Phuong The Le

20040039774, Feb 26, 2004

Aug 20, 2002

10/223976

Ming Xu - San Ramon CA, US
Phuong Le - San Jose CA, US

G06F015/16

709/203000, 709/227000, 709/248000

A plurality of virtual circuits, each including at least two network nodes, may be established over a single network connection for inter-process messaging. The network connection may be opened asynchronously via a non-blocking open. A virtual circuit including three or more nodes may be implemented in a star formation or a relay formation. Messages may be sent as unicast or broadcast messages. An additional virtual circuit may be opened for the purpose of transmitting status information regarding the network connection between the networked computer systems.

20210166035, Jun 3, 2021

Dec 14, 2020

17/120525

- Mountain View CA, US
Tomas Izo - San Francisco CA, US
Apostol Natsev - Sunnyvale CA, US
Sami Abu-El-Haija - San Francisco CA, US
George Dan Toderici - Mountain View CA, US
Susana Ricco - Redwood City CA, US
Balakrishnan Varadarajan - Sunnyvale CA, US
Nicola Muscettola - Sunnyvale CA, US
WeiHsin Gu - Redwood City CA, US
Weilong Yang - Fremont CA, US
Nitin Khandelwal - Milpitas CA, US
Phuong Le - Sunnyvale CA, US

G06K 9/00
G06F 16/783

A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.

20190130192, May 2, 2019

Oct 31, 2017

15/798733

- Mountain View CA, US
Andrew Dahley - San Francisco CA, US
Phuong Le - Sunnyvale CA, US
Mark Bowers - Mountain View CA, US
Ignacio Garcia Dorado - Mountain View CA, US
Robin Debreuil - Mountain View CA, US
William Lindmeier - Mountain View CA, US
Brian Allen - Mountain View CA, US
Ashley Ma - San Francisco CA, US
Pascal Getreuer - San Francisco CA, US

G06K 9/00
H04N 5/14
G11B 27/036
H04N 5/262

The present disclosure provides systems and methods that generate a summary storyboard from a plurality of image frames. An example computer-implemented method can include inputting a plurality of image frames into a machine-learned model and receiving as an output of the machine-learned model, object data that describes the respective locations of a plurality of objects recognized in the plurality of image frames. The method can include generating a plurality of image crops that respectively include the plurality of objects and arranging two or more of the plurality of image crops to generate a storyboard.

20180239964, Aug 23, 2018

Apr 23, 2018

15/959858

- Mountain View CA, US
Tomas Izo - San Francisco CA, US
Apostol Natsev - Sunnyvale CA, US
Sami Abu-El-Haija - San Francisco CA, US
George Dan Toderici - Mountain View CA, US
Susanna Ricco - Redwood City CA, US
Balakrishnan Varadarajan - Sunnyvale CA, US
Nicola Muscettola - Sunnyvale CA, US
WeiHsin Gu - Redwood City CA, US
Weilong Yang - Fremont CA, US
Nitin Khandelwal - Milpitas CA, US
Phuong Le - Sunnyvale CA, US

G06K 9/00
G06F 17/30

A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.

20160070962, Mar 10, 2016

Sep 8, 2015

14/848216

- Mountain View CA, US
Tomas Izo - San Francisco CA, US
Apostol Natsev - Sunnyvale CA, US
Sami Abu-El-Haija - San Francisco CA, US
George Dan Toderici - Mountain View CA, US
Susanna Ricco - Rewood City CA, US
Balakrishnan Varadarajan - Sunnyvale CA, US
Nicola Muscettola - Sunnyvale CA, US
WeiHsin Gu - Redwood City CA, US
Weilong Yang - Fremont CA, US
Nitin Khandelwal - Milpitas CA, US
Phuong Le - Sunnyvale CA, US

G06K 9/00
G06F 17/30

A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.