05月25日(Thu) 15:50〜17:30 M会場(ウインクあいち-10F 1005会議室)
| 演題番号 | 3M2-2 |
|---|---|
| 題目 | Video Compression with a Predictive Neural Network |
| 著者 | しなぱや らな(東京大学池上研究室) 池上 高志(東京大学) |
| 時間 | 05月25日(Thu) 16:10〜16:30 |
| 概要 | Predictive networks are a type of generative neural network model that learns to minimize the error between predicted data and real input. Prediction is used as a way to perform unsupervised learning of latent structure in the data, for example shapes and linear transformations in images. As a result, video-trained predictive networks can produce output by processing input through intrinsically stored invariances. In this study we propose to use such learned invariances as a compresssion/decompression engine for videos on spatial and temporal dimensions. |
| 論文 | PDFファイル |