Abstract: A method of generating additional supervision data to improve learning of a geometrically-consistent latent scene representation with a geometric scene representation architecture is provided. The method includes receiving, with a computing device, a latent scene representation encoding a pointcloud from images of a scene captured by a plurality of cameras each with known intrinsics and poses, generating a virtual camera having a viewpoint different from viewpoints of the plurality of cameras, projecting information from the pointcloud onto the viewpoint of the virtual camera, and decoding the latent scene representation based on the virtual camera thereby generating an RGB image and depth map corresponding to the viewpoint of the virtual camera for implementation as additional supervision data.

Abstract: Systems and methods described herein relate to self-supervised learning of camera intrinsic parameters from a sequence of images. One embodiment produces a depth map from a current image frame captured by a camera; generates a point cloud from the depth map using a differentiable unprojection operation; produces a camera pose estimate from the current image frame and a context image frame; produces a warped point cloud based on the camera pose estimate; generates a warped image frame from the warped point cloud using a differentiable projection operation; compares the warped image frame with the context image frame to produce a self-supervised photometric loss; updates a set of estimated camera intrinsic parameters on a per-image-sequence basis using one or more gradients from the self-supervised photometric loss; and generates, based on a converged set of learned camera intrinsic parameters, a rectified image frame from an image frame captured by the camera.

Abstract: A method (and structure and computer product) for learning Out-of-Vocabulary (OOV) words in an Automatic Speech Recognition (ASR) system includes using an Acoustic Word Embedding Recurrent Neural Network (AWE RNN) to receive a character sequence for a new OOV word for the ASR system, the RNN providing an Acoustic Word Embedding (AWE) vector as an output thereof. The AWE vector output from the AWE RNN is provided as an input into an Acoustic Word Embedding-to-Acoustic-to-Word Neural Network (AWE?A2W NN) trained to provide an OOV word weight value from the AWE vector. The OOV word weight is inserted into a listing of Acoustic-to-Word (A2W) word embeddings used by the ASR system to output recognized words from an input of speech acoustic features, wherein the OOV word weight is inserted into the A2W word embeddings list relative to existing weights in the A2W word embeddings list.

Abstract: In one embodiment, a symbol error correction encoder effects block interleaving on recording data and thereafter performs first error correction encoding on the recording data. Next, a symbol error correction encoder performs encoding on the whole block. A reproducing processing circuit outputs likelihood information of respective bits. A first error correction decoder corrects a random error produced upon recording and reproduction, using the likelihood information. Since it is possible to make an improvement in performance with respect to the random error by repetitive decoding at this time, the post-correction data is returned to the reproducing processing circuit. After the completion of such repetitive processing, the data is digitized and subjected to an error correction in symbol unit by a hard determination, and outputted to a symbol error correction decoder.

Abstract: There is disclosed second-order nonlinear glass material wherein a part having second-order nonlinearity contains Ge, H and OH and has second-order nonlinear optical constant d of 1 pm/V or more, and a method for producing second-order nonlinear glass material comprising treating a porous glass material containing Ge with hydrogen, sintering it and subjecting it to a ultraviolet poling treatment. There can be provided second-order nonlinear glass material having second-order nonlinearity which is a sufficiently high and has a sufficiently long lifetime for a practical purpose, in use of the glass material for optical functional elements or the like.

Abstract: A process for producing a polymer of excellent weatherability, which comprises reacting a polymer having a thioether bond, with a peroxide to oxidize the sulfur atom in the bond to convert it into a sulfone.