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

Neural module networks (NMN) have achieved success in image-grounded taskssuch as Visual Question Answering (VQA) on synthetic images. However, verylimited work on NMN has been studied in the video-grounded dialogue tasks.These tasks extend the complexity of traditional visual tasks with theadditional visual temporal variance and language cross-turn dependencies.Motivated by recent NMN approaches on image-grounded tasks, we introduceVideo-grounded Neural Module Network (VGNMN) to model the information retrievalprocess in video-grounded language tasks as a pipeline of neural modules. VGNMNfirst decomposes all language components in dialogues to explicitly resolve anyentity references and detect corresponding action-based inputs from thequestion. The detected entities and actions are used as parameters toinstantiate neural module networks and extract visual cues from the video. Ourexperiments show that VGNMN can achieve promising performance on a challengingvideo-grounded dialogue benchmark as well as a video QA benchmark.

VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks