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

We propose a method to learn image representations from uncurated videos. Wecombine a supervised loss from off-the-shelf object detectors andself-supervised losses which naturally arise from the video-shot-frame-objecthierarchy present in each video. We report competitive results on 19 transferlearning tasks of the Visual Task Adaptation Benchmark (VTAB), and on 8out-of-distribution-generalization tasks, and discuss the benefits andshortcomings of the proposed approach. In particular, it improves over thebaseline on all 18/19 few-shot learning tasks and 8/8 out-of-distributiongeneralization tasks. Finally, we perform several ablation studies and analyzethe impact of the pretrained object detector on the performance across thissuite of tasks.

Representation learning from videos in-the-wild: An object-centric approach