Trajectory-pooled Deep-learning Descriptors have been the state-of-the-art feature descriptors for human action recognition in video on many datasets. This paper improves their performance by applying the proposed eigen-evolution pooling to each trajectory, encoding the temporal evolution of deep learning features computed along the trajectory. This leads to Eigen-Evolution Trajectory (EET) des...

In the literature of pattern recognition and computer vision, local descriptors have been widely used in applications such as shape matching and object recognition. Numerous descriptors have been proposed and evaluated, but little work is reported in the area of medical image, especially ultrasonic images. In this paper, we assess the performance of different local descriptors to detect specifi...

Despite the progress made in the area of local image descriptors in recent years, virtually no literature is available on the use of more recent descriptors for the problem of 3D face recognition, such as BRIEF, ORB, BRISK or FREAK, which are binary in nature and, therefore, tend to be faster to compute and match, while requiring significantly less memory for storage than, for example, SIFT or ...

The ability to predict organ-specific carcinogenicity would aid FDA reviewers in evaluating new chemical applications. A NCTR liver cancer database (NCTRlcdb) containing 999 compounds has been developed with three sets of descriptors. The NCTRlcdb has Cerius2, Molconn-Z, and (13)C NMR descriptors for each compound. Each compound in the database was assigned a liver cancer or a nonliver cancer c...

Proteochemometrics is a technology for the study of molecular recognition based on chemometric techniques. Here we applied it to analyse the amino acids and amino acid physico-chemical properties that are involved in antibodies' recognition of peptide antigens. To this end, we used a study system comprised by a diverse single chain antibody library derived from the murine mAb anti-p24 (HIV-1) a...

We propose a reinforcement learning approach for an adaptive selection and application of 3D point cloud feature descriptors for the purpose of 3D object classification. The result of the learning process is an autonomously learned strategy of selection of descriptors with the property that the successive application of these descriptors to a 3D point cloud yields high classification rates amon...

Analyzing protein binding sites provides detailed insights into the biological processes proteins are involved in, e.g., into drug-target interactions, and so is of crucial importance in drug discovery. Herein, we present novel alignment-independent binding site descriptors based on DrugScore potential fields. The potential fields are transformed to a set of information-rich descriptors using a...

The aim of the present paper is to present the methodology of the molecular descriptors family (MDF) as an integrative tool in molecular modeling and its abilities as a multivariate QSAR/QSPR modeling tool. An algorithm for extracting useful information from the topological and geometrical representation of chemical compounds was developed and integrated to calculate MDF members. The MDF method...

At the core of a myriad of tasks such as object recognition, tridimensional reconstruction and alignment resides the critical problem of correspondence. Hence, devising descriptors, which identify the entities to be matched and that are able to correctly and reliably establish pairs of corresponding points is of central importance. We introduce three novel descriptors that efficiently combine a...

Embedding a face image to descriptor vector using deep CNN is widely used technique in recognition. Via several possible training strategies, such embeddings are supposed capture only identity information. Information about the environment (such as background and lighting) or changeable aspects of pose, expression, presence glasses, hat etc.) should be discarded since they not useful for In thi...