4 papers
SVHighlights: Towards Extremely Long Sport Video Highlight Detection
Donggyu Lee, Youngbin Ki, Jeonghun Kang +1
While highlight detection for long-form videos is of great practical importance, most existing methods remain limited to short-form content, largely due to the absence of a suitabl…
DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization
Jeonghun Kang, Soonmok Kwon, Joonseok Lee +1
Traditional approaches -- such as Win Probability Added (WPA)-based ranking or computer vision-driven event detection -- can identify scoring plays but often miss strategic depth,…
Generating Realistic Images from In-the-wild Sounds
Taegyeong Lee, Jeonghun Kang, Hyeonyu Kim +1
Representing wild sounds as images is an important but challenging task due to the lack of paired datasets between sound and images and the significant differences in the character…
Technical Report for CVPR 2022 LOVEU AQTC Challenge
Hyeonyu Kim, Jongeun Kim, Jeonghun Kang +3
This technical report presents the 2nd winning model for AQTC, a task newly introduced in CVPR 2022 LOng-form VidEo Understanding (LOVEU) challenges. This challenge faces difficult…