deeplearning4j/deeplearning4j-examples

Video analytics

Open

#871 opened on Aug 8, 2019

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Java (2,395 stars) (1,841 forks)batch import
help wantedquestion

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.

Contributor guide

Tech stack
java
Domain
machine learning
Issue type
research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
5
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
unclear
Prerequisites
Basic deep learning conceptsFamiliarity with DL4JUnderstanding of LSTM
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
10
Research direction
The issue is a request for advice on building a video attention model using DL4J and LSTM. No follow up comments or PRs exist. To address this, one should investigate existing DL4J examples for video classification (e.g., frame based approaches) and explore LSTM tutorials in the DL4J documentation. A potential contribution could be creating a tutorial or example demonstrating video attention with LSTM in DL4J.
Video analytics · deeplearning4j/deeplearning4j-examples#871 | Good First Issue