Abstract: There is described a computer-implemented method and system for classifying images, the computer-implemented method comprising: receiving an image to be classified, generating a vector representation of the image to be classified using an image embedding method, comparing the vector representation of the image to predefined vector representations of the predefined image categories, and identifying a relevant category amongst the predefined image categories based on the comparison, the relevant category being associated with the image to be classified and outputting the relevant category.

Abstract: There is described a computer-implemented method and system for classifying images, the computer-implemented method comprising: receiving an image to be classified, generating a vector representation of the image to be classified using an image embedding method, comparing the vector representation of the image to predefined vector representations of the predefined image categories, and identifying a relevant category amongst the predefined image categories based on the comparison, the relevant category being associated with the image to be classified and outputting the relevant category.

Abstract: There is described a computer-implemented method for generating a vector representation of an image, the computer-implemented method comprising: receiving a given image and semantic information about the given image; generating a first vector representation of the given image using an image embedding method; generating a second vector representation of the semantic information using a word embedding method; combining the first vector representation of the image to be embedded and the second vector representation of the semantic information together, thereby obtaining a modified vector representation for the image to be embedded; and outputting the modified vector representation.

Abstract: There is described a computer-implemented method for generating a vector representation of an image, the computer-implemented method comprising: receiving a given image and semantic information about the given image; generating a first vector representation of the given image using an image embedding method; generating a second vector representation of the semantic information using a word embedding method; combining the first vector representation of the image to be embedded and the second vector representation of the semantic information together, thereby obtaining a modified vector representation for the image to be embedded; and outputting the modified vector representation.

Abstract: Systems and methods for counting objects in images based on each object's approximate location in the images. An image is passed to a segmentation module. The segmentation module segments the image into at least one object blob. Each object blob is an indication of a single object. The object blobs are counted by a counting module. In some embodiments, the segmentation module segments the image by classifying each image pixel and grouping nearby pixels of the same class together. In some embodiments, the segmentation module comprises a neural network that is trained to group pixels based on a set of training images. A plurality of the training images contain at least one point marker corresponding to a single training object. The segmentation module learns to group pixels into training object blobs that each contain a single point marker. Each training object blob is thus an indication of a single object.

Abstract: Systems and methods relating to neural networks. More specifically, the present invention relates to complex valued gating mechanisms which may be used as neurons in a neural network. A novel complex gated recurrent unit and a novel complex recurrent unit use real values for amplitude normalization to stabilize training while retaining phase information.

Abstract: Systems and methods for counting objects in images based on each object's approximate location in the images. An image is passed to a segmentation module. The segmentation module segments the image into at least one object blob. Each object blob is an indication of a single object. The object blobs are counted by a counting module. In some embodiments, the segmentation module segments the image by classifying each image pixel and grouping nearby pixels of the same class together. In some embodiments, the segmentation module comprises a neural network that is trained to group pixels based on a set of training images. A plurality of the training images contain at least one point marker corresponding to a single training object. The segmentation module learns to group pixels into training object blobs that each contain a single point marker. Each training object blob is thus an indication of a single object.