Patents by Inventor Peter Graf

Peter Graf has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11423655
    Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a variational autoencoder, a plurality of supervision signals. The method further includes accessing, by the variational autoencoder, a plurality of auxiliary tasks that utilize the supervision signals as reward signals to learn a disentangled representation. The method also includes training the variational autoencoder to disentangle a sequential data input into a time-invariant factor and a time-varying factor using a self-supervised training approach which is based on outputs of the auxiliary tasks obtained by using the supervision signals to accomplish the plurality of auxiliary tasks.
    Type: Grant
    Filed: November 3, 2020
    Date of Patent: August 23, 2022
    Inventors: Renqiang Min, Yizhe Zhu, Asim Kadav, Hans Peter Graf
  • Patent number: 11415894
    Abstract: A projection exposure apparatus for semiconductor technology includes an optical arrangement with an optical element having an optically effective surface. The optical arrangement also includes an actuator embedded in the optical element. The actuator is outside the optically effective surface and outside the region located behind the optically effective surface. The optical arrangement is set up to deform the optically effective surface.
    Type: Grant
    Filed: July 20, 2021
    Date of Patent: August 16, 2022
    Assignee: Carl Zeiss SMT GmbH
    Inventors: Judith Fingerhuth, Norbert Wabra, Sonja Schneider, Ferdinand Djuric-Rissner, Peter Graf, Reimar Finken
  • Publication number: 20220254152
    Abstract: A method for learning disentangled representations of videos is presented. The method includes feeding each frame of video data into an encoder to produce a sequence of visual features, passing the sequence of visual features through a deep convolutional network to obtain a posterior of a dynamic latent variable and a posterior of a static latent variable, sampling static and dynamic representations from the posterior of the static latent variable and the posterior of the dynamic latent variable, respectively, concatenating the static and dynamic representations to be fed into a decoder to generate reconstructed sequences, and applying three regularizers to the dynamic and static latent variables to trigger representation disentanglement. To facilitate the disentangled sequential representation learning, orthogonal factorization in generative adversarial network (GAN) latent space is leveraged to pre-train a generator as a decoder in the method.
    Type: Application
    Filed: January 27, 2022
    Publication date: August 11, 2022
    Inventors: Renqiang Min, Hans Peter Graf, Ligong Han
  • Publication number: 20220237884
    Abstract: A computer-implemented method is provided for action localization. The method includes converting one or more video frames into person keypoints and object keypoints. The method further includes embedding position, timestamp, instance, and type information with the person keypoints and object keypoints to obtain keypoint embeddings. The method also includes predicting, by a hierarchical transformer encoder using the keypoint embeddings, human actions and bounding box information of when and where the human actions occur in the one or more video frames.
    Type: Application
    Filed: January 27, 2022
    Publication date: July 28, 2022
    Inventors: Asim Kadav, Farley Lai, Hans Peter Graf, Yi Huang
  • Publication number: 20220171989
    Abstract: A computer-implemented method for representation disentanglement is provided. The method includes encoding an input vector into an embedding. The method further includes learning, by a hardware processor, disentangled representations of the input vector including a style embedding and a content embedding by performing sample-based mutual information minimization on the embedding under a Wasserstein distance regularization and a Kullback-Leibler (KL) divergence. The method also includes decoding the style and content embeddings to obtain a reconstructed vector.
    Type: Application
    Filed: November 18, 2021
    Publication date: June 2, 2022
    Inventors: Renqiang Min, Asim Kadav, Hans Peter Graf, Ligong Han
  • Publication number: 20220130490
    Abstract: Methods and systems for generating a peptide sequence include transforming an input peptide sequence into disentangled representations, including a structural representation and an attribute representation, using an autoencoder model. One of the disentangled representations is modified. The disentangled representations, including the modified disentangled representation, are transformed to generate a new peptide sequence using the autoencoder model.
    Type: Application
    Filed: October 26, 2021
    Publication date: April 28, 2022
    Inventors: Renqiang Min, Igor Durdanovic, Hans Peter Graf
  • Publication number: 20220101007
    Abstract: A method for using a multi-hop reasoning framework to perform multi-step compositional long-term reasoning is presented. The method includes extracting feature maps and frame-level representations from a video stream by using a convolutional neural network (CNN), performing object representation learning and detection, linking objects through time via tracking to generate object tracks and image feature tracks, feeding the object tracks and the image feature tracks to a multi-hop transformer that hops over frames in the video stream while concurrently attending to one or more of the objects in the video stream until the multi-hop transformer arrives at a correct answer, and employing video representation learning and recognition from the objects and image context to locate a target object within the video stream.
    Type: Application
    Filed: September 1, 2021
    Publication date: March 31, 2022
    Inventors: Asim Kadav, Farley Lai, Hans Peter Graf, Alexandru Niculescu-Mizil, Renqiang Min, Honglu Zhou
  • Publication number: 20210349399
    Abstract: A projection exposure apparatus for semiconductor technology includes an optical arrangement with an optical element having an optically effective surface. The optical arrangement also includes an actuator embedded in the optical element. The actuator is outside the optically effective surface and outside the region located behind the optically effective surface. The optical arrangement is set up to deform the optically effective surface.
    Type: Application
    Filed: July 20, 2021
    Publication date: November 11, 2021
    Inventors: Judith Fingerhuth, Norbert Wabra, Sonja Schneider, Ferdinand Djuric-Rissner, Peter Graf, Reimar Finken
  • Publication number: 20210319847
    Abstract: A method is provided for peptide-based vaccine generation. The method receives a dataset of positive and negative binding peptide sequences. The method pre-trains a set of peptide binding property predictors on the dataset to generate training data. The method trains a Wasserstein Generative Adversarial Network (WGAN) only on the positive binding peptide sequences, in which a discriminator of the WGAN is updated to distinguish generated peptide sequences from sampled positive peptide sequences from the training data, and a generator of the WGAN is updated to fool the discriminator. The method trains the WGAN only on the positive binding peptide sequences while simultaneously updating the generator to minimize a kernel Maximum Mean Discrepancy (MMD) loss between the generated peptide sequences and the sampled peptide sequences and maximize prediction accuracies of a set of pre-trained peptide binding property predictors with parameters of the set of pre-trained peptide binding property predictors being fixed.
    Type: Application
    Filed: March 10, 2021
    Publication date: October 14, 2021
    Inventors: Renqiang Min, Wenchao Yu, Hans Peter Graf, Igor Durdanovic
  • Patent number: 11087452
    Abstract: A false alarm reduction system and method are provided for reducing false alarms in an automatic defect detection system. The false alarm reduction system includes a defect detection system, generating a list of image boxes marking detected potential defects in an input image. The false alarm reduction system further includes a feature extractor, transforming each of the image boxes in the list into a respective set of numerical features. The false alarm reduction system also includes a classifier, computing as a classification outcome for the each of the image boxes whether the detected potential defect is a true defect or a false alarm responsive to the respective set of numerical features for each of the image boxes.
    Type: Grant
    Filed: January 16, 2019
    Date of Patent: August 10, 2021
    Inventors: Alexandru Niculescu-Mizil, Renqiang Min, Eric Cosatto, Farley Lai, Hans Peter Graf, Xavier Fontaine
  • Patent number: 11087174
    Abstract: A method is provided for visual inspection. The method includes learning, by a processor, group disentangled visual feature embedding vectors of input images. The input images include defective objects and defect-free objects. The method further includes generating, by the processor using a weight generation network, classification weights from visual features and semantic descriptions. Both the visual features and the semantic descriptions are for predicting defective and defect-free labels. The method also includes calculating, by the processor, a cosine similarity score between the classification weights and the group disentangled visual feature embedding vectors. The method additionally includes episodically training, by the processor, the weight generation network on the input images to update parameters of the weight generation network.
    Type: Grant
    Filed: September 24, 2019
    Date of Patent: August 10, 2021
    Inventors: Renqiang Min, Kai Li, Bing Bai, Hans Peter Graf
  • Patent number: 11087184
    Abstract: A computer-implemented method and system are provided for training a model for New Class Categorization (NCC) of a test image. The method includes decoupling, by a hardware processor, a feature extraction part from a classifier part of a deep classification model by reparametrizing learnable weight variables of the classifier part as a combination of learnable variables of the feature extraction part and of a classification weight generator of the classifier part. The method further includes training, by the hardware processor, the deep classification model to obtain a trained deep classification model by (i) learning the feature extraction part as a multiclass classification task, and (ii) episodically training the classifier part by learning a classification weight generator which outputs classification weights given a training image.
    Type: Grant
    Filed: September 24, 2019
    Date of Patent: August 10, 2021
    Inventors: Renqiang Min, Kai Li, Bing Bai, Hans Peter Graf
  • Patent number: 11055605
    Abstract: A computer-implemented method executed by a processor for training a neural network to recognize driving scenes from sensor data received from vehicle radar is presented. The computer-implemented method includes extracting substructures from the sensor data received from the vehicle radar to define a graph having a plurality of nodes and a plurality of edges, constructing a neural network for each extracted substructure, combining the outputs of each of the constructed neural networks for each of the plurality of edges into a single vector describing a driving scene of a vehicle, and classifying the single vector into a set of one or more dangerous situations involving the vehicle.
    Type: Grant
    Filed: October 17, 2017
    Date of Patent: July 6, 2021
    Inventors: Hans Peter Graf, Eric Cosatto, Iain Melvin
  • Publication number: 20210174784
    Abstract: Methods and systems for disentangled data generation include accessing a dataset including pairs, each formed from a given input text structure and a given style label for the input text structures. An encoder is trained to disentangle a sequential text input into disentangled representations, including a content embedding and a style embedding, based on a subset of the dataset, using an objective function that includes a regularization term that minimizes mutual information between the content embedding and the style embedding. A generator is trained to generate a text output that includes content from the style embedding, expressed in a style other than that represented by the style embedding of the text input.
    Type: Application
    Filed: December 8, 2020
    Publication date: June 10, 2021
    Inventors: Renqiang Min, Christopher Malon, Hans Peter Graf
  • Publication number: 20210142120
    Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a variational autoencoder, a plurality of supervision signals. The method further includes accessing, by the variational autoencoder, a plurality of auxiliary tasks that utilize the supervision signals as reward signals to learn a disentangled representation. The method also includes training the variational autoencoder to disentangle a sequential data input into a time-invariant factor and a time-varying factor using a self-supervised training approach which is based on outputs of the auxiliary tasks obtained by using the supervision signals to accomplish the plurality of auxiliary tasks.
    Type: Application
    Filed: November 3, 2020
    Publication date: May 13, 2021
    Inventors: Renqiang Min, Yizhe Zhu, Asim Kadav, Hans Peter Graf
  • Publication number: 20210117556
    Abstract: An apparatus, method, and system assess the trustworthiness of a design representation while maintaining its confidentiality and thwarting attempts at unauthorized access, misappropriation, and reverse engineering of confidential proprietary aspects of the design representation and/or its bit stream. A utility/tool is provided for trust assessment and verification of designs and/or bit streams. The utility/tool may be instantiated on a semiconductor device or implemented as a utility executable on a mobile computing device or other information processing system, apparatus, or network.
    Type: Application
    Filed: December 28, 2020
    Publication date: April 22, 2021
    Inventors: Jonathan Peter GRAF, Ali Asgar Ali Akbar SOHANGHPURWALA, Scott Jeffery HARPER
  • Publication number: 20210082144
    Abstract: Aspects of the present disclosure describe systems, methods and structures for an efficient multi-person posetracking method that advantageously achieves state-of-the-art performance on PoseTrack datasets by only using keypoint information in a tracking step without optical flow or convolution routines. As a consequence, our method has fewer parameters and FLOPs and achieves faster FPS. Our method benefits from our parameter-free tracking method that outperforms commonly used bounding box propagation in top-down methods. Finally, we disclose tokenization and embedding multi-person pose keypoint information in the transformer architecture that can be re-used for other pose tasks such as pose-based action recognition.
    Type: Application
    Filed: September 9, 2020
    Publication date: March 18, 2021
    Applicant: NEC LABORATORIES AMERICA, INC
    Inventors: Asim KADAV, Farley LAI, Hans Peter GRAF, Michael SNOWER
  • Patent number: 10902132
    Abstract: An apparatus, method and system are disclosed which may be used for assessing the trustworthiness of a particular proprietary microelectronics device design representation in a manner that will maintain its confidentiality and, among other things, thwart attempts at unauthorized access, misappropriation and reverse engineering of the confidential proprietary aspects contained in the design representation and/or its bit stream design implementation format. The disclosed method includes performing a process for assessing/verifying a particular microelectronics device design representation and then providing some indication of the trustworthiness of that representation. An example utility/tool which implements the disclosed method is described that is particularly useful for trust assessment and verification of FPGA designs.
    Type: Grant
    Filed: August 25, 2017
    Date of Patent: January 26, 2021
    Assignee: Graf Research Corporation
    Inventors: Jonathan Peter Graf, Ali Asgar Ali Akbar Sohanghpurwala, Scott Jeffery Harper
  • Patent number: 10885627
    Abstract: Methods and systems for detecting and correcting anomalous inputs include training a neural network to embed high-dimensional input data into a low-dimensional space with an embedding that preserves neighbor relationships. Input data items are embedded into the low-dimensional space to form respective low-dimensional codes. An anomaly is determined among the high-dimensional input data based on the low-dimensional codes. The anomaly is corrected.
    Type: Grant
    Filed: April 1, 2019
    Date of Patent: January 5, 2021
    Inventors: Renqiang Min, Farley Lai, Eric Cosatto, Hans Peter Graf
  • Patent number: 10885437
    Abstract: Security systems and methods for detecting intrusion events include one or more sensors configured to monitor an environment. A pruned convolutional neural network (CNN) is configured process information from the one or more sensors to classify events in the monitored environment. CNN filters having the smallest summed weights have been pruned from the pruned CNN. An alert module is configured to detect an intrusion event in the monitored environment based on event classifications. A control module is configured to perform a security action based on the detection of an intrusion event.
    Type: Grant
    Filed: May 9, 2017
    Date of Patent: January 5, 2021
    Inventors: Asim Kadav, Igor Durdanovic, Hans Peter Graf, Hao Li