公开(公告)号：US20200074185A1

公开(公告)日：2020-03-05

申请号：US16678428

申请日：2019-11-08

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06K9/00 ,  G06T7/168 ,  G06N3/04 ,  G06F17/18 ,  G06T7/11 ,  G06T11/20

Abstract: Techniques related to automatically segmenting a video frame into fine grain object of interest and background regions using a ground truth segmentation of an object in a previous frame are discussed. Such techniques apply multiple levels of segmentation tracking and prediction based on color, shape, and motion of the segmentation to determine per-pixel object probabilities, and solve an energy summation model to generate a final segmentation for the video frame using the object probabilities.

公开(公告)号：US20240104380A1

公开(公告)日：2024-03-28

申请号：US18522657

申请日：2023-11-29

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06N3/08 ,  G06N5/046 ,  G06N20/00 ,  G06T7/10 ,  G06V10/44 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06N5/046 ,  G06N20/00 ,  G06T7/10 ,  G06V10/454 ,  G06V10/82 ,  G06T2207/10016 ,  G06T2207/20084

Abstract: Methods, systems and apparatuses may provide for technology that trains a neural network by inputting video data to the neural network, determining a boundary loss function for the neural network, and selecting weights for the neural network based at least in part on the boundary loss function, wherein the neural network outputs a pixel-level segmentation of one or more objects depicted in the video data. The technology may also operate the neural network by accepting video data and an initial feature set, conducting a tensor decomposition on the initial feature set to obtain a reduced feature set, and outputting a pixel-level segmentation of object(s) depicted in the video data based at least in part on the reduced feature set.

公开(公告)号：US20240029193A1

公开(公告)日：2024-01-25

申请号：US18374508

申请日：2023-09-28

Applicant: INTEL CORPORATION

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06T1/20 ,  G06T7/11 ,  G06T7/174 ,  G06T3/40 ,  G06T9/00 ,  G06F18/241 ,  G06V10/764 ,  G06V10/26 ,  G06V20/40

CPC classification number: G06T1/20 ,  G06T7/11 ,  G06T7/174 ,  G06T3/4046 ,  G06T9/002 ,  G06F18/241 ,  G06V10/764 ,  G06V10/26 ,  G06V20/46 ,  G06V20/49 ,  G06T2207/10016 ,  G06T2207/20221

Abstract: Techniques related to automatically segmenting video frames into per pixel fidelity object of interest and background regions are discussed. Such techniques include applying tessellation to a video frame to generate feature frames corresponding to the video frame and applying a segmentation network implementing context aware skip connections to an input volume including the feature frames and a context feature volume corresponding to the video frame to generate a segmentation for the video frame.

公开(公告)号：US11734561B2

公开(公告)日：2023-08-22

申请号：US17571737

申请日：2022-01-10

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06N3/08 ,  G06V20/40 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44 ,  G06V40/10 ,  G06V10/62

CPC classification number: G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V20/40 ,  G06V20/41 ,  G06V20/46 ,  G06V40/103 ,  G06V10/62

Abstract: An apparatus, method, system and computer readable medium for video tracking. An exemplar crop is selected to be tracked in an initial frame of a video. Bayesian optimization is applied with each subsequent frame of the video by building a surrogate model of an objective function using Gaussian Process Regression (GPR) based on similarity scores of candidate crops collected from a search space in a current frame of the video. A next candidate crop in the search space is determined using an acquisition function. The next candidate crop is compared to the exemplar crop using a Siamese neural network. Comparisons of new candidate crops to the exemplar crop are made using the Siamese neural network until the exemplar crop has been found in the current frame. The new candidate crops are selected based on an updated surrogate model.

公开(公告)号：US20230010230A1

公开(公告)日：2023-01-12

申请号：US17932339

申请日：2022-09-15

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Sovan Biswas ,  Giuseppe Raffa

IPC: G06V10/776 ,  G06V10/82 ,  G06V20/40 ,  G06V20/70 ,  G06V10/774

Abstract: Systems, apparatuses, and methods include technology that identifies, with a neural network, that a predetermined amount of a first action is completed at a first portion of a plurality of portions. A subset of the plurality of portions collectively represents the first action. The technology generates a first loss based on the predetermined amount of the first action being identified as being completed at the first portion. The technology updates the neural network based on the first loss.

公开(公告)号：US20220130130A1

公开(公告)日：2022-04-28

申请号：US17571737

申请日：2022-01-10

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06V10/46 ,  G06N3/08 ,  G06V10/426 ,  G06V20/40

Abstract: An apparatus, method, system and computer readable medium for video tracking. An exemplar crop is selected to be tracked in an initial frame of a video. Bayesian optimization is applied with each subsequent frame of the video by building a surrogate model of an objective function using Gaussian Process Regression (GPR) based on similarity scores of candidate crops collected from a search space in a current frame of the video. A next candidate crop in the search space is determined using an acquisition function. The next candidate crop is compared to the exemplar crop using a Siamese neural network. Comparisons of new candidate crops to the exemplar crop are made using the Siamese neural network until the exemplar crop has been found in the current frame. The new candidate crops are selected based on an updated surrogate model.

公开(公告)号：US20210209473A1

公开(公告)日：2021-07-08

申请号：US17212747

申请日：2021-03-25

Applicant: Intel Corporation

Inventor： Julio Cesar Zamora Esquivel ,  Jesus Adan Cruz Vargas ,  Nadine L. Dabby ,  Anthony Rhodes ,  Omesh Tickoo ,  Narayan Sundararajan ,  Lama Nachman

IPC: G06N3/08 ,  G06N3/04

Abstract: The present disclosure provides a machine learning model where each activation node within the model has an adaptive activation function defined in terms of an input and a hyperparameter of the model. Accordingly, each activation node can have a separate of distinct activation function, based on the adaptive activation function where the hyperparameter for each activation node is trained during overall training of the model. Furthermore, the present disclosure provides that a set of adaptive activation functions can be provided for each activation node such that a spike train of activations can be generated.

公开(公告)号：US20200026954A1

公开(公告)日：2020-01-23

申请号：US16586671

申请日：2019-09-27

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06K9/46 ,  G06K9/00 ,  G06N3/08

Abstract: An apparatus, method, system and computer readable medium for video tracking. An exemplar crop is selected to be tracked in an initial frame of a video. Bayesian optimization is applied with each subsequent frame of the video by building a surrogate model of an objective function using Gaussian Process Regression (GPR) based on similarity scores of candidate crops collected from a search space in a current frame of the video. A next candidate crop in the search space is determined using an acquisition function. The next candidate crop is compared to the exemplar crop using a Siamese neural network. Comparisons of new candidate crops to the exemplar crop are made using the Siamese neural network until the exemplar crop has been found in the current frame. The new candidate crops are selected based on an updated surrogate model.

公开(公告)号：US20200026928A1

公开(公告)日：2020-01-23

申请号：US16584709

申请日：2019-09-26

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06K9/00 ,  G06T7/20 ,  G06T7/174 ,  G06T7/00 ,  G06T7/70 ,  G06K9/62

Abstract: Techniques related to automatically segmenting video frames into per pixel dense object of interest and background regions are discussed. Such techniques include applying a segmentation convolutional neural network (CNN) to a CNN input including a current video frame, a previous video frame, an object of interest indicator frame, a motion frame, and multiple feature frames each including features compressed from feature layers of an object classification convolutional neural network as applied to the current video frame to generate candidate segmentations and selecting one of the candidate segmentations as a final segmentation of the current video frame.

公开(公告)号：US20240233379A1

公开(公告)日：2024-07-11

申请号：US18615839

申请日：2024-03-25

Applicant: Intel Corporation

Inventor： Anthony Rhodes

IPC: G06V20/40 ,  G06V10/80 ,  G06V10/82

CPC classification number: G06V20/49 ,  G06V10/80 ,  G06V20/41 ,  G06V20/44 ,  G06V20/46 ,  G06V10/82

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed to enhance action segmentation model with causal explanation capability. An example apparatus includes an interface circuitry to access a pre-trained action segmentation model, instructions, and processor circuitry to at least one of instantiate or execute the machine readable instructions to obtain action segmentation data from the pre-trained action segmentation model, the action segmentation data indicating action prediction for one or more frames of a video sequence, combine the obtained action segmentation data with input features extracted from the one or more video frames, and identify an antecedent action of at least one frame of the video sequence based on pooled importance scores for the frame, the pooled importance scores being calculated from the combined action segmentation data and input features.