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

The foundation models have recently shown excellent performance on a varietyof downstream tasks in computer vision. However, most existing visionfoundation models simply focus on image-level pretraining and adpation, whichare limited for dynamic and complex video-level understanding tasks. To fillthe gap, we present general video foundation models, InternVideo, by takingadvantage of both generative and discriminative self-supervised video learning.Specifically, InternVideo efficiently explores masked video modeling andvideo-language contrastive learning as the pretraining objectives, andselectively coordinates video representations of these two complementaryframeworks in a learnable manner to boost various video applications. Withoutbells and whistles, InternVideo achieves state-of-the-art performance on 39video datasets from extensive tasks including video actionrecognition/detection, video-language alignment, and open-world videoapplications. Especially, our methods can obtain 91.1% and 77.2% top-1 accuracyon the challenging Kinetics-400 and Something-Something V2 benchmarks,respectively. All of these results effectively show the generality of ourInternVideo for video understanding. The code will be released athttps://github.com/OpenGVLab/InternVideo .

InternVideo: General Video Foundation Models via Generative and Discriminative Learning