• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4041-4059
• /
• 2019

Key establishment method based on channel reciprocity for time division duplex (TDD) system has earned a vital consideration in the majority of recent research. While most of the cellular systems rely on frequency division duplex (FDD) systems, especially the 5G network, which is not characterized by the channel reciprocity feature. This paper realizes the generation of a group secret key for multi-terminals communicated through a wireless network in FDD mode, by utilizing the nature of the physical layer for the wireless links between them. I consider a new group key generation approach, which using bitwise XOR with a modified pairwise secret key generation approach not based on the channel reciprocity feature. Precisely, this multi-node secret key agreement technique designed for three wireless network topologies: 1) the triangle topology, 2) the multi-terminal star topology, and 3) the multi-node chain topology. Three multi-node secret key agreement protocols suggest for these wireless communication topologies in FDD mode, respectively. I determine the upper bound for the generation rate of the secret key shared among multi-node, for the three multi-terminals topologies, and give numerical cases to expose the achievement of my offered technique.

• 한국의류학회지
• /
• 제45권2호
• /
• pp.217-232
• /
• 2021

This study analyzed the characteristics of generation Z leading the trend of the fashion industry through the creative activity of Virgil Abloh. A literature review and case study were conducted together with detailing the research methodology. As a result of research, generation Z is conceptualized as a "digital native" who grows in digital technology environment with excellent visual sense. They are "SNS creators" who have influence on Social Networking Services (SNS). They are also characterized as "social activists" who reject social conventions and prejudices. They are a "leading creators" who seek to differentiate with creativity. The characteristics of generation Z in the creative activities of Virgil Abloh have a feature of digital native in that they seek visual originality. In terms of communicating with generation Z through SNS and influencer marketing, it has the characteristics of SNS creators. It expresses social activists in providing consumers with diversity, and social perceptions of differentiation. In terms of providing content that encourages consumers to express their personality, it has a feature of leading creators. It is meaningful in that it contributes to the understanding of the market change and marketing strategy according to the consumer development and the activity of the fashion designer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권2호
• /
• pp.110-114
• /
• 2015

This paper reports a novel object-detection technique in video sequences. The proposed algorithm consists of detection of objects in illuminated and occluded videos by using object features and a neural network technique. It consists of two functional modules: region-based object feature extraction and continuous detection of objects in video sequences with region features. This scheme is proposed as an enhancement of the Lowe's scale-invariant feature transform (SIFT) object detection method. This technique solved the high computation time problem of feature generation in the SIFT method. The improvement is achieved by region-based feature classification in the objects to be detected; optimal neural network-based feature reduction is presented in order to reduce the object region feature dataset with winner pixel estimation between the video frames of the video sequence. Simulation results show that the proposed scheme achieves better overall performance than other object detection techniques, and region-based feature detection is faster in comparison to other recent techniques.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1281-1288
• /
• 2015

Nongroup Cellular Automata(CA) having two trees in the state transition diagram of a CA is suitable for pattern classifier which divides pattern set into two classes. Maji et al. [1] classified patterns by using multiple attractor cellular automata as a pattern classifier with dependency vector. In this paper we propose a method of generation of a pattern classifier using feature vector which is the extension of dependency vector. In addition, we propose methods for finding nonreachable states in the 0-tree of the state transition diagram of TPMACA corresponding to the given feature vector for the analysis of the state transition behavior of the generated pattern classifier.

• Journal of Multimedia Information System
• /
• 제6권1호
• /
• pp.15-22
• /
• 2019

There are many ways to perform face recognition. The first step of face recognition is the face detection step. If the face is not found in the first step, the face recognition fails. Face detection research has many difficulties because it can be varied according to face size change, left and right rotation and up and down rotation, side face and front face, facial expression, and light condition. In this study, facial features are extracted and the extracted features are geometrically reconstructed in order to improve face recognition rate in extracted face region. Also, it is aimed to adjust face angle using reconstructed facial feature vector, and to improve recognition rate for each face angle. In the recognition attempt using the result after the geometric reconstruction, both the up and down and the left and right facial angles have improved recognition performance.

• 제어로봇시스템학회논문지
• /
• 제12권3호
• /
• pp.255-263
• /
• 2006

In the last decade, face analysis, e.g. face detection, face recognition, facial expression recognition, is a very lively and expanding research field. As computer animated agents and robots bring a social dimension to human computer interaction, interest in this research field is increasing rapidly. In this paper, we introduce an artificial emotion mimic system which can recognize human facial expressions and also generate the recognized facial expression. In order to recognize human facial expression in real-time, we propose a facial expression classification method that is performed by weak classifiers obtained by using new rectangular feature types. In addition, we make the artificial facial expression using the developed robotic system based on biological observation. Finally, experimental results of facial expression recognition and generation are shown for the validity of our robotic system.

• 한국CDE학회논문집
• /
• 제6권4호
• /
• pp.244-253
• /
• 2001

For more complete process planning, machining sequence determination is critical to attain machining economics. Although many studies have been conducted in recent years, most of them suggests the non-unique machining sequences. When the tool approach directions(TAD) are considered fur a feature, both machining time and number of setups can be reduced. Then, the unique machining sequence can be extracted from alternate(non-unique) sequences by minimizing the idle time between operations within a sequence. This study develops an algorithm to generate the best machining sequence for composite prismatic features in a vertical milling operation. The algorithm contains five steps to produce an unique sequence: a precedence relation matrix(PRM) development, tool approach direction determination, machining time calculation, alternate machining sequence generation, and finally, best machining sequence generation with idle times. As a result, the study shows that the algorithm is effective for a given composite feature and can be applicable fur other prismatic parts.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1318-1330
• /
• 2018

Video captioning refers to the process of extracting features from a video and generating video captions using the extracted features. This paper introduces a deep neural network model and its learning method for effective video captioning. In this study, visual features as well as semantic features, which effectively express the video, are also used. The visual features of the video are extracted using convolutional neural networks, such as C3D and ResNet, while the semantic features are extracted using a semantic feature extraction network proposed in this paper. Further, an attention-based caption generation network is proposed for effective generation of video captions using the extracted features. The performance and effectiveness of the proposed model is verified through various experiments using two large-scale video benchmarks such as the Microsoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).