Search

Error Correcting Output Codes (ECOC) is a successful technique in multi-class classification, which is a core problem in Pattern Recognition and Machine Learning. A major advantage of ECOC over other methods is that the multi-class problem is decoupled into a set of binary problems that are solved independently. However, literature defines a general error-correcting capability for ECOCs without analyzing how it distributes among classes, hindering a deeper analysis of pair-wise error-correction. To address these limitations this paper proposes an Error-Correcting Factorization (ECF) method. Our contribution is three fold: (I) We propose a novel representation of the error-correction capability, called the design matrix, that enables us to build an ECOC on the basis of allocating correction to pairs of classes. (II) We derive the optimal code length of an ECOC using rank properties of the design matrix. (III) ECF is formulated as a discrete optimization problem, and a relaxed solution is found using an efficient constrained block coordinate descent approach. (IV) Enabled by the flexibility introduced with the design matrix we propose to allocate the error-correction on classes that are prone to confusion. Experimental results in several databases show that when allocating the error-correction to confusable classes ECF outperforms state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Linear regression is a fundamental building block in many face detection and tracking algorithms, typically used to predict shape displacements from image features through a linear mapping. This paper presents a Functional Regression solution to the least squares problem, which we coin Continuous Regression, resulting in the first real-time incremental face tracker. Contrary to prior work in Functional Regression, in which B-splines or Fourier series were used, we propose to approximate the input space by its first-order Taylor expansion, yielding a closed-form solution for the continuous domain of displacements. We then extend the continuous least squares problem to correlated variables, and demonstrate the generalisation of our approach. We incorporate Continuous Regression into the cascaded regression framework, and show its computational benefits for both training and testing. We then present a fast approach for incremental learning within Cascaded Continuous Regression, coined iCCR, and show that its complexity allows real-time face tracking, being 20 times faster than the state of the art. To the best of our knowledge, this is the first incremental face tracker that is shown to operate in real-time. We show that iCCR achieves state-of-the-art performance on the 300-VW dataset, the most recent, large-scale benchmark for face tracking. [ABSTRACT FROM AUTHOR]

Automatic facial action unit (AU) and expression detection from videos is a long-standing problem. The problem is challenging in part because classifiers must generalize to previously unknown subjects that differ markedly in behavior and facial morphology (e.g., heavy versus delicate brows, smooth versus deeply etched wrinkles) from those on which the classifiers are trained. While some progress has been achieved through improvements in choices of features and classifiers, the challenge occasioned by individual differences among people remains. Person-specific classifiers would be a possible solution but for a paucity of training data. Sufficient training data for person-specific classifiers typically is unavailable. This paper addresses the problem of how to personalize a generic classifier without additional labels from the test subject. We propose a transductive learning method, which we refer to as a Selective Transfer Machine (STM), to personalize a generic classifier by attenuating person-specific mismatches. STM achieves this effect by simultaneously learning a classifier and re-weighting the training samples that are most relevant to the test subject. We compared STM to both generic classifiers and cross-domain learning methods on four benchmarks: CK+ [44] , GEMEP-FERA [67] , RU-FACS [4] and GFT [57] . STM outperformed generic classifiers in all. [ABSTRACT FROM PUBLISHER]

Detection and tracking humans in videos have been long-standing problems in computer vision. Most successful approaches (e.g., deformable parts models) heavily rely on discriminative models to build appearance detectors for body joints and generative models to constrain possible body configurations (e.g., trees). While these $2$ D models have been successfully applied to images (and with less success to videos), a major challenge is to generalize these models to cope with camera views. In order to achieve view-invariance, these $2$ D models typically require a large amount of training data across views that is difficult to gather and time-consuming to label. Unlike existing $2$ D models, this paper formulates the problem of human detection in videos as spatio-temporal matching (STM) between a $3$ D motion capture model and trajectories in videos. Our algorithm estimates the camera view and selects a subset of tracked trajectories that matches the motion of the $3$ D model. The STM is efficiently solved with linear programming, and it is robust to tracking mismatches, occlusions and outliers. To the best of our knowledge this is the first paper that solves the correspondence between video and $3$ D motion capture data for human pose detection. Experiments on the CMU motion capture, Human3.6M, Berkeley MHAD and CMU MAD databases illustrate the benefits of our method over state-of-the-art approaches. [ABSTRACT FROM PUBLISHER]

Temporal alignment of human motion has been of recent interest due to its applications in animation, tele-rehabilitation and activity recognition. This paper presents generalized canonical time warping (GCTW), an extension of dynamic time warping (DTW) and canonical correlation analysis (CCA) for temporally aligning multi-modal sequences from multiple subjects performing similar activities. GCTW extends previous work on DTW and CCA in several ways: (1) it combines CCA with DTW to align multi-modal data (e.g., video and motion capture data); (2) it extends DTW by using a linear combination of monotonic functions to represent the warping path, providing a more flexible temporal warp. Unlike exact DTW, which has quadratic complexity, we propose a linear time algorithm to minimize GCTW. (3) GCTW allows simultaneous alignment of multiple sequences. Experimental results on aligning multi-modal data, facial expressions, motion capture data and video illustrate the benefits of GCTW. The code is available at http://humansensing.cs.cmu.edu/ctw. [ABSTRACT FROM PUBLISHER]

In the last few years, image classification has become an incredibly active research topic, with widespread applications. Most methods for visual recognition are fully supervised, as they make use of bounding boxes or pixelwise segmentations to locate objects of interest. However, this type of manual labeling is time consuming, error prone and it has been shown that manual segmentations are not necessarily the optimal spatial enclosure for object classifiers. This paper proposes a weakly-supervised system for multi-label image classification. In this setting, training images are annotated with a set of keywords describing their contents, but the visual concepts are not explicitly segmented in the images. We formulate the weakly-supervised image classification as a low-rank matrix completion problem. Compared to previous work, our proposed framework has three advantages: (1) Unlike existing solutions based on multiple-instance learning methods, our model is convex. We propose two alternative algorithms for matrix completion specifically tailored to visual data, and prove their convergence. (2) Unlike existing discriminative methods, our algorithm is robust to labeling errors, background noise and partial occlusions. (3) Our method can potentially be used for semantic segmentation. Experimental validation on several data sets shows that our method outperforms state-of-the-art classification algorithms, while effectively capturing each class appearance. [ABSTRACT FROM AUTHOR]

Temporal segmentation of human motion into plausible motion primitives is central to understanding and building computational models of human motion. Several issues contribute to the challenge of discovering motion primitives: the exponential nature of all possible movement combinations, the variability in the temporal scale of human actions, and the complexity of representing articulated motion. We pose the problem of learning motion primitives as one of temporal clustering, and derive an unsupervised hierarchical bottom-up framework called hierarchical aligned cluster analysis (HACA). HACA finds a partition of a given multidimensional time series into m disjoint segments such that each segment belongs to one of k clusters. HACA combines kernel k--means with the generalized dynamic time alignment kernel to cluster time series data. Moreover, it provides a natural framework to find a low-dimensional embedding for time series. HACA is efficiently optimized with a coordinate descent strategy and dynamic programming. Experimental results on motion capture and video data demonstrate the effectiveness of HACA for segmenting complex motions and as a visualization tool. We also compare the performance of HACA to state-of-the-art algorithms for temporal clustering on data of a honey bee dance. The HACA code is available online. [ABSTRACT FROM AUTHOR]

In this paper, we report the identification of genes from pine ( PpAAT), Arabidopsis ( AtAAT) and rice ( OsAAT) encoding a novel class of aspartate aminotransferase (AAT, EC 2.6.1.1) in plants. The enzyme is unrelated to other eukaryotic AATs from plants and animals but similar to bacterial enzymes. Phylogenetic analysis indicates that this prokaryotic-type AAT is closely related to cyanobacterial enzymes, suggesting it might have an endosymbiotic origin. Interestingly, most of the essential residues involved in the interaction with the substrate and the attachment of pyridoxal phosphate cofactor in the active site of the enzyme were conserved in the deduced polypeptide. The polypeptide is processed in planta to a mature subunit of 45 kDa that is immunologically distinct from the cytosolic, mitochondrial and chloroplastic isoforms of AAT previously characterized in plants. Functional expression of PpAAT sequences in Escherichia coli showed that the processed precursor is assembled into a catalytically active homodimeric holoenzyme that is strictly specific for aspartate. These atypical genes are predominantly expressed in green tissues of pine, Arabidopsis and rice, suggesting a key role of this AAT in nitrogen metabolism associated with photosynthetic activity. Moreover, immunological analyses revealed that the plant prokaryotic-type AAT is a nuclear-encoded chloroplast protein. This implies that two plastidic AAT co-exist in plants: a eukaryotic type previously characterized and the prokaryotic type described here. The respective roles of these two enzymes in plant amino acid metabolism are discussed. [ABSTRACT FROM AUTHOR]

Nitrogen is an important macronutrient for plant growth and development. Research has long been carried out to elucidate the mechanisms involved in nitrogen uptake, assimilation, and utilization in plants. However, despite recent advances, many of these mechanisms still are not fully understood. In this special issue, several research articles and two reviews, all of them aiming to elucidate some specific aspects of nitrogen (N) metabolism, are presented. Together, the articles in this issue provide a state-of-the-art perspective on important questions related to nitrogen metabolism in photosynthetic organisms, highlighting the fundamental importance of research in this field. [ABSTRACT FROM AUTHOR]

Triclosan (TCS) is an antimicrobial and antimycotic agent widely used in personal care products. In aquatic environments, both TCS and its biomethylated more persistent form, methyl-triclosan (MeTCS), are usually detected in wastewater effluents and rivers, where are commonly adsorbed to suspended solids and sediments. The aim of this study was to evaluate biochemical and physiological effects in Danio rerio after a short term (2 days) and prolonged (21 days) exposures to sediment spiked with TCS acting as the source of the pollutant in the assay. The activities of catalase (CAT), glutathione-s transferase (GST) and superoxide dismutase (SOD), lipid peroxidation levels (LPO), total capacity against peroxyl radicals (ACAP), and acetylcholinesterase enzymatic activity (AChE) were measured in liver, gills, and brain. Most of TCS on the spiked sediment was biotransformed to MeTCS and promoted different adverse effects on D. rerio. Gills were the most sensitive organ after 2 day-exposure, showing lipid damage and increased SOD activity. After 21 days of exposure, liver was the most sensitive organ, showing lower ACAP, increased LPO levels, and SOD and CAT activities. This is the first study reporting the effects on biochemical markers in D. rerio from a MeTCS sink resulting from sediment spiked with TCS.