James Won‐Ki Hong
포항공과대학교 컴퓨터공학과 · 컴퓨터과학
James Won-ki Hong 교수의 연구실은 비디오 이해 및 딥러닝 기반 영상 분석 분야에서 주로 활동하고 있습니다. 특히 스포츠 동작 인식에서 신뢰할 수 없는 포즈 추론 문제를 해결하기 위한 약한 지도 학습 기반 비디오 포즈 distillation 기법을 개발하며, 실생활 영상 환경에서의 강건한 특징 학습을 목표로 합니다. 또한 블록체인 기반 NFT 기술의 표준화와 응용에 관한 연구를 통해 디지털 자산의 소유권 관리 및 시장 동향 분석에도 기여하고 있습니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor accuracy when downstream tasks, such as action recognition, depend on pose. End-to-end learning circumvents pose, but requires more labels to generalize.We introduce Video Pose Distillation (VPD), a weakly-supervised technique to learn features for new video domain
Abstract This paper presents a survey of non‐fungible tokens (NFTs), including its history, technologies, standards, and challenges in their development. An NFT is a unique digital entity that is created and maintained using blockchain technology. Each NFT is identified using a unique smart contract and a token ID, so the whole history of the NFT can be globally identified by its address and token ID. The blockchain information indelibly identifies the current owner of any asset, previous owners
Cable (TV) news reaches millions of US households each day. News stakeholders such as communications researchers, journalists, and media monitoring organizations are interested in the visual content of cable news, especially who is on-screen. Manual analysis, however, is labor intensive and limits the size of prior studies. We conduct a large-scale, quantitative analysis of the faces in a decade of cable news video from the top three US cable news networks (CNN, FOX, and MSNBC), totaling 244,038
This paper examines the potential role and feasibility of using the X.500 Directory Service in the network management framework. We examine the network management requirements and investigate how the Directory Service can satisfy them. A simple network load monitoring tool was adapted to use a prototype X.500 Directory Service (Quipu) for the storage and retrieval of (1) network domain information, (2) host information, (3) network monitoring tool application information, and (4) network managem
The Internet of Things (IoT) is changing the way we interact with everyday objects. "Smart" devices will reduce energy use, keep our homes safe, and improve our health. However, as recent attacks have shown, these devices also create tremendous security vulnerabilities in our computing networks. Securing all of these devices is a daunting task. In this paper, we argue that IoT device communications should be default-off and desired network communications must be explicitly enabled. Unlike tradit
For distributed multimedia services, it is essential that quality of service be guaranteed system-wide, including end systems, communication systems, and networks. Although many researchers have addressed issues of QoS management, little attention has so far been paid to the QoS management services in distributed multimedia services and applications. To address this deficiency, we have designed a layered model for end-to-end QoS management called the QoS management framework. Our framework, whic
Abstract Fractional non‐fungible tokens (NFTs) have emerged at the forefront of blockchain innovation, merging tokenization, NFTs, and fractional ownership to democratize access to high‐value digital assets. In this paper, we explore the fundamental concepts of blockchain technology, smart contracts, NFTs, and tokenization to lay the groundwork for understanding fractional NFTs. We investigate key ERC standards, including ERC‐20, ERC‐721, and ERC‐1155, which are pivotal in enabling the creation