Energy-Guided Temporal Segmentation Network for Multimodal Human Action Recognition.

To achieve the satisfactory performance of human action recognition, a central task is to address the sub-action sharing problem, especially in similar action classes. Nevertheless, most existing convolutional neural network (CNN)-based action recognition algorithms uniformly divide video into frames and then randomly select the frames as inputs, ignoring the distinct characteristics among different frames. In recent years, depth videos have been increasingly used for action recognition, but most methods merely focus on the spatial information of the different actions without utilizing temporal information. In order to address these issues, a novel energy-guided temporal segmentation method is proposed here, and a multimodal fusion strategy is employed with the proposed segmentation method to construct an energy-guided temporal segmentation network (EGTSN). Specifically, the EGTSN had two parts: energy-guided video segmentation and a multimodal fusion heterogeneous CNN. The proposed solution was evaluated on a public large-scale NTU RGB+D dataset. Comparisons with state-of-the-art methods demonstrate the effectiveness of the proposed network.

Synthesis, biological evaluation of benzothiazole derivatives bearing a 1,3,4-oxadiazole moiety as potential anti-oxidant and anti-inflammatory agents.

Twenty benzothiazole derivatives bearing a 1,3,4-oxadiazole moiety were synthesized and evaluated for their anti-oxidant and anti-inflammatory activities. Among these compounds, 8h and 8l were appeared to have high radical scavenging efficacies as 0.05 ± 0.02 and 0.07 ± 0.03 mmol/L of IC50 values in ABTS+ bioassay, respectively. In anti-inflammatory tests, compound 8h displayed good activity with 57.35% inhibition after intraperitoneal administration, which was more potent than the reference drug (indomethacin). Molecular modeling studies were performed to investigate the binding mode of the representative compound 8h into COX-2 enzyme. In vitro enzyme study implied that compound 8h exerted its anti-inflammatory activity through COX-2 inhibition.

Exploring Inter-Instance Relationships within the Query Set for Robust Image Set Matching.

Image set matching (ISM) has attracted increasing attention in the field of computer vision and pattern recognition. Some studies attempt to model query and gallery sets under a joint or collaborative representation framework, achieving impressive performance. However, existing models consider only the competition and collaboration among gallery sets, neglecting the inter-instance relationships within the query set which are also regarded as one important clue for ISM. In this paper, inter-instance relationships within the query set are explored for robust image set matching. Specifically, we propose to represent the query set instances jointly via a combined dictionary learned from the gallery sets. To explore the commonality and variations within the query set simultaneously to benefit the matching, both low rank and class-level sparsity constraints are imposed on the representation coefficients. Then, to deal with nonlinear data in real scenarios, the'kernelized version is also proposed. Moreover, to tackle the gross corruptions mixed in the query set, the proposed model is extended for robust ISM. The optimization problems are solved efficiently by employing singular value thresholding and block soft thresholding operators in an alternating direction manner. Experiments on five public datasets demonstrate the effectiveness of the proposed method, comparing favorably with state-of-the-art methods.

Synthesis of 2-alkynyl substituted 4'-thioadenosine derivatives and their binding affinities at the adenosine receptors.

On the basis of high binding affinity of 2-hexynyl-N(6)-methyladenosine and N(6)-substituted-4'-thioadenosine derivatives at the A3 adenosine receptor (AR), novel 2-alkynyl-substituted-N(6)-methyl-4'-thioadenosine derivatives, combining the characteristics of two classes of nucleosides were designed and synthesized from D-gulonic gamma-lactone via palladium-catalyzed cross coupling reaction as a key step. Among compounds tested, only compound 3b showed moderate binding affinity at the human A3 adenosine receptor without binding affinities at other subtypes.