Patents by Inventor Balamanohar Paluri

Balamanohar Paluri 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).

  • Publication number: 20190279053
    Abstract: A sample set of images is received. Each image in the sample set may be associated with one or more social cues. Correlation of each image in the sample set with an image class is scored based on the one or more social cues associated with the image. Based on the scoring, a training set of images to train a classifier is determined from the sample set. In an embodiment, an extent to which an evaluation set of images correlates with the image class is determined. The determination may comprise ranking a top scoring subset of the evaluation set of images.
    Type: Application
    Filed: November 15, 2018
    Publication date: September 12, 2019
    Inventors: Lubomir Bourdev, Balamanohar Paluri
  • Publication number: 20190244367
    Abstract: Systems, methods, and non-transitory computer-readable media can obtain a first video frame and a second video frame. The first video frame can be processed using a convolutional neural network to output a first set of feature maps. The second video frame can be processed using the convolutional neural network to output a second set of feature maps. The first set of feature maps and the second set of feature maps can be processed using a spatial matching layer of the convolutional neural network to determine an optical flow for at least one pixel.
    Type: Application
    Filed: December 5, 2018
    Publication date: August 8, 2019
    Inventor: Balamanohar Paluri
  • Patent number: 10360466
    Abstract: Systems, methods, and non-transitory computer-readable media can receive an image. One or more concepts depicted in the image are identified based on machine learning techniques. The one or more concepts are filtered based on filtering criteria to identify one or more selected concepts. An image description is generated comprising the one or more selected concepts.
    Type: Grant
    Filed: December 27, 2016
    Date of Patent: July 23, 2019
    Assignee: Facebook, Inc.
    Inventors: Shaomei Wu, Lada Ariana Adamic, Jeffrey C. Wieland, Omid Farivar, Hermes Germi Pique Corchs, Matt King, Brett Alden Lavalla, Balamanohar Paluri
  • Patent number: 10360498
    Abstract: Various embodiments of the present disclosure include systems, methods, and non-transitory computer storage media configured to identify a set of training content items, each of the set of training content items comprising video content. A category may be assigned to each of the set of training content items. A plurality of variations may be provided to the each of the set of training content items. A first content recognition module may be trained in an unsupervised process to associate the plurality of variations of the each of the set of training content items with the category assigned to the each of the set of training content items. A classification layer may be generated based on the training the first content recognition module in the unsupervised process. A second content recognition module may be trained in a supervised process based on the classification layer.
    Type: Grant
    Filed: December 18, 2014
    Date of Patent: July 23, 2019
    Assignee: Facebook, Inc.
    Inventors: Robert D. Fergus, Lubomir Bourdev, Balamanohar Paluri, Sainbayar Sukhbaatar
  • Publication number: 20190156011
    Abstract: Systems, methods, and non-transitory computer-readable media can detect an operation that causes a challenge response process to be initiated. An image category associated with a recognized category label can be identified. At least one image associated with the image category can be displayed during the challenge response process. The operation can be executed when the challenge response process, based on the at least one image, is successfully completed.
    Type: Application
    Filed: January 23, 2019
    Publication date: May 23, 2019
    Inventors: Nikhil Johri, Trevor M. Pottinger, Balamanohar Paluri
  • Patent number: 10255423
    Abstract: Systems, methods, and non-transitory computer-readable media can detect an operation that causes a challenge response process to be initiated. An image category associated with a recognized category label can be identified. At least one image associated with the image category can be displayed during the challenge response process. The operation can be executed when the challenge response process, based on the at least one image, is successfully completed.
    Type: Grant
    Filed: May 9, 2017
    Date of Patent: April 9, 2019
    Assignee: Facebook, Inc.
    Inventors: Nikhil Johri, Trevor M. Pottinger, Balamanohar Paluri
  • Patent number: 10198637
    Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.
    Type: Grant
    Filed: December 20, 2017
    Date of Patent: February 5, 2019
    Assignee: Facebook, Inc.
    Inventors: Du Le Hong Tran, Balamanohar Paluri, Lubomir Bourdev, Robert D. Fergus, Sumit Chopra
  • Patent number: 10181195
    Abstract: Systems, methods, and non-transitory computer-readable media can obtain a first video frame and a second video frame. The first video frame can be processed using a convolutional neural network to output a first set of feature maps. The second video frame can be processed using the convolutional neural network to output a second set of feature maps. The first set of feature maps and the second set of feature maps can be processed using a spatial matching layer of the convolutional neural network to determine an optical flow for at least one pixel.
    Type: Grant
    Filed: December 28, 2015
    Date of Patent: January 15, 2019
    Assignee: Facebook, Inc.
    Inventor: Balamanohar Paluri
  • Patent number: 10169686
    Abstract: A sample set of images is received. Each image in the sample set may be associated with one or more social cues. Correlation of each image in the sample set with an image class is scored based on the one or more social cues associated with the image. Based on the scoring, a training set of images to train a classifier is determined from the sample set. In an embodiment, an extent to which an evaluation set of images correlates with the image class is determined. The determination may comprise ranking a top scoring subset of the evaluation set of images.
    Type: Grant
    Filed: August 5, 2013
    Date of Patent: January 1, 2019
    Assignee: Facebook, Inc.
    Inventors: Lubomir Bourdev, Balamanohar Paluri
  • Publication number: 20180189281
    Abstract: Systems, methods, and non-transitory computer-readable media can receive a first content item having a set of frames. A binary hash code that represents the first content item is generated using at least an aggregation model and an iterative quantization hash model, the binary hash code being determined based at least in part on the set of frames of the first content item. The binary hash code is stored, wherein a similarity between the first content item and a second content item is capable of being measured based at least in part on a comparison of the binary hash code of the first content item and a binary hash code of the second content item.
    Type: Application
    Filed: December 30, 2016
    Publication date: July 5, 2018
    Inventors: Kai Li, Fei Yang, Balamanohar Paluri
  • Publication number: 20180181832
    Abstract: Systems, methods, and non-transitory computer-readable media can receive an image. One or more concepts depicted in the image are identified based on machine learning techniques. The one or more concepts are filtered based on filtering criteria to identify one or more selected concepts. An image description is generated comprising the one or more selected concepts.
    Type: Application
    Filed: December 27, 2016
    Publication date: June 28, 2018
    Inventors: Shaomei Wu, Lada Ariana Adamic, Jeffrey C. Wieland, Omid Farivar, Hermes Germi Pique Corchs, Matt King, Brett Alden Lavalla, Balamanohar Paluri
  • Publication number: 20180114069
    Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.
    Type: Application
    Filed: December 20, 2017
    Publication date: April 26, 2018
    Inventors: Du Le Hong Tran, Balamanohar Paluri, Lubomir Bourdev, Robert D. Fergus, Sumit Chopra
  • Publication number: 20180107881
    Abstract: Aspects determining anomalous events, wherein processors determine a trajectory of tracked movement of an object through an image field of a camera partitioned into a matrix grid of different local units. The aspects generate anomaly confidence decision values for image features extracted from video data of the tracked movement of the object as a function of fitting extracted image features to normal patterns of local motion pattern models defined by dominant distributions of extracted image features. The aspects further extract trajectory features from the video data relative to the trajectory of the tracked movement of the object, and generate global anomaly confidence decision values for the object trajectory as a function of fitting the extracted trajectory features to a normal learned motion trajectory model. The aspects determine anomalous events as a function of the generated global anomaly confidence decision value and the anomaly confidence decision values.
    Type: Application
    Filed: December 7, 2017
    Publication date: April 19, 2018
    Inventors: ANKUR DATTA, BALAMANOHAR PALURI, SHARATHCHANDRA U. PANKANTI, YUN ZHAI
  • Patent number: 9946926
    Abstract: Systems, methods, and non-transitory computer-readable media can calculate raw scores for a plurality of media items based on a classifier model and a target concept. The plurality of media items are ranked based on the raw scores. A review set of the plurality of media items is determined, the review set comprising a subset of the plurality of media items. Each of the media items of the review set is associated with a content depiction determination. A normalized score formula is calculated based on the raw scores and the content depiction determinations for the media items of the review set.
    Type: Grant
    Filed: July 7, 2017
    Date of Patent: April 17, 2018
    Assignee: Facebook, Inc.
    Inventors: Nikhil Johri, Balamanohar Paluri, Lubomir Bourdev
  • Patent number: 9928423
    Abstract: Local models learned from anomaly detection are used to rank detected anomalies. The local model patterns are defined from image feature values extracted from an image field of video image data with respect to different predefined spatial and temporal local units, wherein anomaly results are determined by fitting extracted image features to the local model patterns. Image features values extracted from the image field local units associated with anomaly results are normalized, and image feature values extracted from the image field local units are clustered. Weights for anomaly results are learned as a function of the relations of the normalized extracted image feature values to the clustered image feature values. The normalized values are multiplied by the learned weights to generate ranking values to rank the anomalies.
    Type: Grant
    Filed: September 4, 2015
    Date of Patent: March 27, 2018
    Assignee: International Business Machines Corporation
    Inventors: Ankur Datta, Balamanohar Paluri, Sharathchandra U. Pankanti, Yun Zhai
  • Patent number: 9892423
    Abstract: Systems, methods, and non-transitory computer readable media configured to receive an advertisement including an image. A fraud assessment value for the advertisement can be determined. An image assessment value for the image can be determined. The fraud assessment value and a threshold value for fraud assessment can be compared. The image assessment value and a threshold value for image assessment can be compared. Fraud associated with the advertisement can be determined based on comparison of the fraud assessment value and the threshold value for fraud assessment and comparison of the image assessment value and the threshold value for image assessment.
    Type: Grant
    Filed: March 24, 2015
    Date of Patent: February 13, 2018
    Assignee: Facebook, Inc.
    Inventors: Vivek Kaul, Tara Brittany Stewart, Utkarsh Lath, Michael Francis Zolli, Balamanohar Paluri, Nikhil Johri
  • Patent number: 9858484
    Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.
    Type: Grant
    Filed: December 30, 2014
    Date of Patent: January 2, 2018
    Assignee: Facebook, Inc.
    Inventors: Du Le Hong Tran, Balamanohar Paluri, Lubomir Bourdev, Robert D. Fergus, Sumit Chopra
  • Publication number: 20170308747
    Abstract: Systems, methods, and non-transitory computer-readable media can calculate raw scores for a plurality of media items based on a classifier model and a target concept. The plurality of media items are ranked based on the raw scores. A review set of the plurality of media items is determined, the review set comprising a subset of the plurality of media items. Each of the media items of the review set is associated with a content depiction determination. A normalized score formula is calculated based on the raw scores and the content depiction determinations for the media items of the review set.
    Type: Application
    Filed: July 7, 2017
    Publication date: October 26, 2017
    Inventors: Nikhil Johri, Balamanohar Paluri, Lubomir Bourdev
  • Publication number: 20170300784
    Abstract: Systems, methods, and non-transitory computer-readable media can identify a set of regions corresponding to a geographical area. A collection of training images can be acquired. Each training image in the collection can be associated with one or more respective recognized objects and with a respective region in the set of regions. Histogram metrics for a plurality of object categories within each region in the set of regions can be determined based at least in part on the collection of training images. A neural network can be developed based at least in part on the histogram metrics for the plurality of object categories within each region in the set of regions and on the collection of training images.
    Type: Application
    Filed: June 30, 2017
    Publication date: October 19, 2017
    Inventors: Kevin Dechau Tang, Lubomir Bourdev, Balamanohar Paluri, Robert D. Fergus
  • Patent number: 9767357
    Abstract: Systems, methods, and non-transitory computer-readable media can calculate raw scores for a plurality of media items based on a classifier model and a target concept. The plurality of media items are ranked based on the raw scores. A review set of the plurality of media items is determined, the review set comprising a subset of the plurality of media items. Each of the media items of the review set is associated with a content depiction determination. A normalized score formula is calculated based on the raw scores and the content depiction determinations for the media items of the review set.
    Type: Grant
    Filed: December 29, 2015
    Date of Patent: September 19, 2017
    Assignee: Facebook, Inc
    Inventors: Nikhil Johri, Balamanohar Paluri, Lubomir Bourdev