Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.
In pedestrian detection applications, one of the most popular frameworks that has received extensive attention in recent years is widely known as a 'Hough forest' (HF). To improve the accuracy of detection, this paper proposes a novel split function to exploit the statistical information of the training set stored in each node during the construction of the forest. The proposed split function makes the trees in the forest more robust to noise and illumination changes. Moreover, the errors of each stage in the training forest are minimized using a global loss function to support trees to track harder training samples. After having the forest trained, the standard HF detector follows up to search for and localize instances in the image. Experimental results showed that the detection performance of the proposed framework was improved significantly with respect to the standard HF and alternating decision forest (ADF) in some public datasets.
The paper presents new method to improve computational performance by introducing the mutual spatial feature in order to make strong visual cue in image parsing problem based on non-parametric model. This feature models the spatial context and mutual information in our previous study [1] to enhance accuracy and performance of image parsing problem in calculating the probability of co-occurrence objects. The experimental results based on Matlab programming language using SIFTFlow and Barcelona datasets showed that the mutualspatial feature is promising to refine image parsing problem.
Beta-glucosidase enzyme belongs to family GH3 is widely used in food, medicine and pharmaceutical industries. In order to quickly search for these enzyme coding sequences from DNA metagenomic data, in this study, bacterial-derived enzyme-coding sequences which was investigated empirically on the CAZy database was collected. By analogy, we have developed that a specific probe for beta-glucosidase GH3 had a length of 330 amino acids, which contains 26 conserved residues in all sequences, 37 residues similar in almost sequences, and 21 residues conserved in many sequences and homologous with all the reference sequences with the lowest coverage and identity of 79% and 38% respectively and max score of 122. Probe was used and extracted 59 coded sequences of beta-glucosidase GH3 from the metagenome DNA sequences of goat rumen bacteria. The most ORFs were annotated as beta-glucosidase GH3 by KEGG and CAZy. The sequences are estimated to have a tertiary structure similar to beta-glucosidase.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.