公开(公告)号：US11017556B2

公开(公告)日：2021-05-25

申请号：US16152303

申请日：2018-10-04

Applicant: NVIDIA Corporation

Inventor： Xiaodong Yang ,  Xitong Yang ,  Fanyi Xiao ,  Ming-Yu Liu ,  Jan Kautz

IPC: G06T7/73 ,  G06K9/00 ,  G06T7/277

Abstract: Iterative prediction systems and methods for the task of action detection process an inputted sequence of video frames to generate an output of both action tubes and respective action labels, wherein the action tubes comprise a sequence of bounding boxes on each video frame. An iterative predictor processes large offsets between the bounding boxes and the ground-truth.

公开(公告)号：US11631239B2

公开(公告)日：2023-04-18

申请号：US17237728

申请日：2021-04-22

Applicant: NVIDIA Corporation

Inventor： Xiaodong Yang ,  Ming-Yu Liu ,  Jan Kautz ,  Fanyi Xiao ,  Xitong Yang

IPC: G06T7/73 ,  G06V10/82 ,  G06T7/277 ,  G06V40/20 ,  G06V10/25 ,  G06V10/764

Abstract: Iterative prediction systems and methods for the task of action detection process an inputted sequence of video frames to generate an output of both action tubes and respective action labels, wherein the action tubes comprise a sequence of bounding boxes on each video frame. An iterative predictor processes large offsets between the bounding boxes and the ground-truth.

公开(公告)号：US20210064931A1

公开(公告)日：2021-03-04

申请号：US16998914

申请日：2020-08-20

Applicant: NVIDIA Corporation

Inventor： Xiaodong Yang ,  Xitong Yang ,  Sifei Liu ,  Jan Kautz

IPC: G06K9/62 ,  G06K9/72 ,  G06K9/00 ,  G06N3/08 ,  G06N3/04

Abstract: There are numerous features in video that can be detected using computer-based systems, such as objects and/or motion. The detection of these features, and in particular the detection of motion, has many useful applications, such as action recognition, activity detection, object tracking, etc. The present disclosure provides a neural network that learns motion from unlabeled video frames. In particular, the neural network uses the unlabeled video frames to perform self-supervised hierarchical motion learning. The present disclosure also describes how the learned motion can be used in video action recognition.

公开(公告)号：US11594006B2

公开(公告)日：2023-02-28

申请号：US16998914

申请日：2020-08-20

Applicant: NVIDIA Corporation

Inventor： Xiaodong Yang ,  Xitong Yang ,  Sifei Liu ,  Jan Kautz

IPC: G06V10/34 ,  G06K9/62 ,  G06N3/04 ,  G06V10/40 ,  G06N3/088 ,  G06V20/40 ,  G06V30/262

Abstract: There are numerous features in video that can be detected using computer-based systems, such as objects and/or motion. The detection of these features, and in particular the detection of motion, has many useful applications, such as action recognition, activity detection, object tracking, etc. The present disclosure provides a neural network that learns motion from unlabeled video frames. In particular, the neural network uses the unlabeled video frames to perform self-supervised hierarchical motion learning. The present disclosure also describes how the learned motion can be used in video action recognition.