公开(公告)号：US11600069B2

公开(公告)日：2023-03-07

申请号：US17144205

申请日：2021-01-08

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Tianwei Lin ,  Xin Li ,  Dongliang He ,  Fu Li ,  Hao Sun ,  Shilei Wen ,  Errui Ding

IPC: G06K9/00 ,  G06K9/62 ,  G06V20/40

Abstract: A method and apparatus for detecting a temporal action of a video, an electronic device and a storage medium are disclosed, which relates to the field of video processing technologies. An implementation includes: acquiring an initial temporal feature sequence of a video to be detected; acquiring, by a pre-trained video-temporal-action detecting module, implicit features and explicit features of a plurality of configured temporal anchor boxes based on the initial temporal feature sequence; and acquiring, by the video-temporal-action detecting module, the starting position and the ending position of a video clip containing a specified action, the category of the specified action and the probability that the specified action belongs to the category from the plural temporal anchor boxes according to the explicit features and the implicit features of the plural temporal anchor boxes.

公开(公告)号：US11410422B2

公开(公告)日：2022-08-09

申请号：US16905482

申请日：2020-06-18

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Dongliang He ,  Xiang Zhao ,  Jizhou Huang ,  Fu Li ,  Xiao Liu ,  Shilei Wen

IPC: G06V20/40 ,  G06N3/00 ,  G06V10/40 ,  G06F16/783 ,  G06N3/08 ,  G06N3/04 ,  G06F16/00 ,  G06K9/62

Abstract: A method and an apparatus for grounding a target video clip in a video are provided. The method includes: determining a current video clip in the video based on a current position; acquiring descriptive information indicative of a pre-generated target video clip descriptive feature, and executing a target video clip determining step which includes: determining current state information of the current video clip, wherein the current state information includes information indicative of a feature of the current video clip; generating a current action policy based on the descriptive information and the current state information, the current action policy being indicative of a position change of the current video clip in the video; the method further comprises: in response to reaching a preset condition, using a video clip resulting from executing the current action policy on the current video clip as the target video clip.

公开(公告)号：US11259029B2

公开(公告)日：2022-02-22

申请号：US16797911

申请日：2020-02-21

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Zhichao Zhou ,  Dongliang He ,  Fu Li ,  Xiang Zhao ,  Xin Li ,  Zhizhen Chi ,  Xiang Long ,  Hao Sun

IPC: H04N19/14 ,  H04N19/12 ,  H04N19/625 ,  G06N3/08

Abstract: A method, device, apparatus for predicting a video coding complexity and a computer-readable storage medium are provided. The method includes: acquiring an attribute feature of a target video; extracting a plurality of first target image frames from the target video; performing a frame difference calculation on the plurality of the first target image frames, to acquire a plurality of first frame difference images; determining a histogram feature for frame difference images of the target video according to a statistical histogram of each first frame difference image; and inputting a plurality of features of the target video into a coding complexity prediction model to acquire a coding complexity prediction value of the target video. Through the above method, the BPP prediction value can be acquired intelligently.

公开(公告)号：US20210334579A1

公开(公告)日：2021-10-28

申请号：US17184379

申请日：2021-02-24

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Tianwei LIN ,  Xin Li ,  Fu Li ,  Dongliang He ,  Hao Sun ,  Henan Zhang

IPC: G06K9/62 ,  G06N3/04 ,  G06K9/00

Abstract: A method and apparatus for processing a video frame are provided. The method may include: converting, using an optical flow generated based on a previous frame and a next frame of adjacent frames in a video, a feature map of the previous frame to obtain a converted feature map; determining, based on an error of the optical flow, a weight of the converted feature map, and obtaining a fused feature map based on a weighted result of a feature of the converted feature map and a feature of a feature map of the next frame; and updating the feature map of the next frame as the fused feature map.

公开(公告)号：US20210019531A1

公开(公告)日：2021-01-21

申请号：US16830895

申请日：2020-03-26

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Xiang Long ,  Dongliang He ,  Fu Li ,  Zhizhen Chi ,  Zhichao Zhou ,  Xiang Zhao ,  Ping Wang ,  Hao Sun ,  Shilei Wen ,  Errui Ding

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62

Abstract: a method and an apparatus for classifying a video are provided. The method may include: acquiring a to-be-classified video; extracting a set of multimodal features of the to-be-classified video; inputting the set of multimodal features into a post-fusion model corresponding to each modal respectively, to obtain multimodal category information of the to-be-classified video; and fusing the multimodal category information of the to-be-classified video, to obtain category information of the to-be-classified video. This embodiment improves the accuracy of video classification.