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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

From a visual scene containing multiple people, human is able to distinguisheach individual given the context descriptions about what happened before,their mental/physical states or intentions, etc. Above ability heavily relieson human-centric commonsense knowledge and reasoning. For example, if asked toidentify the "person who needs healing" in an image, we need to first know thatthey usually have injuries or suffering expressions, then find thecorresponding visual clues before finally grounding the person. We present anew commonsense task, Human-centric Commonsense Grounding, that tests themodels' ability to ground individuals given the context descriptions about whathappened before, and their mental/physical states or intentions. We furthercreate a benchmark, HumanCog, a dataset with 130k grounded commonsensicaldescriptions annotated on 67k images, covering diverse types of commonsense andvisual scenes. We set up a context-object-aware method as a strong baselinethat outperforms previous pre-trained and non-pretrained models. Furtheranalysis demonstrates that rich visual commonsense and powerful integration ofmulti-modal commonsense are essential, which sheds light on future works. Dataand code will be available https://github.com/Hxyou/HumanCog.

Find Someone Who: Visual Commonsense Understanding in Human-Centric Grounding