公开(公告)号：US20210342924A9

公开(公告)日：2021-11-04

申请号：US16728714

申请日：2019-12-27

Applicant: A9.com, Inc.

Inventor： R. Manmatha ,  Hexiang Hu ,  Deva Ramanan

IPC: G06Q30/06 ,  G06F16/951 ,  G06F3/0482 ,  G06F3/0481

Abstract: Various embodiments of a framework which allow, as an alternative to resource-taxing decompression, efficient computation of feature maps using a compressed content data subset, such as video, by exploiting the motion information, such as a motion vector, present in the compressed video. This framework allows frame-specific object recognition and action detection algorithms to be applied to compressed video and other media files by executing only on I-frames in a Group of Pictures and linearly interpolating the results. Training and machine learning increases recognition accuracy. Yielding significant computational gains, this approach accelerates frame-wise feature extraction I-frame/P-frame/P-frame videos as well as I-frame/P-frame/B-frame videos. The present techniques may also be used for segmentation to identify and label respective regions for objects in a video.

公开(公告)号：US10528819B1

公开(公告)日：2020-01-07

申请号：US15818390

申请日：2017-11-20

Applicant: A9.com, Inc.

Inventor： R. Manmatha ,  Hexiang Hu ,  Deva Ramanan

IPC: G06K9/00 ,  G06K9/62

Abstract: Various embodiments of a framework which allow, as an alternative to resource-taxing decompression, efficient computation of feature maps using a compressed content data subset, such as video, by exploiting the motion information, such as a motion vector, present in the compressed video. This framework allows frame-specific object recognition and action detection algorithms to be applied to compressed video and other media files by executing only on I-frames in a Group of Pictures and linearly interpolating the results. Training and machine learning increases recognition accuracy. Yielding significant computational gains, this approach accelerates frame-wise feature extraction I-frame/P-frame/P-frame videos as well as I-frame/P-frame/B-frame videos. The present techniques may also be used for segmentation to identify and label respective regions for objects in a video.

公开(公告)号：US11568545B2

公开(公告)日：2023-01-31

申请号：US16728714

申请日：2019-12-27

Applicant: A9.com, Inc.

Inventor： R. Manmatha ,  Hexiang Hu ,  Deva Ramanan

IPC: G06T7/20 ,  G06F3/04812 ,  G06F3/0482 ,  G06F16/951 ,  G06T7/174 ,  G06T7/246 ,  G06Q30/06

Abstract: Various embodiments of a framework which allow, as an alternative to resource-taxing decompression, efficient computation of feature maps using a compressed content data subset, such as video, by exploiting the motion information, such as a motion vector, present in the compressed video. This framework allows frame-specific object recognition and action detection algorithms to be applied to compressed video and other media files by executing only on I-frames in a Group of Pictures and linearly interpolating the results. Training and machine learning increases recognition accuracy. Yielding significant computational gains, this approach accelerates frame-wise feature extraction I-frame/P-frame/P-frame videos as well as I-frame/P-frame/B-frame videos. The present techniques may also be used for segmentation to identify and label respective regions for objects in a video.