Search Results for "action"

...The architecture is designed to scale: spatiotemporal ViT backbones, flexible masking schedules, and efficient sampling let it train on long clips while remaining stable. Trained representations transfer well to downstream tasks such as action recognition, temporal localization, and video retrieval, often with simple linear probes or light fine-tuning. The repository typically includes end-to-end recipes—data pipelines, augmentation policies, training scripts, and evaluation harnesses.