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

'Actions' play a vital role in how humans interact with the world. Thus,autonomous agents that would assist us in everyday tasks also require thecapability to perform 'Reasoning about Actions & Change' (RAC). This has beenan important research direction in Artificial Intelligence (AI) in general, butthe study of RAC with visual and linguistic inputs is relatively recent. TheCLEVR_HYP (Sampat et. al., 2021) is one such testbed for hypotheticalvision-language reasoning with actions as the key focus. In this work, wepropose a novel learning strategy that can improve reasoning about the effectsof actions. We implement an encoder-decoder architecture to learn therepresentation of actions as vectors. We combine the aforementionedencoder-decoder architecture with existing modality parsers and a scene graphquestion answering model to evaluate our proposed system on the CLEVR_HYPdataset. We conduct thorough experiments to demonstrate the effectiveness ofour proposed approach and discuss its advantages over previous baselines interms of performance, data efficiency, and generalization capability.

Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task