• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1535-1545
• /
• 2022

Sign language has completely different meaning depending on the direction of the hand or the change of facial expression even with the same gesture. In this respect, it is crucial to capture the spatial-temporal structure information of each movement. However, sign language translation studies based on Sign2Gloss2Text only convey comprehensive spatial-temporal information about the entire sign language movement. Consequently, detailed information (facial expression, gestures, and etc.) of each movement that is important for sign language translation is not emphasized. Accordingly, in this paper, we propose Spatial-temporal Keypoints Centered Sign2Gloss2Text Translation, named STKC-Sign2 Gloss2Text, to supplement the sequential and semantic information of keypoints which are the core of recognizing and translating sign language. STKC-Sign2Gloss2Text consists of two steps, Spatial Keypoints Embedding, which extracts 121 major keypoints from each image, and Temporal Keypoints Embedding, which emphasizes sequential information using Bi-GRU for extracted keypoints of sign language. The proposed model outperformed all Bilingual Evaluation Understudy(BLEU) scores in Development(DEV) and Testing(TEST) than Sign2Gloss2Text as the baseline, and in particular, it proved the effectiveness of the proposed methodology by achieving 23.19, an improvement of 1.87 based on TEST BLEU-4.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.5
• /
• pp.836-847
• /
• 2020

Objective: We investigated the temporal expression profiles of long noncoding RNA (lncRNA) and mRNA in the peripheral blood of pigs during development and identified the lncRNAs that are related to the blood-based immune system. Methods: Peripheral blood samples were obtained from the pigs at 0, 7, 28, and 180 days and 2 years of age. RNA sequencing was performed to survey the lncRNA and mRNA transcriptomes in the samples. Short time-series expression miner (STEM) was used to show temporal expression patterns in the mRNAs and lncRNAs. Gene ontology and Kyoto encyclopedia of genes and genomes analyses were performed to assess the genes' biological relevance. To predict the functions of the identified lncRNAs, we extracted mRNAs that were nearby loci and highly correlated with the lncRNAs. Results: In total of 5,946 lncRNA and 12,354 mRNA transcripts were identified among the samples. STEM showed that most lncRNAs and mRNAs had similar temporal expression patterns during development, indicating the expressional correlation and functional relatedness between them. The five stages were divided into two classes: the suckling period and the late developmental stage. Most genes were expressed at low level during the suckling period, but at higher level during the late stages. Expression of several T-cell-related genes increased continuously during the suckling period, indicating that these genes are crucial for establishing the adaptive immune system in piglets at this stage. Notably, lncRNA TCONS-00086451 may promote blood-based immune system development by upregulating nuclear factor of activated T-cells cytoplasmic 2 expression. Conclusion: This study provides a catalog of porcine peripheral blood-related lncRNAs and mRNAs and reveals the characteristics and temporal expression profiles of these lncRNAs and mRNAs during peripheral blood development from the newborn to adult stages in pigs.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.3
• /
• pp.284-291
• /
• 2005

I propose a framework for detecting, recognizing and classifying facial features based on learned expression patterns. The framework recognizes facial expressions by using PCA and expression HMM(EHMM) which is Hidden Markov Model (HMM) approach to represent the spatial information and the temporal dynamics of the time varying visual expression patterns. Because the low level spatial feature extraction is fused with the temporal analysis, a unified spatio-temporal approach of HMM to common detection, tracking and classification problems is effective. The proposed recognition framework is accomplished by applying posterior probability between current visual observations and previous visual evidences. Consequently, the framework shows accurate and robust results of recognition on as well simple expressions as basic 6 facial feature patterns. The method allows us to perform a set of important tasks such as facial-expression recognition, HCI and key-frame extraction.

• Molecules and Cells
• /
• v.21 no.3
• /
• pp.436-442
• /
• 2006

Different proliferation of neuroblast 6-4 (NB6-4) in the thorax and abdomen produces segmental specific expression pattern of several neuroblast marker genes. NB6-4 is divided to form four medialmost cell body glia (MM-CBG) per segment in thorax and two MM-CBG per segment in abdomen. As homeotic genes determine the identities of embryonic segments along the A/P axis, we investigated if temporal and specific expression of homeotic genes affects MM-CBG patterns in thorax and abdomen. A Ubx loss-of-function mutation was found to hardly affect MM-CBG formation, whereas abd-A and Abd-B caused the transformation of abdominal MM-CBG to their thoracic counterparts. On the other hand, gain-of-function mutants of Ubx, abd-A and Abd-B genes reduced the number of thoracic MM-CBG, indicating that thoracic MM-CBG resembled abdominal MM-CBG. However, mutations in Polycomb group (PcG) genes, which are negative transregulators of homeotic genes, did not cause the thoracic to abdominal MM-CBG pattern transformation although the number of MM-CBG in a few percent of embryos were partially reduced or abnormally patterned. Our results indicate that temporal and spatial expression of the homeotic genes is important to determine segmental-specificity of NB6-4 daughter cells along the anterior-posterior (A/P) axis.

• Molecules and Cells
• /
• v.39 no.2
• /
• pp.136-140
• /
• 2016

Eph receptors and their ligands, ephrins, mediate cell-to-cell contacts in a specific brain region and their bidirectional signaling is implicated in the regulation of apoptosis during early brain development. In this report, we used the alpha(${\alpha}$)-Cre transgenic line to induce ephrin-A5 over-expression in the distal region of the neural retina. Using this double transgenic embryo, we show that the over-expression of ephrin-A5 was responsible for inducing massive apoptosis in both the nasal and temporal retinas. In addition, the number of differentiated retinal neurons with the exception of the bipolar neuron was significantly reduced, whereas the laminar organization of the mature retina remained intact. Consistent with this finding, an analysis of the mature retina revealed that the size of the whole retina-particularly the nasal and temporal regions-is markedly reduced. These results strongly suggest that the level of ephrin-A5 expression plays a role in the regulation of the size of the retinal progenitor pool in the neural retina.

• Journal of Korean Institute of Industrial Engineers
• /
• v.16 no.2
• /
• pp.63-70
• /
• 1990

This paper presents a new temporal reasoning scheme based on explicit expression of time intervals. The proposed scheme deals with the general problem of temporal knowledge representation and temporal reasoning and may be used in rule-based systems and qualitative models. Time intervals, not time points, are defined in terms of orders and/or numbers in a quantity space. As a result, the system behavior is represented in the form of partially ordered networks. Such explicit and qualitative description of temporal quantities enables both reduction of ambiguity and parsimonious used of temporal information. Based on the proposed temporal reasoning scheme, a new rule-based qualitative simulation system is being built and evaluated.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.35-48
• /
• 2017

Extracting temporal information from documents is becoming more important, because it can be used to various applications such as Question-Answering (QA) systems, Recommendation systems, or Information Retrieval (IR) systems. Most previous studies only focus on English documents, and they are not applicable to the other languages due to the inherent characteristics of languages. In this paper, we propose a new system, named ExoTime, designed to extract temporal information from Korean documents. The ExoTime adopts an external Knowledge Base (KB) in order to achieve better prediction performance, and it also applies a bagging method to the temporal relation prediction. We show that the effectiveness of the proposed approaches by empirical results using Korean TimeBank. The ExoTime system works as a part of ExoBrain that is an artificial intelligent QA system.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.3
• /
• pp.149-157
• /
• 2001

In the video retrieval system, visual clues of still images and motion information of video are employed as feature vectors. We generate the temporal textures to express the motion information whose properties are simple expression, easy to compute. We make those temporal textures of wavelet coefficients to express motion information, M components. Then, temporal texture feature vectors are extracted using spatial texture feature vectors, i.e. spatial gray-level dependence. Also, motion amount and motion centroid are computed from temporal textures. Motion trajectories provide the most important information for expressing the motion property. In our modeling system, we can extract the main motion trajectory from the temporal textures.

• Animal cells and systems
• /
• v.1 no.4
• /
• pp.589-594
• /
• 1997

The neuronal voltage-sensitive calcium channels (VSCCs) are multisubunit complexes consisting of $\alpha_1,\;\alpha_2-\delta$ and $\beta$ subunits. Heterologous expression and biochemical studies have shown that the activity of VSCCs is regulated by their $\beta$ subunits in a $\beta$ subunit isoform-specific manner. To elucidate the $\beta$ subunit identity of the P/Q-type calcium channel encoded by an $\alpha_{1A}$ subunit, which is exclusively expressed in the Purkinje and granule cell of the cerebellum, we have examined the spatial and temporal expression patterns of $\beta$ subunits and compared them with those of $\alpha_{1A}$ subunit in the developing rat cerebellum. Reverse transcriptase- polymerase chain reaction (RT-PCR) and Northern blot analysis have shown that $\beta_4$ subunit mRNA was prominently expressed in the cerebellum and much more abundant than any other distinct $\beta$ subunits. RNase protection assay has further demonstrated that the expression of $\alpha_{1A}$ and $\beta_4$ subunits increased during cerebellar development, while the amount of $\beta_2$ and $\beta_3$ mRNAs did not significantly change. In addition, a $\beta_4$ transcript was present in cultured cerebellar granule cells, but not in astrocyte cells, and the level of $\beta_4$ mRNA expression increased gradually in vitro seen as in vivo. Based on the spatial and temporal expression patterns of $\beta_4$ subunit, we conclude that $\beta_4$ may predominantly associate, but probably not exclusively, with the $\alpha_{1A}$ subunit in rat cerebellar granule cells.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.564-566
• /
• 2003

There are no immutable phenomena in reality. A lot of applications are dealing with data characterized by spatial and temporal and/or uncertain features. Currently, there has no any data model accommodating enough those three elements of spatial objects to directly use in application systems. For such reasons, we introduce a fuzzy spatio -temporal data model (FSTDM) and a method of integrating temporal and fuzzy spatial operators in a unified manner to create fuzzy spatio -temporal (FST) operators. With these operators, complex query expression will become concise. Our research is feasible to apply to the management systems and query processor of natural resource data, weather information, graphic information, and so on.