公开(公告)号：US12238451B2

公开(公告)日：2025-02-25

申请号：US18055301

申请日：2022-11-14

Applicant: Adobe Inc.

Inventor： Uttaran Bhattacharya ,  Gang Wu ,  Viswanathan Swaminathan ,  Stefano Petrangeli

IPC: H04N7/00 ,  G06T11/60

Abstract: Embodiments are disclosed for predicting, using neural networks, editing operations for application to a video sequence based on processing conversational messages by a video editing system. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a video sequence and text sentences, the text sentences describing a modification to the video sequence, mapping, by a first neural network content of the text sentences describing the modification to the video sequence to a candidate editing operation, processing, by a second neural network, the video sequence to predict parameter values for the candidate editing operation, and generating a modified video sequence by applying the candidate editing operation with the predicted parameter values to the video sequence.

公开(公告)号：US12192681B2

公开(公告)日：2025-01-07

申请号：US18242252

申请日：2023-09-05

Applicant: Cloud Byte LLC.

Inventor： Takeshi Arikuma ,  Masahiro Tani

IPC: H04N7/00 ,  G08B13/16 ,  G08B13/196 ,  G08B25/08 ,  H04N7/18 ,  G06V20/52

Abstract: Event-related data based on an image that has been captured is generated. Coverage information relating to imaging range is compared to the event-related data. The cameras that can capture an image of the event, based on a comparing result, are listed so that an operator can select one of the listed cameras.

公开(公告)号：US20250008127A1

公开(公告)日：2025-01-02

申请号：US18884379

申请日：2024-09-13

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： Qian XU ,  Yunfei ZHENG ,  Xiaoan LU ,  Peng YIN ,  Joel SOLE

IPC: H04N19/186 ,  H04N7/00 ,  H04N19/11 ,  H04N19/147 ,  H04N19/176 ,  H04N19/196 ,  H04N19/46 ,  H04N19/463 ,  H04N19/70

Abstract: Methods and apparatus are provided for improved chroma encoding and decoding. An apparatus includes an encoder (400) for encoding picture data for at least a block in a picture. Multiple partition types are supported for intra chroma coding of the block. The multiple partition types include a set of chroma partition types and a set of luma partition types. The set of chroma partition types are different than the set of luma partition types.

公开(公告)号：US20240314267A1

公开(公告)日：2024-09-19

申请号：US18122315

申请日：2023-03-16

Applicant: ATI TECHNOLOGIES ULC

Inventor： Wing-Chi Chow

IPC: H04N7/00 ,  H04N7/01 ,  H04N7/025

CPC classification number: H04N7/007 ,  H04N7/0122 ,  H04N7/025

Abstract: In response to a video aspect ratio of a frame of video not matching an aspect ratio of a display panel of a display device, a source device of a processing system transmits only the frame to the display device and metadata indicating that the display device is to generate bars for letterboxing or pillarboxing. By generating the bars for letterboxing or pillarboxing at the display device instead of transmitting the bars from the source device to the display device or storing the bars at a frame buffer of the display device, the processing system conserves power and bandwidth.

公开(公告)号：US12094212B2

公开(公告)日：2024-09-17

申请号：US18213516

申请日：2023-06-23

Applicant: Intellective Ai, Inc.

Inventor： Wesley Kenneth Cobb ,  Ming-Jung Seow ,  Gang Xu ,  Kishor Adinath Saitwal ,  Anthony Akins ,  Kerry Joseph ,  Dennis G. Urech

IPC: H04N7/18 ,  G06F18/40 ,  G06N20/00 ,  G06V10/778 ,  G06V20/52 ,  G06V40/10 ,  G08B21/18 ,  G08B23/00 ,  G08B29/18 ,  H04N7/00 ,  G08B13/196

CPC classification number: G06V20/52 ,  G06F18/41 ,  G06N20/00 ,  G06V10/7788 ,  G06V20/53 ,  G06V40/103 ,  G08B21/182 ,  G08B23/00 ,  G08B29/185 ,  H04N7/002 ,  G08B13/19608

Abstract: Alert directives and focused alert directives allow a user to provide feedback to a behavioral recognition system to always or never publish an alert for certain events. Such an approach bypasses the normal publication methods of the behavioral recognition system yet does not obstruct the system's learning procedures.

公开(公告)号：US20240292000A1

公开(公告)日：2024-08-29

申请号：US18659460

申请日：2024-05-09

Applicant: Sun Patent Trust

Inventor： Toshiyasu SUGIO ,  Takahiro Nishi ,  Youji Shibahara ,  Kyoko Tanikawa ,  Hisao Sasai ,  Toru Matsunobu ,  Kengo Terada

IPC: H04N19/139 ,  H04N7/00 ,  H04N19/105 ,  H04N19/124 ,  H04N19/13 ,  H04N19/137 ,  H04N19/15 ,  H04N19/159 ,  H04N19/172 ,  H04N19/176 ,  H04N19/44 ,  H04N19/503 ,  H04N19/51 ,  H04N19/513 ,  H04N19/52 ,  H04N19/56 ,  H04N19/567 ,  H04N19/593 ,  H04N19/61

CPC classification number: H04N19/139 ,  H04N7/00 ,  H04N19/105 ,  H04N19/124 ,  H04N19/13 ,  H04N19/137 ,  H04N19/15 ,  H04N19/159 ,  H04N19/176 ,  H04N19/44 ,  H04N19/503 ,  H04N19/51 ,  H04N19/513 ,  H04N19/52 ,  H04N19/56 ,  H04N19/567 ,  H04N19/593 ,  H04N19/61 ,  H04N19/172

Abstract: A moving picture coding apparatus includes an intra-inter prediction unit which calculates a second motion vector by performing a scaling process on a first motion vector of a temporally neighboring corresponding block, when selectively adding, to a list, a motion vector of each of one or more corresponding blocks each of which is either a block included in a current picture to be coded and spatially neighboring a current block to be coded or a block included in a picture other than the current picture and temporally neighboring the current block, determines whether the second motion vector has a magnitude that is within a predetermined magnitude or not within the predetermined magnitude, and adds the second motion vector to the list when the intra-inter prediction unit determines that the second motion vector has a magnitude that is within the predetermined magnitude range.

公开(公告)号：US12015872B2

公开(公告)日：2024-06-18

申请号：US17851958

申请日：2022-06-28

Applicant: SONY GROUP CORPORATION

Inventor： Ikuo Tsukagoshi

IPC: H04N7/00 ,  G06T5/50 ,  G06T5/92 ,  H04L65/70 ,  H04N19/46 ,  H04N19/70 ,  H04N21/236 ,  H04N21/434 ,  H04N21/84 ,  H04N23/00 ,  H04N23/76

CPC classification number: H04N7/005 ,  G06T5/50 ,  G06T5/92 ,  H04L65/70 ,  H04N19/46 ,  H04N19/70 ,  H04N21/236 ,  H04N21/434 ,  H04N21/84 ,  H04N23/00 ,  H04N23/76 ,  G06T2207/20208

Abstract: The present technology ensures that electrooptical conversion processing for transmission video data obtained using an HDR optoelectrical conversion characteristic is favorably carried out at a receiving side. The transmission video data is obtained by performing high dynamic range optoelectrical conversion on high dynamic range video data. A video stream is obtained by applying encoding processing to this transmission video data. A container in a predetermined format including this video stream is transmitted. Meta information indicating an electrooptical conversion characteristic corresponding to a high dynamic range optoelectrical conversion characteristic is inserted into a parameter set field in the video stream.

公开(公告)号：US12015782B2

公开(公告)日：2024-06-18

申请号：US18203709

申请日：2023-05-31

Applicant: Sun Patent Trust

Inventor： Toshiyasu Sugio ,  Takahiro Nishi ,  Youji Shibahara ,  Kyoko Tanikawa ,  Hisao Sasai ,  Toru Matsunobu ,  Kengo Terada

IPC: H04N19/00 ,  H04N7/00 ,  H04N19/105 ,  H04N19/124 ,  H04N19/13 ,  H04N19/137 ,  H04N19/139 ,  H04N19/15 ,  H04N19/159 ,  H04N19/176 ,  H04N19/44 ,  H04N19/503 ,  H04N19/51 ,  H04N19/513 ,  H04N19/52 ,  H04N19/56 ,  H04N19/567 ,  H04N19/593 ,  H04N19/61 ,  H04N19/172

CPC classification number: H04N19/139 ,  H04N7/00 ,  H04N19/105 ,  H04N19/124 ,  H04N19/13 ,  H04N19/137 ,  H04N19/15 ,  H04N19/159 ,  H04N19/176 ,  H04N19/44 ,  H04N19/503 ,  H04N19/51 ,  H04N19/513 ,  H04N19/52 ,  H04N19/56 ,  H04N19/567 ,  H04N19/593 ,  H04N19/61 ,  H04N19/172

Abstract: A moving picture coding apparatus includes an intra-inter prediction unit which calculates a second motion vector by performing a scaling process on a first motion vector of a temporally neighboring corresponding block, when selectively adding, to a list, a motion vector of each of one or more corresponding blocks each of which is either a block included in a current picture to be coded and spatially neighboring a current block to be coded or a block included in a picture other than the current picture and temporally neighboring the current block, determines whether the second motion vector has a magnitude that is within a predetermined magnitude or not within the predetermined magnitude, and adds the second motion vector to the list when the intra-inter prediction unit determines that the second motion vector has a magnitude that is within the predetermined magnitude range.

公开(公告)号：US12003892B2

公开(公告)日：2024-06-04

申请号：US17585419

申请日：2022-01-26

Applicant: Coretronic Corporation

Inventor： Chia-Chien Wu ,  Chen Hsiang Shih ,  Yi-Fa Wang ,  I-Han Chen

IPC: H04N7/00 ,  A61B90/00 ,  G02B27/01 ,  G16H30/40 ,  H04N5/272 ,  H04N7/18 ,  H04N23/57 ,  H04N23/80 ,  H04N23/90 ,  A61B90/50

CPC classification number: H04N7/181 ,  A61B90/361 ,  G02B27/0172 ,  G16H30/40 ,  H04N5/272 ,  H04N7/183 ,  H04N23/57 ,  H04N23/80 ,  H04N23/90 ,  A61B2090/365 ,  A61B2090/373 ,  A61B2090/502 ,  G02B2027/0138 ,  G02B2027/0141 ,  G02B2027/0178

Abstract: A medical image assistance system and a medical image assistance method are provided. During a medical process, an image capturing apparatus located at a local location captures a first image and transmits the first image to a control device located at the local location, and the control device transmits the first image captured by the image capturing apparatus to an electronic apparatus located at a remote location. The electronic apparatus performs a marking operation on the first image to generate a second image, and transmits the second image to the control device. The control device transmits the second image to a head-mounted display apparatus located at the local location so that the head-mounted display apparatus simultaneously displays the second image and a real-time local image. The first image and the second image are at least partially the same in content.

公开(公告)号：US20240163393A1

公开(公告)日：2024-05-16

申请号：US18055301

申请日：2022-11-14

Applicant: Adobe Inc.

Inventor： Uttaran BHATTACHARYA ,  Gang WU ,  Viswanathan SWAMINATHAN ,  Stefano PETRANGELI

IPC: H04N7/00 ,  G06T11/60

CPC classification number: H04N7/002 ,  G06T11/60

Abstract: Embodiments are disclosed for predicting, using neural networks, editing operations for application to a video sequence based on processing conversational messages by a video editing system. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a video sequence and text sentences, the text sentences describing a modification to the video sequence, mapping, by a first neural network content of the text sentences describing the modification to the video sequence to a candidate editing operation, processing, by a second neural network, the video sequence to predict parameter values for the candidate editing operation, and generating a modified video sequence by applying the candidate editing operation with the predicted parameter values to the video sequence.