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

Group-level emotion recognition (ER) is a growing research area as thedemands for assessing crowds of all sizes are becoming an interest in both thesecurity arena as well as social media. This work extends the earlier ERinvestigations, which focused on either group-level ER on single images orwithin a video, by fully investigating group-level expression recognition oncrowd videos. In this paper, we propose an effective deep feature level fusionmechanism to model the spatial-temporal information in the crowd videos. In ourapproach, the fusing process is performed on the deep feature domain by agenerative probabilistic model, Non-Volume Preserving Fusion (NVPF), thatmodels spatial information relationships. Furthermore, we extend our proposedspatial NVPF approach to the spatial-temporal NVPF approach to learn thetemporal information between frames. To demonstrate the robustness andeffectiveness of each component in the proposed approach, three experimentswere conducted: (i) evaluation on AffectNet database to benchmark the proposedEmoNet for recognizing facial expression; (ii) evaluation on EmotiW2018 tobenchmark the proposed deep feature level fusion mechanism NVPF; and, (iii)examine the proposed TNVPF on an innovative Group-level Emotion on Crowd Videos(GECV) dataset composed of 627 videos collected from publicly availablesources. GECV dataset is a collection of videos containing crowds of people.Each video is labeled with emotion categories at three levels: individualfaces, group of people, and the entire video frame.

Non-Volume Preserving-based Fusion to Group-Level Emotion Recognition on Crowd Videos