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

Action recognition from videos, i.e., classifying a video into one of thepre-defined action types, has been a popular topic in the communities ofartificial intelligence, multimedia, and signal processing. However, existingmethods usually consider an input video as a whole and learn models, e.g.,Convolutional Neural Networks (CNNs), with coarse video-level class labels.These methods can only output an action class for the video, but cannot providefine-grained and explainable cues to answer why the video shows a specificaction. Therefore, researchers start to focus on a new task, Part-level ActionParsing (PAP), which aims to not only predict the video-level action but alsorecognize the frame-level fine-grained actions or interactions of body partsfor each person in the video. To this end, we propose a coarse-to-fineframework for this challenging task. In particular, our framework firstpredicts the video-level class of the input video, then localizes the bodyparts and predicts the part-level action. Moreover, to balance the accuracy andcomputation in part-level action parsing, we propose to recognize thepart-level actions by segment-level features. Furthermore, to overcome theambiguity of body parts, we propose a pose-guided positional embedding methodto accurately localize body parts. Through comprehensive experiments on alarge-scale dataset, i.e., Kinetics-TPS, our framework achievesstate-of-the-art performance and outperforms existing methods over a 31.10% ROCscore.

Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework