Microsoft Technology Licensing, LLC

Jifeng Dai

Jian Qiao Sun

Kaiming He

Lu Yuan

Yichen Wei

Various embodiments herein each include at least one of systems, methods, and software for feature flow for video recognition. Such embodiments generally include a fast and accurate framework for video recognition. One example method includes receiving a first frame captured by an imaging device and designating the first frame as a key frame. The method may then generate at least one feature map to identify features in the key frame and subsequently receive a second frame. The method also includes designating the second frame as a current frame and applying a flow estimation algorithm to the key frame and current frame to generate a flow field representing a flow from the key frame to the current frame. The method then propagates each of the at least one feature maps based on the flow field to approximate current locations of features identified within each of the at least one feature maps.

Feature flow for video recognition

In implementations of the subject matter described herein, the feature maps are obtained by convoluting an input image using a plurality of layers of convolution filters. The feature maps record semantic information for respective regions on the image and only need to be computed once. Segment features of the image are extracted from the convolutional feature maps. Particularly, the binary masks may be obtained from a set of candidate segments of the image. The binary masks are used to mask the feature maps instead of the raw image. The masked feature maps define the segment features. The semantic segmentation of the image is done by determining a semantic category for each pixel in the image at least in part based on the resulting segment features.

Image semantic segmentation

Disclosed herein are technologies directed to training a neural network to perform semantic segmentation. A system receives a training image, and using the training image, candidate masks are generated. The candidate masks are ranked and a set of the ranked candidate masks are selected for further processing. One of the set of the ranked candidate masks is selected to train the neural network. The one of the set of the set of the ranked candidate masks is also used as an input to train the neural network in a further training evolution. In some examples, the one of the set of the ranked candidate masks is selected randomly to reduce the likelihood of ending up in poor local optima that result in poor training inputs.

Growing community of inventors

Beijing, China

Jifeng Dai