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

In this paper, we propose an end-to-end capsule network for pixel levellocalization of actors and actions present in a video. The localization isperformed based on a natural language query through which an actor and actionare specified. We propose to encode both the video as well as textual input inthe form of capsules, which provide more effective representation in comparisonwith standard convolution based features. We introduce a novel capsule basedattention mechanism for fusion of video and text capsules for text selectedvideo segmentation. The attention mechanism is performed via joint EM routingover video and text capsules for text selected actor and action localization.The existing works on actor-action localization are mainly focused onlocalization in a single frame instead of the full video. Different fromexisting works, we propose to perform the localization on all frames of thevideo. To validate the potential of the proposed network for actor and actionlocalization on all the frames of a video, we extend an existing actor-actiondataset (A2D) with annotations for all the frames. The experimental evaluationdemonstrates the effectiveness of the proposed capsule network for textselective actor and action localization in videos, and it also improves uponthe performance of the existing state-of-the art works on single frame-basedlocalization.

Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries