Infant – CV4Smalls Workshop

Datasets:

Non-nutritive sucking in-the-wild dataset (NNS) – This public NNS in-the-wild dataset, consisting of 10 naturalistic infant video clips annotated for NNS activity.
Infant Annotated Faces (InfAnFace) – This dataset consisting of 410 images of infant faces with labels for 68 facial landmark locations and various pose attributes.
Synthetic and Real Infant Pose (SyRIP) – An infant pose dataset with diverse and fully-annotated real infant images and generated synthetic infant images

Recent Publications and Codes:

M. Wan, X. Huang, B. Tunik, and S. Ostadabbas, “Automatic assessment of infant face and upper-body symmetry as early signs of torticollis,” in FG 2023 workshop on Artificial Intelligence for Automated Human Health-care and Monitoring, Jan. 2023. [arXiv preprint at arXiv][Code]
X. Huang, L. Luan, E. Hatamimajoumerd, M. Wan , P. DaneshvarKakhaki, R. Obeid, and S. Ostadabbas, “Posture-based Infant Action Recognition in the Wild with Very Limited Data,” in CVPR Workshop on Learning with Limited Labelled Data (CVPRW), Jun. 2023. [Code]
S. Zhu , M. Wan, E. Hatamimajoumerd, C. V. Kamath, K. Jain, S. Zlota, E. Grace, C. Rowan, M. Goodwin, R. Schwartz-Mette, E. Zimmerman, M. Hayes, and S. Ostadabbas, “A video-based end-to-end pipeline for non- nutritive sucking action recognition and segmentation in young infants,” in International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Oct. 2023. [arXiv preprint at arXiv][Code]
X. Huang, M. Wan, L. Luan⋆, B. Tunik, and S. Ostadabbas, “Computer vision to the rescue: Infant postural symmetry estimation from incongruent annotations,” in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan. 2023. [arXiv preprint at arXiv][Code]
M. Wan, S. Zhu, L. Luan, P. Gulati, X. Huang⋆, R. Schwartz-Mette, M. Hayes, E. Zimmerman, and S. Ostadabbas, “InfAnFace: Bridging the infant–adult domain gap in facial landmark estimation in the wild,” in 26TH International Conference on Pattern Recognition (ICPR), (accepted for oral presentation), Aug. 2022. [arXiv preprint at arXiv][Code]