• Electronics and Telecommunications Trends
• /
• v.35 no.3
• /
• pp.20-33
• /
• 2020

Temporal action detection (TAD) in untrimmed videos is an important but a challenging problem in the field of computer vision and has gathered increasing interest recently. Although most studies on action in videos have addressed action recognition in trimmed videos, TAD methods are required to understand real-world untrimmed videos, including mostly background and some meaningful action instances belonging to multiple action classes. TAD is mainly composed of temporal action localization that generates temporal action proposals, such as single action and action recognition, which classifies action proposals into action classes. However, the task of generating temporal action proposals with accurate temporal boundaries is challenging in TAD. In this paper, we discuss TAD technologies that are considered high performance in terms of representative TAD studies based on deep learning. Further, we investigate evaluation methodologies for TAD, such as benchmark datasets and performance measures, and subsequently compare the performance of the discussed TAD models.

• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.75-82
• /
• 2021

Online action detection (OAD) in a streaming video is an attractive research area that has aroused interest lately. Although most studies for action understanding have considered action recognition in well-trimmed videos and offline temporal action detection in untrimmed videos, online action detection methods are required to monitor action occurrences in streaming videos. OAD predicts action probabilities for a current frame or frame sequence using a fixed-sized video segment, including past and current frames. In this article, we discuss deep learning-based OAD models. In addition, we investigated OAD evaluation methodologies, including benchmark datasets and performance measures, and compared the performances of the presented OAD models.

• Korean Journal of Culture and Social Issue
• /
• v.8 no.1
• /
• pp.79-101
• /
• 2002

The present study was to investigate the psychological characteristics of Urie(義理; interpersonal morality) in Korean interpersonal relationships in terms of qualitative approach and quantitative approach. In study 1, the authors developed an open-ended questionnaire focused on Urie behavior and not Urie behavior. The results revealed that helping, trusting, and caring behaviors and historicality were the key elements of Urie relationships. On the other hand, selfish and distrusting behaviors disrupted Urie relationships. In study 2, the authors conducted video experiment in order to study how the subjects interpret and understand Urie phenomenon. This video stimulus composed of love and friendship. The main characters showed their conflicts between love and friendship. Thus, subjects were asked to answer their interpretations and understandings about what was going on according to the scene. In study 3, we made three kinds of scenarios which were constituted in conflict situation between close friends who works together at their own company. If one asks some favors to you against social justice, how do you do? Most subjects evaluated the whistle blowing behavior as moral and just. However, they evaluated the insider as not good friend. They evaluated one who did favor even though that behavior was socially unjust as good friend and having Urie. Consequently, Korean people emphasize on their human relationships in everyday life. Urie relationship is built in close and Cheong relationship.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1439-1441
• /
• 2015

본 연구는 비디오 이해를 위해 비디오에 등장하는 주요 객체들의 행동이나 상태를 시각 동사라고 명명하고, 도메인 확장성 있는 계층적 시각 동사의 인식을 위해 온톨로지와 규칙을 기반으로 도메인 독립적인 시각 동사를 계층적으로 인식하는 방법과 특정 도메인에 관련된 시각 동사를 도메인 독립적 시각 동사를 기반으로 확장하여 인식하는 방법을 제안하고, CCTV 감시 비디오에서 인식 시뮬레이션 결과를 보여준다.

• Informatization Policy
• /
• v.29 no.3
• /
• pp.82-104
• /
• 2022

One of the interesting social phenomena in short-form video platforms is the hashtag challenge wherein ordinary users are encouraged to create by imitating short viral videos on a particular theme. Despite the increasing popularity of hashtag challenges, theoretical discussion on related user behavior is still very insufficient. In this study, we attempted to examine the impact of micro-influencers in order to understand users' willingness to participate in hashtag challenges. For this purpose, the para-social interaction theory and imitation behavior literature were adopted as key theoretical basis. In an empirical investigation using 243 survey data from TikTok users, our study found that a user's illusion of intimacy with a micro-influencer (i.e., para-social interaction) had significant positive impact on the intention to participate in a hashtag challenge. This study also showed that the degree of para-social interaction in a short-form video platform was determined by both media content-related factors and media character-related factors (i.e., content attractiveness, physical attractiveness, and attitude homophily). Our work in this study provided significant theoretical and practical implications on how to leverage micro-influencers for the success of hashtag challenges in a short-form video platform.

• Journal of Korea Game Society
• /
• v.21 no.5
• /
• pp.87-104
• /
• 2021

Ludo-narrative dissonance is a prevalent problem among open-world genre video games. However, Ghost of Tsushima (2020) alleviates this issue by designing its characters and narrative structure influenced by Akira Kurosawa's samurai films. The game's protagonist represents "Bushido," a samurai code, and the structure exudes similarity to Joseph Campbell's "Hero's Journey," which heavily influenced Kurosawa's films. The developers also designed the gameplay mechanics such as level-up system, map design, and side quests based on these narrative traits, ultimately making the goal of the narrative and the gameplay mechanics cohesive.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.6
• /
• pp.1502-1508
• /
• 2013

In aspect of HCI(Human Computer Interaction) gameplay is the procedure to solve the problem that gamers encounter in order to generate or discover a new rule to achieve gamers' goal. The goal of this research is to investigate the structure and understand the gameplay in aspect of affordance from ecological psychology rather than the traditional problem solving theory. This research selects App. game based on smart phone. Expert gamers participated in this experiment. We record all gameplay using audio and video device. We conducted protocol analysis as qualitative method based on the verbal report and action protocol during game playing. As result, gameplay based on affordance includes selection and relation. We found that subjects selected one thing at once with attention. Moreover, we found that there were two behaviors : exploratory action and performatory action. We believe that exploration, action, and transformation for affordance appear. The result of this research imply to suggest design guideline for game design methodology when designers develop game.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.170-171
• /
• 2013

In aspect of HCI(Human Computer Interaction) gameplay is the procedure to solve the problem that gamers encounter in order to generate or discover a new rule to achieve gamers' goal. The goal of this research is to investigate the structure and understand the gameplay in aspect of affordance from ecological psychology rather than the traditional problem solving theory. This research selects 'World of Warcraft' as MMORPG(Massively Multiplayer Online Role Playing Game). Five expert gamers participated in this experiment. We record all gameplay using audio and video device. We conducted protocol analysis as qualitative method based on the verbal report and action protocol during game playing. As result, gameplay based on affordance includes selection and relation. We found that subjects selected one thing at once with attention. Moreover, we found that there were two behaviors : exploratory action and performatory action. We believe that learning, utilization, and transformation for affordance appear. The result of this research imply to suggest design guideline for game design methodology when designers develop game.

• The Journal of the Korea Contents Association
• /
• v.11 no.11
• /
• pp.102-110
• /
• 2011

This study is to reveal the meaning of the interaction between a player and a game with the approach of an operational interaction such as joystick and keyboard, and also a representational interaction that the player takes during the game. It has been usually recognized that cut-scene in existing games is just limited to the role of opening scene that delivers mainly a background story of the game, and has the only passive function that serves additionally the expression of the state of the player or the replay of the results of the player's action. But in the aspect of game-direction, the study of the player's action about the interaction movie of 'Uncharted2', for example, one of the most representative video games, shows the possible classification of interaction movie along with three functions(situation direction, induced selective-action, information transfer). As a result, it is judged that interaction movie is not an additional element for the game-play, but rather takes the function of as an interface. The effective application of interaction movie could help a smooth connection between the recognizability from the view point of the player and the playing from the main character's viewpoint, ultimately leading to a direct means to maximize the delivery of the story.

• Journal of Industrial Convergence
• /
• v.20 no.2
• /
• pp.29-36
• /
• 2022

Computational thinking in the AI and Big Data era for digital society means a series of problem-solving methods that involve expressing problems and their solutions in ways that computers can execute. Computational thinking is an approach to solving problems, designing systems, and understanding human behavior by deriving basic concepts in computer science, and solving difficult problems and elusive puzzles for students. We recently studied 93 pre-service teachers who are currently a freshman at ◯◯ university. The results of the first semester class, the participants created a satisfactory algorithm of the video level. Also, the proposed model was found to contribute greatly to the understanding of the computational thinking of the students participating in the class.