Nice use of Q-Networks and MCTS to do scene arrangement. Given an initial layout it learns to find a sequence of moves (actions) that bring it close to the target layout all with a collision free path.
generating scenes via RL or generative models, training systems in them, tracking performance and if success rate is high go back to generating scenes but with increasing complexity all without a human in the loop - some sort of auto-ml.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
finally got around to reading this eccv20 best paper award winner work on optical flow that has interesting ideas: multi-scale 4D correlation volumes, learned-upsampling (using convex weights of lower res pixels), and iterative refinement of flow.
first up, joblib's memory. If you are reading a huge file Memory class helps you cache that on your disk during the first call. Successive calls load the data much faster. Assuming you didn't change both the function as well as the contents of the file.
This is one of the finest lecture notes in computer vision by Svetlana Lazebnik. Highly recommended to everyone in CV. It mentions the origins, various historic perspectives and anecdotes in CV. Also talks about ethical and societal impacts of CV.