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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we propose a discriminative video representation for eventdetection over a large scale video dataset when only limited hardware resourcesare available. The focus of this paper is to effectively leverage deepConvolutional Neural Networks (CNNs) to advance event detection, where onlyframe level static descriptors can be extracted by the existing CNN toolkit.This paper makes two contributions to the inference of CNN videorepresentation. First, while average pooling and max pooling have long been thestandard approaches to aggregating frame level static features, we show thatperformance can be significantly improved by taking advantage of an appropriateencoding method. Second, we propose using a set of latent concept descriptorsas the frame descriptor, which enriches visual information while keeping itcomputationally affordable. The integration of the two contributions results ina new state-of-the-art performance in event detection over the largest videodatasets. Compared to improved Dense Trajectories, which has been recognized asthe best video representation for event detection, our new representationimproves the Mean Average Precision (mAP) from 27.6% to 36.8% for the TRECVIDMEDTest 14 dataset and from 34.0% to 44.6% for the TRECVID MEDTest 13 dataset.This work is the core part of the winning solution of our CMU-Informedia teamin TRECVID MED 2014 competition.

A Discriminative CNN Video Representation for Event Detection