English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

We conduct an in-depth exploration of different strategies for doing eventdetection in videos using convolutional neural networks (CNNs) trained forimage classification. We study different ways of performing spatial andtemporal pooling, feature normalization, choice of CNN layers as well as choiceof classifiers. Making judicious choices along these dimensions led to a verysignificant increase in performance over more naive approaches that have beenused till now. We evaluate our approach on the challenging TRECVID MED'14dataset with two popular CNN architectures pretrained on ImageNet. On thisMED'14 dataset, our methods, based entirely on image-trained CNN features, canoutperform several state-of-the-art non-CNN models. Our proposed late fusion ofCNN- and motion-based features can further increase the mean average precision(mAP) on MED'14 from 34.95% to 38.74%. The fusion approach achieves thestate-of-the-art classification performance on the challenging UCF-101 dataset.

Exploiting Image-trained CNN Architectures for Unconstrained Video Classification