Modern Architectures for Core Computer Vision on Videos

Over the last half decade, the computer vision field has made huge strides on core image understanding tasks such as object recognition, detection, segmentation and keypoint estimation - today these are technologies that are ubiquitously available to everyday consumers. However, video understanding technology is relatively less pervasive as computer vision models must deal with more difficult appearance, less labeled data, and computational challenges. In this talk, I will cover some of what I consider to be the core challenges of computer vision for video understanding, discussing these in the context of several recent research projects by the Perception team at Google.