Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟰𝟲 Computer Vision Learning 𝐈𝐃𝐔: Learning to Discriminate Information for Online Action Detection by Korea Advanced Institute of Science and Technology (KAIST) Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR 2020 with over 8 citations. 🔸 It outperform RNN-LSTM, RNN-GRU, etc. ------------------------------------------------------------------ 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eYVTxqG Code: https://lnkd.in/enkzQj3 ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸From a streaming video, online action detection aims to identify actions in the present. For this task, previous methods use recurrent networks to model the temporal sequence of current action frames. 🔸This paper propose a novel recurrent unit to explicitly discriminate the information relevant to an ongoing action from others. It named Information Discrimination Unit (IDU), decides whether to accumulate input information based on its relevance to the current action. #computervision #artificialintelligence #innovation

  • diagram

Interesting. That looks very computationally intensive to train though.

See more comments

To view or add a comment, sign in

Explore content categories