector Machine (SVM) as the base classifier. The empirical results of applying this ensemble method using 10 real-world data sets of Persian handwritten letters indicate that this method has better results in identifying the Persian handwritten letters than other ensemble methods and also single classifications. Moreover, by testing a number of different features, this paper found that we can reduce the additional cost in feature selection stage by using this method.
The human behavior of evaluating other individuals with respect to their personality traits and intelligence by evaluating their faces plays a crucial role in human relations. These trait judgments might influence important social outcomes in our lives such as elections and court sentences. Previous studies have reported that human can make valid inferences for at least four personality traits. In addition, some studies have demonstrated that facial trait evaluation can be learned using machine learning methods accurately. In this work, we experimentally explore whether self-reported personality traits and intelligence can be predicted reliably from a facial image. More specifically, the prediction problem is separately cast in two parts: a classification task and a regression task. A facial structural feature is constructed from the relations among facial salient points, and an appearance feature is built by five texture descriptors. In addition, a minutia-based fingerprint feature from a fingerprint image is also explored. The classification results show that the personality traits "Rule-consciousness" and "Vigilance" can be predicted reliably, and that the traits of females can be predicted more accurately than those of male. However, the regression experiments show that it is difficult to predict scores for individual personality traits and intelligence. The residual plots and the correlation results indicate no evident linear correlation between the measured scores and the predicted scores. Both the classification and the regression results reveal that "Rule-consciousness" and "Tension" can be reliably predicted from the facial features, while "Social boldness" gets the worst prediction results. The experiments results show that it is difficult to predict intelligence from either the facial features or the fingerprint feature, a finding that is in agreement with previous studies.
Attributes, or semantic features, have gained popularity in the past few years in domains ranging from activity recognition in video to face verification. Improving the accuracy of attribute classifiers is an important first step in any application which uses these attributes. In most works to date, attributes have been considered to be independent. However, we know this not to be the case. Many attributes are very strongly related, such as heavy makeup and wearing lipstick. We propose to take advantage of attribute relationships in three ways: by using a multi-task deep convolutional neural network (MCNN) sharing the lowest layers amongst all attributes, sharing the higher layers for related attributes, and by building an auxiliary network on top of the MCNN which utilizes the scores from all attributes to improve the final classification of each attribute. We demonstrate the effectiveness of our method by producing results on two challenging publicly available datasets.
We propose a flexible procedure for large-scale image search by hash functions with kernels. Our method treats binary codes and pairwise semantic similarity as latent and observed variables, respectively, in a probabilistic model based on Gaussian processes for binary classification. We present an efficient inference algorithm with the sparse pseudo-input Gaussian process (SPGP) model and parallelization. Experiments on three large-scale image dataset demonstrate the effectiveness of the proposed hashing method, Gaussian Process Hashing (GPH), for short binary codes and the datasets without predefined classes in comparison to the state-of-the-art supervised hashing methods.
This paper presents a comparison of classification methods for linguistic typology for the purpose of expanding an extensive, but sparse language resource: the World Atlas of Language Structures (WALS) (Dryer and Haspelmath, 2013). We experimented with a variety of regression and nearest-neighbor methods for use in classification over a set of 325 languages and six syntactic rules drawn from WALS. To classify each rule, we consider the typological features of the other five rules; linguistic features extracted from a word-aligned Bible in each language; and genealogical features (genus and family) of each language. In general, we find that propagating the majority label among all languages of the same genus achieves the best accuracy in label pre- diction. Following this, a logistic regression model that combines typological and linguistic features offers the next best performance. Interestingly, this model actually outperforms the majority labels among all languages of the same family.
In recent decades, the use of 3D point clouds has been widespread in computer industry. The development of techniques in analyzing point clouds is increasingly important. In particular, mapping of point clouds has been a challenging problem. In this paper, we develop a discrete analogue of the Teichm\"{u}ller extremal mappings, which guarantee uniform conformality distortions, on point cloud surfaces. Based on the discrete analogue, we propose a novel method called TEMPO for computing Teichm\"{u}ller extremal mappings between feature-endowed point clouds. Using our proposed method, the Teichm\"{u}ller metric is introduced for evaluating the dissimilarity of point clouds. Consequently, our algorithm enables accurate recognition and classification of point clouds. Experimental results demonstrate the effectiveness of our proposed method.
We conduct an empirical study to test the ability of Convolutional Neural Networks (CNNs) to reduce the effects of nuisance transformations of the input data, such as location, scale and aspect ratio. We isolate factors by adopting a common convolutional architecture either deployed globally on the image to compute class posterior distributions, or restricted locally to compute class conditional distributions given location, scale and aspect ratios of bounding boxes determined by proposal heuristics. In theory, averaging the latter should yield inferior performance compared to proper marginalization. Yet empirical evidence suggests the converse, leading us to conclude that - at the current level of complexity of convolutional architectures and scale of the data sets used to train them - CNNs are not very effective at marginalizing nuisance variability. We also quantify the effects of context on the overall classification task and its impact on the performance of CNNs, and propose improved sampling techniques for heuristic proposal schemes that improve end-to-end performance to state-of-the-art levels. We test our hypothesis on a classification task using the ImageNet Challenge benchmark and on a wide-baseline matching task using the Oxford and Fischer's datasets.
We propose a robust approach for performing automatic species-level recognition of fossil pollen grains in microscopy images that exploits both global shape and local texture characteristics in a patch-based matching methodology. We introduce a novel criteria for selecting meaningful and discriminative exemplar patches. We optimize this function during training using a greedy submodular function optimization framework that gives a near-optimal solution with bounded approximation error. We use these selected exemplars as a dictionary basis and propose a spatially-aware sparse coding method to match testing images for identification while maintaining global shape correspondence. To accelerate the coding process for fast matching, we introduce a relaxed form that uses spatially-aware soft-thresholding during coding. Finally, we carry out an experimental study that demonstrates the effectiveness and efficiency of our exemplar selection and classification mechanisms, achieving $86.13\%$ accuracy on a difficult fine-grained species classification task distinguishing three types of fossil spruce pollen.
Artery and vein (AV) classification of retinal images is a key to necessary tasks, such as automated measurement of arteriolar-to-venular diameter ratio (AVR). This paper comprehensively reviews the state-of-the art in AV classification methods. To improve on previous methods, a new Local Bi- nary Pattern-based method (LBP) is proposed. Beside its simplicity, LBP is robust against low contrast and low quality fundus images; and it helps the process by including additional AV texture and shape information. Experimental results compare the performance of the new method with the state-of-the art; and also methods with different feature extraction and classification schemas.
In this paper, we describe a compact low-power, high performance hardware implementation of the extreme learning machine (ELM) for machine learning applications. Mismatch in current mirrors are used to perform the vector-matrix multiplication that forms the first stage of this classifier and is the most computationally intensive. Both regression and classification (on UCI data sets) are demonstrated and a design space trade-off between speed, power and accuracy is explored. Our results indicate that for a wide set of problems, $\sigma V_T$ in the range of $15-25$mV gives optimal results. An input weight matrix rotation method to extend the input dimension and hidden layer size beyond the physical limits imposed by the chip is also described. This allows us to overcome a major limit imposed on most hardware machine learners. The chip is implemented in a $0.35 \mu$m CMOS process and occupies a die area of around 5 mm $\times$ 5 mm. Operating from a $1$ V power supply, it achieves an energy efficiency of $0.47$ pJ/MAC at a classification rate of $31.6$ kHz.
Closed Form is a propagation based matting algorithm, functioning well on images with good propagation . The deficiency of the Closed Form method is that for complex areas with poor image propagation , such as hole areas or areas of long and narrow structures. The right results are usually hard to get. On these areas, if certain flags are provided, it can improve the effects of matting. In this paper, we design a matting algorithm by local sampling and the KNN classifier propagation based matting algorithm. First of all, build the corresponding features space according to the different components of image colors to reduce the influence of overlapping between the foreground and background, and to improve the classification accuracy of KNN classifier. Second, adaptively use local sampling or using local KNN classifier for processing based on the pros and cons of the sample performance of unknown image areas. Finally, based on different treatment methods for the unknown areas, we will use different weight for augmenting constraints to make the treatment more effective. In this paper, by combining qualitative observation and quantitative analysis, we will make evaluation of the experimental results through online standard set of evaluation tests. It shows that on images with good propagation , this method is as effective as the Closed Form method, while on images in complex regions, it can perform even better than Closed Form.
We introduce learned attention models into the radio machine learning domain for the task of modulation recognition by leveraging spatial transformer networks and introducing new radio domain appropriate transformations. This attention model allows the network to learn a localization network capable of synchronizing and normalizing a radio signal blindly with zero knowledge of the signals structure based on optimization of the network for classification accuracy, sparse representation, and regularization. Using this architecture we are able to outperform our prior results in accuracy vs signal to noise ratio against an identical system without attention, however we believe such an attention model has implication far beyond the task of modulation recognition.