Unified Embedding and Metric Learning for Zero-Exemplar Event Detection

Noureldien Hussein, Efstratios Gavves, Arnold W.M. Smeulders; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1096-1105

Abstract


Event detection in unconstrained videos is conceived as a content-based video retrieval with two modalities: textual and visual. Given a text describing a novel event, the goal is to rank related videos accordingly. This task is zero-exemplar, no video examples are given to the novel event. Related works train a bank of concept detectors on external data sources. These detectors predict confidence scores for test videos, which are ranked and retrieved accordingly. In contrast, we learn a joint space in which the visual and textual representations are embedded. The space casts a novel event as a probability of pre-defined events. Also, it learns to measure the distance between an event and its related videos. Our model is trained end-to-end on publicly available EventNet. When applied to TRECVID Multimedia Event Detection dataset, it outperforms the state-of-the-art by a considerable margin.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Hussein_2017_CVPR,
author = {Hussein, Noureldien and Gavves, Efstratios and Smeulders, Arnold W.M.},
title = {Unified Embedding and Metric Learning for Zero-Exemplar Event Detection},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}