• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4412-4428
• /
• 2018

The purpose of this work is to solve the problem of representing an entire video using Convolutional Neural Network (CNN) features for human action recognition. Recently, due to insufficient GPU memory, it has been difficult to take the whole video as the input of the CNN for end-to-end learning. A typical method is to use sampled video frames as inputs and corresponding labels as supervision. One major issue of this popular approach is that the local samples may not contain the information indicated by the global labels and sufficient motion information. To address this issue, we propose a binary hashing method to enhance the local feature extractors. First, we extract the local features and aggregate them into global features using maximum/minimum pooling. Second, we use the binary hashing method to capture the motion features. Finally, we concatenate the hashing features with global features using different normalization methods to train the classifier. Experimental results on the JHMDB and MPII-Cooking datasets show that, for these new local features, binary hashing mapping on the sparsely sampled features led to significant performance improvements.

• Journal of Arbitration Studies
• /
• 제25권2호
• /
• pp.49-70
• /
• 2015

There are three categories of arbitration - domestic arbitration, foreign-related arbitration and foreign arbitration. Although the meaning of foreign arbitration and International Commercial Arbitration is different, they are used to mean the same in practice. In fact, there is significant controversy about the meaning of non-domestic arbitration because it is too difficult to distinguish between non-domestic arbitration and domestic arbitration. In the Chinese arbitration system, there are two main laws,Chinese Arbitration Law and Chinese Civil Procedure Law. Chinese Arbitration Law regulates the internal matters, while Chinese Civil Procedure Law regulates the external legal regulations. After the 2012 revised Chinese Civil Procedure Law, a number of laws and regulations have been revised, and almost every Arbitrations Rules have been revised, and will be in effect in 2015. Depending on the nationality of arbitration, the applicable laws will be different. The nationality of arbitration is so important that this paper will pay more attention to it. Although the case in China has no precedent effect, it is so important to the parties that this paper will address it. This paper will analyze the process and the cases of the recognition and enforcement of the award system in China.

• Journal of Arbitration Studies
• /
• 제27권3호
• /
• pp.53-76
• /
• 2017

Korean businesses, and their legal representatives, have observed the improvements of enforcement of commercial judgments through arbitration over traditional collections litigation in U.S. Courts-due to quicker proceedings, exceptional cost savings and more predictable outcomes-in attaching assets within U.S. jurisdictions. But how are the 2016 interim measures implemented by the Arbitration Act of Korea utilized to avoid jurisdictional and procedure pitfalls of enforcement proceedings in the Federal Courts of the United States? Authors examine the necessary prerequisites of the U.S. Federal Arbitration Act as adopted through the New York Convention, to which Korea and the U.S. are signatories, as distinguished from the Panama Convention. Five common U.S. arbitration institutions address U.S. "domestic" disputes, preempting U.S. state law arbitrations, while this article focuses on U.S. enforcement of "international" arbitration awards. Seeking U.S. recognition and enforcement of Korean arbitral awards necessitates avoiding common defenses involving due process, public policy or documentary formality challenges. Provisional and conservatory injunctive relief measures are explored. A variety of U.S. cases involving Korean litigants are examined to illustrate the legal challenges involving non?domestic arbitral awards, foreign arbitral awards and injunctive relief. Suggestions aimed toward further research are focused on typical Korean business needs such as motions to confirm foreign arbitration awards, enforce such awards or motions to compel arbitration.

• Journal of Advanced Technology Convergence
• /
• 제2권4호
• /
• pp.7-11
• /
• 2023

In this study, we presented a method to recognize vehicle license plates using CNN techniques. A vehicle plate is normally used for the official identification purposes by the authorities. Most regular Optical Character Recognition (OCR) techniques perform well in recognizing printed characters on documents but cannot make out the registration number on the number plates. Besides, the existing approaches to plate number detection require that the vehicle is stationary and not in motion. To address these challenges to number plate detection we make the following contributions. We create a database of captured vehicle number plate's images and recognize the number plate character using Convolutional Neural Networks. The results of this study can be usefully used in parking management systems and enforcement cameras.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.774-776
• /
• 2024

The effective implementation of advanced speech recognition (ASR) systems necessitates the deployment of sophisticated keyword spotting models that are both responsive and resource-efficient. The initial local detection of user interactions is crucial as it allows for the selective transmission of audio data to cloud services, thereby reducing operational costs and mitigating privacy risks associated with continuous data streaming. In this paper, we address these needs and propose utilizing the Whisper-Tiny model with fine-tuning process to specifically recognize keywords from google speech dataset which includes 65000 audio clips of keyword commands. By adapting the model's encoder and appending a lightweight classification head, we ensure that it operates within the limited resource constraints of local devices. The proposed model achieves the notable test accuracy of 92.94%. This architecture demonstrates the efficiency as on-device model with stringent resources leading to enhanced accessibility in everyday speech recognition applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2103-2118
• /
• 2024

Chinese herbal slices (CHS) automated recognition based on computer vision plays a critical role in the practical application of intelligent Chinese medicine. Due to the complexity and similarity of herbal images, identifying Chinese herbal slices is still a challenging task. Especially, easily-confused CHS have higher inter-class and intra-class complexity and similarity issues, the existing deep learning models are less adaptable to identify them efficiently. To comprehensively address these problems, a novel tiny easily-confused CHS dataset has been built firstly, which includes six pairs of twelve categories with about 2395 samples. Furthermore, we propose a ResNeSt-CHS model that combines multilevel perception fusion (MPF) and perceptive sparse fusion (PSF) blocks for efficiently recognizing easilyconfused CHS images. To verify the superiority of the ResNeSt-CHS and the effectiveness of our dataset, experiments have been employed, validating that the ResNeSt-CHS is optimal for easily-confused CHS recognition, with 2.1% improvement of the original ResNeSt model. Additionally, the results indicate that ResNeSt-CHS is applied on a relatively small-scale dataset yet high accuracy. This model has obtained state-of-the-art easily-confused CHS classification performance, with accuracy of 90.8%, far beyond other models (EfficientNet, Transformer, and ResNeSt, etc) in terms of evaluation criteria.

• Journal of Broadcast Engineering
• /
• 제23권1호
• /
• pp.154-161
• /
• 2018

As the number of smartphone users increases, research on indoor location recognition service is necessary. Access to indoor locations is predominantly WiFi, Bluetooth, etc., but in most quarters, WiFi is equipped with WiFi functionality, which uses WiFi features to provide WiFi functionality. The study uses the random forest algorithm, which employs the fingerprint index of the acquired WiFi and the use of the multI-value classification method, which employs the receiver signal strength of the acquired WiFi. As the data of the fingerprint, a total of 4 radio maps using the Mac address together with the received signal strength were used. The experiment was conducted in a limited indoor space and compared to an indoor location recognition system using an existing random forest, similar to the method proposed in this study for experimental analysis. Experiments have shown that the system's positioning accuracy as suggested by this study is approximately 5.8 % higher than that of a conventional indoor location recognition system using a random forest, and that its location recognition speed is consistent and faster than that of a study.

• Journal of KIISE:Computing Practices and Letters
• /
• 제16권4호
• /
• pp.482-486
• /
• 2010

Recently, gesture recognition methods based on dynamic time warping (DTW) have been actively investigated as more mobile devices have equipped the accelerometer. DTW has no additional training step since it uses given samples as the matching templates. However, it is difficult to apply the DTW on mobile environments because of its computational complexity of matching step where the input pattern has to be compared with every templates. In order to address the problem, this paper proposes a gesture recognition method based on DTW that uses localized subset of templates. Here, the k-means clustering algorithm is used to divide each class into subclasses in which the most centered sample in each subclass is employed as the localized template. It increases the recognition speed by reducing the number of matches while it minimizes the errors by preserving the diversities of the training patterns. Experimental results showed that the proposed method was about five times faster than the DTW with all training samples, and more stable than the randomly selected templates.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3172-3193
• /
• 2018

Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.

• Journal of Digital Convergence
• /
• 제18권3호
• /
• pp.13-21
• /
• 2020

This study aims to provide the policy implications for the Korean government which has to attract foreign workers with higher education degrees in order to address shortage of human resources. As a way of doing this, the study has compared the foreign qualification evaluation and recognition (FQER) systems in Germany, Denmark and Norway. The results of the study reveal that the three countries are similar in that they have developed their own FQER systems according to the Lisbon Recognition Convention and has thus provided everyone with opportunities to have his/her qualifications evaluated fairly. However, there are differences in terms of the evaluation target, the recognition of prior learning and the linkage between the evaluation and employment approval for foreigners among the three countries. These cases altogether provide meaningful policy implications for the Korean government that has to develop its own FQER system in the near future.