Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction

O Ignat, S Castro, W Li, R Mihalcea - arXiv preprint arXiv:2309.06219, 2023 - arxiv.org
We introduce the task of automatic human action co-occurrence identification, ie, determine
whether two human actions can co-occur in the same interval of time. We create and make …

Human motion video generation: A survey

H Xue, X Luo, Z Hu, X Zhang, X Xiang, Y Dai, J Liu… - Authorea …, 2024 - techrxiv.org
Human motion video generation has garnered significant research interest due to its broad
applications, enabling innovations such as photorealistic singing heads or dynamic avatars …

Learning Human Action Representations from Temporal Context in Lifestyle Vlogs

O Ignat, S Castro, W Li, R Mihalcea - Proceedings of TextGraphs …, 2024 - aclanthology.org
We address the task of human action representation and show how the approach to
generating word representations based on co-occurrence can be adapted to generate …

ProposalVLAD with Proposal-Intra Exploring for Temporal Action Proposal Generation

K Xing, T Li, X Wang - ACM Transactions on Multimedia Computing …, 2023 - dl.acm.org
Temporal action proposal generation aims to localize temporal segments of human activities
in videos. Current boundary-based proposal generation methods can generate proposals …