Cargando…
WildGait: Learning Gait Representations from Raw Surveillance Streams
SIMPLE SUMMARY: In this work, we explore self-supervised pretraining for gait recognition. We gather the largest dataset to date of real-world gait sequences automatically annotated through pose tracking (UWG), which offers realistic confounding factors as opposed to current datasets. Results highli...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
MDPI
2021
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8705742/ https://www.ncbi.nlm.nih.gov/pubmed/34960479 http://dx.doi.org/10.3390/s21248387 |