Closed adeljalalyousif closed 10 months ago
The core of event boundary detection is to determine the key turning points in the video. You can refer "Local Compressed Video Stream Learning for Generic Event Boundary Detection".
GX @.***
------------------ 原始邮件 ------------------ 发件人: "GX77/Dual-Stream-Transformer-for-Generic-Event-Boundary-Captioning" @.>; 发送时间: 2023年11月26日(星期天) 晚上7:37 @.>; @.***>; 主题: [GX77/Dual-Stream-Transformer-for-Generic-Event-Boundary-Captioning] Event Boundary Detection (Issue #2)
Hello, I am currently working on detecting event boundaries in videos from MSVD or MSR-VTT datasets. Unlike the ActivityNet dataset, these datasets lack timing information. Do you have any straightforward ideas or methods that could help me address this challenge?
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>
Thank you
Hello, I am currently working on detecting event boundaries in videos from MSVD or MSR-VTT datasets. Unlike the ActivityNet dataset, these datasets lack timing information. Do you have any straightforward ideas or methods that could help me address this challenge?