Video2vec: Learning semantic spatio-temporal embeddings for video representation
Sheng-Hung Hu, Yikang Li, Baoxin Li · 2016
We propose to learn semantic spatio-temporal embeddings for videos to support high-level video analysis. The first step of the proposed embedding employs a deep architecture consisting of two channels of convolutional neural networks (capturing appearance and local motion) followed by their corresponding Gated Recurrent Unit encoders for capturing longer-term temporal structure of the CNN features. The resultant spatio-temporal representation (a vector) is used to learn a mapping via a multilayer perceptron to the word2vec semantic embedding space, leading to a semantic interpretation of the video vector that supports high-level analysis. We demonstrate the usefulness and effectiveness of this new video representation by experiments on action recognition, zero-shot video classification, and “word-to-video” retrieval, using the UCF-101 dataset.