Semi-Supervised Sperm Motility Classification Using WHO Kinematic Features and Domain-Adapted Detection on VISEM-Tracking

S Kumar; A Singh; S Manna; R Saini

doi:10.5617/nmi.13362

Abstract

A semi-supervised framework leveraging WHO kinematic criteria and domain adaptation for accurate sperm motility tracking and clinical fertility classification.

More works

Breaking the Privacy Promise: Gradient Inversion Attacks on Federated Low-Rank Adapted Vision Transformers Winter Conference on Applications of Computer Vision (WACV 2027) 2027
Bridging the Applicator Gap with Data-Doping: Dual-Domain Learning for Precise Bladder Segmentation in CT-Guided Brachytherapy arXiv preprint 2026
On the Role of the Projector in Contrastive Self-Supervised Learning: Last-Layer Rank Dynamics Drive Representation Quality arXiv preprint 2026
Multiorgan Segmentation in Magnetic Resonance Images for Gynecological Brachytherapy Using Residuals in Residual Dense Block Journal of Medical Physics 2026
Reliability-Aware Weighted Multi-Scale Spatio-Temporal Maps for Heart Rate Monitoring IEEE International Conference on Image Processing (ICIP 2026) 2026
Dynamically Scaled Temperature in Self-Supervised Contrastive Learning IEEE Transactions on Artificial Intelligence 2025

All publications →

BibTeX

@inproceedings{kumar2026semisupervised,
  title={Semi-Supervised Sperm Motility Classification Using WHO Kinematic Features and Domain-Adapted Detection on VISEM-Tracking},
  author={Kumar, S and Singh, A and Manna, S and Saini, R},
  booktitle={The First Workshop on AI in Fertility Science (2026)},
  year={2026},
  doi={10.5617/nmi.13362},
  url={https://sadimanna.github.io/papers/semisup-motility/}
}