• ETRI Journal
• /
• v.42 no.2
• /
• pp.230-238
• /
• 2020

Human-object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extractor followed by detection layers comprising small filters (eg, 1 × 1 or 3 × 3). Although small filters can capture local spatial features with a few parameters, they fail to capture larger context information relevant for recognizing interactions between humans and distant objects owing to their small receptive regions. Hence, we herein propose a three-stream HOI detection network that employs a context convolution module (CCM) in each stream branch. The CCM can capture larger contexts from input feature maps by adopting combinations of large separable convolution layers and residual-based convolution layers without increasing the number of parameters by using fewer large separable filters. We evaluate our HOI detection method using two benchmark datasets, V-COCO and HICO-DET, and demonstrate its state-of-the-art performance.

• ETRI Journal
• /
• v.30 no.3
• /
• pp.486-488
• /
• 2008

In this paper, a scheme to increase the throughput of RFID systems is presented, which considers the capture effect in the context of framed ALOHA protocol. Under the capture model in which the probability of one tag is identified successfully depending on the number of tags involved in the collision, two probabilistic methods for estimating the unknown number of tags are proposed. The first method is the maximum likelihood estimation method, and the second method is an approximate algorithm for reducing the computational time. The optimal frame size condition to maximize the system throughput by considering the capture effect is also presented.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.9 no.1
• /
• pp.1-9
• /
• 2014

As Android platform and its applications are widely used, it is necessary to assure the reliability and safety of Android applications. The capture and replay technique is widely used for reproducing the crashes in Java applications. In this paper, we adapt the context-based capture and replay technique to Android applications by considering Android activity structure and its GUI characteristics. Our capture and replay technique uses probe code insertion based on AspectJ for minimizing the original code change and for enhancing the efficiency and reusability of the probe codes. For proving the efficiency of our technique, we provide a case study and execution overhead comparisons with related works, in which our approach has merits in GUI oriented Android applications with relatively low execution overhead.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.4
• /
• pp.249-256
• /
• 2022

In the case of Drone Photogrammetry, the "pixel to point tool" module of Metashape, Pix4D Mapper, ContextCapture, and Global MapperGIS, which is a simple software, are widely used. Each SW has its own logic for the analysis of aerial triangulation, but from the user's point of view, it is necessary to select a SW by comparative analysis of the coordinate values of geospatial information for the result. Taking aerial photos for drone photogrammetry, surveying GCP reference points through VRS-GPS Survey, processing the acquired basic data using each SW to construct ortho image and DSM, and GCPSurvey performance and acquisition from each SW The coordinates (X,Y) of the center point of the GCP target on the Ortho-Image and the height value (EL) of the GCP point by DSM were compared. According to the "Public Surveying Work Regulations", the results of each SW are all within the margin of error. It turned out that there is no problem with the regulations no matter which SW is included within the scope.

• Journal of Korea Multimedia Society
• /
• v.10 no.6
• /
• pp.786-798
• /
• 2007

As we go about our daily lives, people often collect surrounding information and adapt to the situation. Computer development trends show that one wants computers to work like human beings, i.e. computers can sense its context and adapt corresponding to context changes. To implement this expectation, a context aware service layer is needed. In this layer, sensors capture its environment and send this information to the service center. Considering received information as its context, the service center seeks the suitable operation according to the context. Tills paper presents a context aware service which is applied in controlling air-conditioner. The air-conditioner includes sensors which are installed at some special positions in a room. Each of these sensors gathers comfort-influenced information like temperature, humidity and sends them to air-conditioner. The air-conditioner adapts its operation to the environment according to the sensed information. To control the air-conditioner effectively, we use a genetic algorithm which is suitable in adaptation issues. The simulation shows that the room condition can be maintained at a comfortable level by using context-aware services in the operation of the air-conditioning system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1396-1412
• /
• 2023

Conversation modeling is an important and challenging task in the field of natural language processing because it is a key component promoting the development of automated humanmachine conversation. Most recent research concerning conversation modeling focuses only on the current utterance (considered as the current question) to generate a response, and thus fails to capture the conversation's logic from its beginning. Some studies concatenate the current question with previous conversation sentences and use it as input for response generation. Another approach is to use an encoder to store all previous utterances. Each time a new question is encountered, the encoder is updated and used to generate the response. Our approach in this paper differs from previous studies in that we explicitly separate the encoding of the question from the encoding of its context. This results in different encoding models for the question and the context, capturing the specificity of each. In this way, we have access to the entire context when generating the response. To this end, we propose a deep neural network-based model, called the Context Model, to encode previous utterances' information and combine it with the current question. This approach satisfies the need for context information while keeping the different roles of the current question and its context separate while generating a response. We investigate two approaches for representing the context: Long short-term memory and Convolutional neural network. Experiments show that our Context Model outperforms a baseline model on both ConvAI2 Dataset and a collected dataset of conversational English.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.2
• /
• pp.99-113
• /
• 1992

In general, TDMA and FDMA have been used for multiple access communication methods. Recently. However, ALOHA and CSMA protocols came to exist as new schemes for VSAT data networks and LANs, respectively. These schemes are proven to be effective for packet switched communication systems that has bursty traffic but packet collisions. In this paper we analyze capture statistics arising from fading channels in packet radio communication systems in the context of ALOHA protocol. We derive general results of the exact form of capture probabilities and present numerical data for wide range of fading parameters. Since the capture probabilities are found to approach zero when the number of transmitted signals become larger, we are able to determine the achievable channel throughput by a least squares fitting of an exponential-type function to the probabilities.

• Journal of Korean Society for Geospatial Information Science
• /
• v.5 no.2 s.10
• /
• pp.55-63
• /
• 1997

Precision digital data capture and spatial analysis system to cultural properties play important roles in preserving the existing properties. This study presents the acquisition oi digital data in geometrical context and spatial analysis for more effective management to cultural properties. Established in the same coordinates system, Precision 3D measurements and image analysis were peformed. In addition, geometrical analysis, and 3D monitoring to Songsanri Royals Tombs in Gongju were carried out in generating basedata for conservation plan.

• 한국경영정보학회:학술대회논문집
• /
• 2007.11a
• /
• pp.273-277
• /
• 2007

Ubiquitous computing environment accelerates the advent of the IT Ecosystem. In the coming generation, a massive number of ubiquitous devices and services are converged into an ultra-large-scale system. In this context, high degrees of complexity and organization change the paradigm of knowledge and its management levels. The objective of this paper is to explore the Knowledge Management Systems in view of demands in ultra-large-scale systems. We introduce motivation for Next-Generation (NG) usage and their upcoming requirements. The possible applications will be discussed, and summary of different techniques are conducted. The tools and techniques that allow KMS to operate as "Vital Success Enabler" to achieve organizational benefits will be examined. Potential future directions for research are highlighted: these include advances in knowledge capture, storage / retrieval and sharing techniques, in particular with the surrounding role of information technology.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.714-718
• /
• 2005

Knowledge management (KM) continues to receive mounting interest within the construction industry due to its potential to offer solutions for organisations seeking competitive advantage. This paper presents a KM input-process-output conceptual model comprising unique and well-defined theoretical constructs representing KM practices and their internal and external determinants in the context of construction. The paper also presents the underlying principles used in operationally defining each construct using extant KM literature, and offers a number of testable hypotheses that capture the inter-relationships between the identified constructs.