Abstract: Systems and methods to detect one or more segments of one or more objects within one or more images based, at least in part, on a neural network trained in an unsupervised manner to infer the one or more segments. Systems and methods to help train one or more neural networks to detect one or more segments of one or more objects within one or more images in an unsupervised manner.

Abstract: A technique for managing a user interface in a continuous integration (CI) environment includes providing user-interface (UI) regions in a UI page downloaded from a server. The UI regions correspond to respective parameters of a CI job. In response to a change in a particular parameter associated with a UI region, the technique further includes updating, by the server, the UI page to contain code configured to hide a specified set of other UI regions, such as those rendered irrelevant based on the parameter change.

Abstract: One embodiment of the present invention sets forth a technique for executing a transformer neural network. The technique includes computing a first set of halting scores for a first set of tokens that has been input into a first layer of the transformer neural network. The technique also includes determining that a first halting score included in the first set of halting scores exceeds a threshold value. The technique further includes in response to the first halting score exceeding the threshold value, causing a first token that is included in the first set of tokens and is associated with the first halting score not to be processed by one or more layers within the transformer neural network that are subsequent to the first layer.

Abstract: A method, computer readable medium, and system are disclosed for visual sequence learning using neural networks. The method includes the steps of replacing a non-recurrent layer within a trained convolutional neural network model with a recurrent layer to produce a visual sequence learning neural network model and transforming feedforward weights for the non-recurrent layer into input-to-hidden weights of the recurrent layer to produce a transformed recurrent layer. The method also includes the steps of setting hidden-to-hidden weights of the recurrent layer to initial values and processing video image data by the visual sequence learning neural network model to generate classification or regression output data.

Abstract: Techniques for facilitating the composition of console commands for storage systems and appliances. The techniques include receiving a command prefix at a management console and accessing a plurality of first parameter designations associated with the command prefix from a first hierarchical level of a command tree. The techniques include receiving a selection of a first parameter designation from among the first parameter designations and accessing a plurality of second parameter designations associated with the first parameter designation from a second hierarchical level of the command tree. The techniques include receiving a selection of a second parameter designation from among the second parameter designations and merging the command prefix, the first parameter designation, and the second parameter designation to form a console command for performing a specified task or operation.

Abstract: Systems and methods for more accurate and robust determination of subject characteristics from an image of the subject. One or more machine learning models receive as input an image of a subject, and output both facial landmarks and associated confidence values. Confidence values represent the degrees to which portions of the subject's face corresponding to those landmarks are occluded, i.e., the amount of uncertainty in the position of each landmark location. These landmark points and their associated confidence values, and/or associated information, may then be input to another set of one or more machine learning models which may output any facial analysis quantity or quantities, such as the subject's gaze direction, head pose, drowsiness state, cognitive load, or distraction state.

Abstract: A vision transformer is a deep learning model used to perform vision processing tasks such as image recognition. Vision transformers are currently designed with a plurality of same-size blocks that perform the vision processing tasks. However, some portions of these blocks are unnecessary and not only slow down the vision transformer but use more memory than required. In response, parameters of these blocks are analyzed to determine a score for each parameter, and if the score falls below a threshold, the parameter is removed from the associated block. This reduces a size of the resulting vision transformer, which reduces unnecessary memory usage and increases performance.

Abstract: In order to determine accurate three-dimensional (3D) models for objects within a video, the objects are first identified and tracked within the video, and a pose and shape are estimated for these tracked objects. A translation and global orientation are removed from the tracked objects to determine local motion for the objects, and motion infilling is performed to fill in any missing portions for the object within the video. A global trajectory is then determined for the objects within the video, and the infilled motion and global trajectory are then used to determine infilled global motion for the object within the video. This enables the accurate depiction of each object as a 3D pose sequence for that model that accounts for occlusions and global factors within the video.

Abstract: Apparatuses, systems, and techniques are presented to simplify neural networks. In at least one embodiment, one or more portions of one or more neural networks are cause to be removed based, at least in part, on one or more performance metrics of the one or more neural networks.

Abstract: An apparatus pulls a single crystal of semiconductor material by the Czochralski (CZ) method from a melt. The apparatus includes: a crucible that accommodates the melt; a resistance heater around the crucible; a camera system for observing a phase boundary between the melt and a growing single crystal, the camera system having an optical axis; a heat shield in frustoconical form with a narrowing diameter in a region at its lower end and arranged above the crucible and surrounding the growing single crystal; and an annular element, which is configured to capture particles, that projects inward from an inner side face of the heat shield and has an arrestor edge directed upward at an inner end of the annular element. The optical axis of the camera system runs between the arrestor edge and the growing single crystal. The annular element is releasably connected to the heat shield.

Abstract: A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.

Abstract: There is provided servers and methods of generating a waveform based on a spectrogram and a noise input. The method includes acquiring a trained flow-based vocoder including invertible blocks, and an untrained feed-forward vocoder including non-invertible blocks, which form a student-teacher network. The method includes executing a training process in the student-teacher network during which the server generates (i) a teacher waveform by the trained flow-based vocoder using a first spectrogram and a first noise input, (ii) a student waveform by the untrained feed-forward vocoder using the first spectrogram and the first noise input, and (iii) a loss value for the given training iteration using the teacher waveform and the student waveform. The server then trains the untrained feed-forward vocoder to generate the waveform. The trained feed-forward vocoder in then used lieu of the trained flow-based vocoder for generating waveforms based on spectrograms and noise inputs.

Abstract: Estimating a three-dimensional (3D) pose of an object, such as a hand or body (human, animal, robot, etc.), from a 2D image is necessary for human-computer interaction. A hand pose can be represented by a set of points in 3D space, called keypoints. Two coordinates (x,y) represent spatial displacement and a third coordinate represents a depth of every point with respect to the camera. A monocular camera is used to capture an image of the 3D pose, but does not capture depth information. A neural network architecture is configured to generate a depth value for each keypoint in the captured image, even when portions of the pose are occluded, or the orientation of the object is ambiguous. Generation of the depth values enables estimation of the 3D pose of the object.

Abstract: Systems and methods for more accurate and robust determination of subject characteristics from an image of the subject. One or more machine learning models receive as input an image of a subject, and output both facial landmarks and associated confidence values. Confidence values represent the degrees to which portions of the subject's face corresponding to those landmarks are occluded, i.e., the amount of uncertainty in the position of each landmark location. These landmark points and their associated confidence values, and/or associated information, may then be input to another set of one or more machine learning models which may output any facial analysis quantity or quantities, such as the subject's gaze direction, head pose, drowsiness state, cognitive load, or distraction state.

Abstract: A handshake message includes a field containing random data that is filled with data used to derive keying material on the source and destination computers. The data may be elliptic curve data and may include a representation of the data used by the destination computer to verify that elliptic curve data is present. The data may additionally include data for deriving second keying material on a second destination computer that the first destination computer forwards to the second computer, receives a response, and returns data from the response as part of its own handshake message.

Abstract: Apparatuses, systems, and techniques to remove one or more nodes of a neural network. In at least one embodiment, one or more nodes of a neural network are removed, based on, for example, whether the one or more nodes are likely to affect performance of the neural network.

Abstract: Apparatuses, systems, and techniques to invert a neural network. In at least one embodiment, one or more neural network layers are inverted and, in at least one embodiment, loaded in reverse order.

Abstract: Apparatuses, systems, and techniques to identify one or more images used to train one or more neural networks. In at least one embodiment, one or more images used to train one or more neural networks are identified, based on, for example, one or more labels of one or more objects within the one or more images.

Abstract: Learning to estimate a 3D body pose, and likewise the pose of any type of object, from a single 2D image is of great interest for many practical graphics applications and generally relies on neural networks that have been trained with sample data which annotates (labels) each sample 2D image with a known 3D pose. Requiring this labeled training data however has various drawbacks, including for example that traditionally used training data sets lack diversity and therefore limit the extent to which neural networks are able to estimate 3D pose. Expanding these training data sets is also difficult since it requires manually provided annotations for 2D images, which is time consuming and prone to errors. The present disclosure overcomes these and other limitations of existing techniques by providing a model that is trained from unlabeled multi-view data for use in 3D pose estimation.

Abstract: The neural network includes an encoder, a common decoder, and a residual decoder. The encoder encodes input images into a latent space. The latent space disentangles unique features from other common features. The common decoder decodes common features resident in the latent space to generate translated images which lack the unique features. The residual decoder decodes unique features resident in the latent space to generate image deltas corresponding to the unique features. The neural network combines the translated images with the image deltas to generate combined images that may include both common features and unique features. The combined images can be used to drive autoencoding. Once training is complete, the residual decoder can be modified to generate segmentation masks that indicate any regions of a given input image where a unique feature resides.