Open
Description
I need advice: I'm a Java guy, and I would feel very comfortable using DL4J. The problem I'm trying to solve is to build a video-attention model. Basically, given a video, it gives me a rank of attention about video shots; basically which shot is more interesting.
Apparently I should use LSTM for that. But is there a good tutorial how to do this using DL4J? The video classification example is basically frame-based, not timed video based.
Activity