Asymmetric Spatio-Temporal Embeddings for Large-Scale Image-to-Video Retrieval
Aston Publications Explorer (Aston University) · 2018
Abstract
We address the problem of image-to-video retrieval. Given a query image, the aim is to identify the frame or scene within a collection of videos that best matches the visual input. Matching images to videos is an asymmetric task in which specific features for capturing the visual information in images and, at the same time, compacting the temporal correlation from videos are needed. Methods proposed so far are based on the temporal aggregation of hand-crafted features. In this work, we propose a deep learning architecture for learning specific asymmetric spatio-temporal embeddings for image-tovideo retrieval. Our method learns non-linear projections from training data for both images and videos and projects their visual content into a common latent space, where they can be easily compared with a standard similarity function. Experiments conducted here show that our proposed asymmetric spatio-temporal embeddings outperform stateof-the-art in standard image-to-video retrieval datasets.
Citation
Noa García and George Vogiatzis. “Asymmetric Spatio-Temporal Embeddings for Large-Scale Image-to-Video Retrieval.” Aston Publications Explorer (Aston University), pp. 206. 2018.
BibTeX
@inproceedings{garca2018,
title = {Asymmetric Spatio-Temporal Embeddings for Large-Scale Image-to-Video Retrieval},
author = {Noa García and George Vogiatzis},
booktitle = {Aston Publications Explorer (Aston University)},
pages = {206},
year = {2018},
}