公开(公告)号：US20240028904A1

公开(公告)日：2024-01-25

申请号：US18476078

申请日：2023-09-27

Applicant: QUALCOMM Incorporated

Inventor： Songan MAO ,  Youngmin HUH ,  Ehsan SHAHRIAN VARNOUSFADERANI ,  Ajit CHOURASIA ,  Donald GOSNELL ,  Muhua LI ,  Denis MAMEDOV

IPC: G06N3/084 ,  G06T3/40 ,  G06V10/25 ,  G06V10/22 ,  G06V20/40 ,  H04N23/63 ,  G06V10/764 ,  G06V10/82 ,  G06V10/32 ,  G06V10/62

CPC classification number: G06N3/084 ,  G06T3/40 ,  G06V10/25 ,  G06V10/235 ,  G06V20/40 ,  H04N23/631 ,  G06V10/764 ,  G06V10/82 ,  G06V10/32 ,  G06V10/62 ,  G06V20/46

Abstract: Techniques are provided for processing one or more frames. For example, a region of interest can be determined in a first frame of a sequence of frames. The region of interest in the first frame includes an object having a size in the first frame. A portion of a second frame of the sequence of frames (occurring after the first frame in the sequence of frames) can be cropped and scaled to cause the object in the second frame to have a same size (and in some cases a same location) as the object in the first frame.

公开(公告)号：US20190304102A1

公开(公告)日：2019-10-03

申请号：US16290790

申请日：2019-03-01

Applicant: QUALCOMM Incorporated

Inventor： Ying CHEN ,  Songan MAO ,  Yang ZHOU ,  Karthik NAGARAJAN

IPC: G06T7/246 ,  G06T7/73 ,  G06K9/62 ,  G06T7/11 ,  G06N20/00 ,  G06N3/08

Abstract: Techniques and systems are provided for classifying objects in one or more video frames. An object tracker associated with an object in a current video frame can be selected for object classification. Object classification can be determined to be performed in a next video frame (instead of the current video frame) for the object associated with the selected tracker. An image patch to use for the object classification can be obtained from the next video frame. The image patch can be based on a first bounding region associated with the object tracker in the current video frame, can be based on a second bounding region associated with the tracker in the next video frame, or can be based on both the first and second bounding regions. The object classification can be performed for the object associated with the selected object tracker using the image patch from the next video frame.

公开(公告)号：US20210365707A1

公开(公告)日：2021-11-25

申请号：US17239300

申请日：2021-04-23

Applicant: QUALCOMM Incorporated

Inventor： Songan MAO ,  Youngmin HUH ,  Ehsan SHAHRIAN VARNOUSFADERANI ,  Ajit CHOURASIA ,  Donald GOSNELL ,  Muhua LI ,  Denis MAMEDOV

IPC: G06K9/32 ,  G06K9/20 ,  G06T3/40 ,  G06K9/00 ,  H04N5/232

Abstract: Techniques are provided for processing one or more frames. For example, a region of interest can be determined in a first frame of a sequence of frames. The region of interest in the first frame includes an object having a size in the first frame. A portion of a second frame of the sequence of frames (occurring after the first frame in the sequence of frames) can be cropped and scaled to cause the object in the second frame to have a same size (and in some cases a same location) as the object in the first frame.

公开(公告)号：US20210258405A1

公开(公告)日：2021-08-19

申请号：US16809022

申请日：2020-03-04

Applicant: QUALCOMM Incorporated

Inventor： Ajit CHOURASIA ,  Jaikanth KRISHNASWAMY ,  Rasjinder SINGH ,  Vijaya Datta MAYYURI ,  Songan MAO

IPC: H04L29/06 ,  H04L29/08 ,  H04L12/26

Abstract: Methods, systems, and devices are provided for supporting hypertext transfer protocol (HTTP) download of a content item by a computing device. Various embodiments may enable swift content download (SCD). Once SCD is triggered, the current request to the server may be closed. SCD partitions the content into fragments (e.g., byte ranges) spanning the entire file content, and then simultaneously requests the fragments individually over multiple HTTP requests in a multi-threaded framework leveraging multiple network connections and interfaces (e.g., WiFi and 3G/4G/5G).