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

Video recognition in an open and dynamic world is quite challenging, as weneed to handle different settings such as close-set, long-tail, few-shot andopen-set. By leveraging semantic knowledge from noisy text descriptions crawledfrom the Internet, we focus on the general video recognition (GVR) problem ofsolving different recognition tasks within a unified framework. The corecontribution of this paper is twofold. First, we build a comprehensive videorecognition benchmark of Kinetics-GVR, including four sub-task datasets tocover the mentioned settings. To facilitate the research of GVR, we propose toutilize external textual knowledge from the Internet and provide multi-sourcetext descriptions for all action classes. Second, inspired by the flexibilityof language representation, we present a unified visual-linguistic framework(VLG) to solve the problem of GVR by an effective two-stage training paradigm.Our VLG is first pre-trained on video and language datasets to learn a sharedfeature space, and then devises a flexible bi-modal attention head tocollaborate high-level semantic concepts under different settings. Extensiveresults show that our VLG obtains the state-of-the-art performance under foursettings. The superior performance demonstrates the effectiveness andgeneralization ability of our proposed framework. We hope our work makes a steptowards the general video recognition and could serve as a baseline for futureresearch. The code and models will be available athttps://github.com/MCG-NJU/VLG.

VLG: General Video Recognition with Web Textual Knowledge