UNSUPERVISED LEARNING OF OBJECT KEYPOINT LOCATIONS IN IMAGES THROUGH TEMPORAL TRANSPORT OR SPATIO-TEMPORAL TRANSPORT

Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for unsupervised learning of object keypoint locations in images. in particular, a keypoint extraction machine learning model having a plurality of keypoint model parameters is trained to receive an input image and to process the input image in accordance with the keypoint model parameters to generate a plurality of keypoint locations in the input image. the machine learning model is trained using either temporal transport or spatio-temporal transport.

Inventor(s): Ankush Gupta, Tejas Dattatraya Kulkarni

CPC Classification: G06V10/462 (IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING)

Search for rejections for patent application number 20250182439