Robert Boschgmbh

Amazon Technologies, Inc.

Chun-Hao Liu

Naveen Ramakrishnan

Jayanta Kumar Dutta

Burhaneddin Yaman

Maxim Arap

Tanvir Mahmud

Sheng Liu

At least part of a visual pattern may be detected, in an image of a video, at a location within the image. An occlusion determination may be performed corresponding to the at least part of the visual pattern. At least part of a virtual asset may be inserted, based at least in part on the occlusion determination, into the image at the location. An appearance of the at least part of the virtual asset within the image may be adjusted based at least in part on an appearance of the at least part of the visual pattern within the image.

Virtual asset insertion

Methods and systems for classifying a long-tail distribution of data. Data deriving from one or more sensors is classified into a plurality of classes by using (i) a feature-extractor backbone model configured to extract features from the data, and (ii) a classifier model configured to classify the data based on the extracted features. The plurality of classes are grouped, with each group assigned to a respective teacher model. Each respective teacher model is trained with the data in its respective group, as well as the feature-extractor backbone model. The outputs of the teacher models are then merged into a final class prediction model configured to classify the data.

Systems and methods for multi-teacher group-distillation for long-tail classification

Identifying key frames of a video for use in training a machine learning model is provided. Object detection is performed to identify frames of a video including target classes of objects of interest. Feature extraction is performed on the identified frames to generate raw feature vectors. The feature vectors are compressed into lower dimension vectors. The compressed feature vectors are compressed into a plurality of clusters. The clustered compressed feature vectors are filtered to identify the key frames from each of the plurality of clusters. The key frames may be provided as a representative data set of the video.

Automated key frame selection

Growing community of inventors

Fremont, CA, United States of America

Chun-Hao Liu