Action recognition by turning videos into an image mosaic
Action recognition by turning videos into an image mosaic
An Image Classifier Can Suffice Video Understanding
arXiv paper abstract https://arxiv.org/abs/2106.14104
arXiv PDF paper https://arxiv.org/pdf/2106.14104.pdf
… casting the video recognition problem as an image recognition task.
… composes input frames into a super image to train an image classifier to fulfill the task of action recognition, in exactly the same way as classifying an image.
… demonstrating strong and promising performance on four public datasets including Kinetics400, Something-to-something (V2), MiT and Jester, using a recently developed vision transformer.
… also experiment with the prevalent ResNet image classifiers
… results on Kinetics400 are comparable to some of the best-performed CNN approaches based on spatio-temporal modeling. …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
