Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Baidu Online Network Technology (beijing) Co., Ltd.

Baidu Online Network Technology Co., Ltd.

Dongliang He

Hao Sun

Fu Li

Shilei Wen

Errui Ding

Xiang Long

Zhichao Zhou

Ping Wang

Xiang Zhao

Xin Li

Chao Li

Xiao Xi Liu

Henan Zhang

Zhizhen Chi

Tianwei Lin

Yukang Ding

Hui Shen

Yuan Gao

Jizhou Huang

Xiao Tan

Hongwu Zhang

Xubin Li

Xiao Liu

An image filling method and apparatus, a device and a storage medium are disclosed. The image filling method includes: performing multilevel encoding processing on features of an image to be filled to generate multilevel encoded feature layers, sizes of the multilevel encoded feature layers being reduced layer by layer; performing layer-by-layer decoding processing on the multilevel encoded feature layers to obtain multilevel decoded feature layers and a first image, there being no missing region in the first image, wherein the layer-by-layer decoding processing includes a concatenation operation on a decoded feature layer and an encoded feature layer with a same size; and performing up-sampling processing on the first image to obtain multilevel up-sampled feature layers and a second image optimized by the up-sampling processing, the up-sampling processing including a concatenation operation on an up-sampled feature layer and a decoded feature layer with a same size.

Image filling method and apparatus, device, and storage medium

The satellite image processing method includes: acquiring a first target satellite image; defogging the first target satellite image through a first neural network to acquire a first satellite image; and adjusting an image quality parameter of the first satellite image through a second neural network to acquire a second satellite image.

Satellite image processing method, network training method, related devices and electronic device

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.

Method and apparatus for processing video frame

Embodiments of the present disclosure provide a method and apparatus for processing an image, and relates to the field of computer vision technology. The method may include: acquiring a value to be processed, where the value to be processed is associated with an image to be processed; and processing the value to be processed by using a quality scoring model to generate a score of the image to be processed in a target scoring domain, where the score of the image to be processed in the target scoring domain is related to an image quality of the image to be processed.

Method and apparatus for processing image

Embodiments of the present disclosure disclose a method and apparatus for identifying a video. A specific embodiment of the method includes: acquiring a predetermined number of video frames from a video to be identified to obtain a video frame sequence; performing the following processing step: importing the video frame sequence into a pre-trained video identification model to obtain a classification tag probability corresponding to the video frame sequence, wherein the classification tag probability is used to characterize a probability of identifying a corresponding tag category of the video to be identified; and setting, in response to the classification tag probability being greater than or equal to a preset identification accuracy threshold, a video tag for the video to be identified according to the classification tag probability, or else increasing the number of video frames in the video frame sequence and continuing to perform the above processing step.

Method and apparatus for identifying video

Embodiments of the present disclosure disclose a method and apparatus for searching a video segment, a device and a medium, and relate to the field of video data search. The method includes: sampling video frames from a target video and videos to be searched in a video library, and extracting features from the sampled frames; matching the target video and the videos to be searched according to the extracted features to determine a candidate video to be searched that matches the target video; determining at least one candidate video segment from the determined candidate video, and calculating a degree of matching between the target video and each candidate video segment based on the extracted features of each sampled frame; and determining a video segment matching the target video in the videos to be searched according to the calculated degree of matching between the target video and each candidate video segment.

Method and apparatus for searching video segment, device, and medium

A method includes screening, by a video-clip screening module in a video description model, a plurality of video proposal clips acquired from a video to be analyzed, to acquire a plurality of video clips suitable for description. The plural video proposal clips acquired from the video to be analyzed may be screened by the video-clip screening module to acquire the plural video clips suitable for description; and then, each video clip is described by a video-clip describing module, thus avoiding description of all the video proposal clips, only describing the screened video clips which have strong correlation with the video and are suitable for description, removing the interference of the description of the video clips which are not suitable for description in the description of the video, guaranteeing the accuracy of the final descriptions of the video clips, and improving the quality of the descriptions of the video clips.

Method and apparatus for detecting temporal action of video, electronic device and storage medium

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.

The present disclosure provides a method and apparatus for detecting a region of interest in a video, a device and a storage medium. The method may include: acquiring a current to-be-processed frame from a picture frame sequence of a video; detecting a region of interest (ROI) in the current to-be-processed frame, in response to determining that the current to-be-processed frame is a detection picture frame, to determine at least one ROI in the current to-be-processed frame; and updating a to-be-tracked ROI, based on the ROI in the current to-be-processed frame and a tracking result determined by a pre-order tracking picture frame; and tracking the current to-be-processed frame based on the existing to-be-tracked ROI, in response to determining that the current to-be-processed frame is a tracking picture frame, to determine at least one tracking result as the ROI of the current to-be-processed frame.

Method and apparatus for detecting region of interest in video, device and medium

Embodiments of the present disclosure relate to a method and apparatus for selecting a video clip, a server and a medium. The method may include: determining at least two video clips from a video; for each video clip, perform following excitement determination steps: inputting a feature sequence of a video frame in the video clip and title information of the video into a pre-established prediction model to obtain a relevance between the inputted video frame and a title of the video; and determining an excitement of the video clip, based on the relevance between the video frame in the video clip and the title; and determining a target video clip from the video clips, based on the excitement of each of the video clips.

Method and apparatus for selecting video clip, server and medium

The present application discloses a video-based human behavior recognition method, apparatus, device and storage medium, and relates to the technical field of human recognitions. The specific implementation scheme lies in: acquiring a human rectangle of each video frame of the video to be recognized, where each human rectangle includes a plurality of human key points, and each of the human key points has a key point feature; constructing a feature matrix according to the human rectangle of the each video frame; convolving the feature matrix with respect to a video frame quantity dimension to obtain a first convolution result and convolving the feature matrix with respect to a key point quantity dimension to obtain a second convolution result; inputting the first convolution result and the second convolution result into a preset classification model to obtain a human behavior category of the video to be recognized.

Video-based human behavior recognition method, apparatus, device and storage medium

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.

Method and apparatus for grounding a target video clip in a video

Embodiments of the present disclosure disclose a method and apparatus for recognizing a body movement. A specific embodiment of the method includes: sampling an input to-be-recognized video to obtain a sampled image frame sequence of the to-be-recognized video; performing key point detection on the sampled image frame sequence by using a trained body key point detection model, to obtain a body key point position heat map of each sampled image frame in the sampled image frame sequence, the body key point position heat map being used to represent a probability feature of a position of a preset body key point; and inputting body key point position heat maps of the sampled image frame sequence into a trained movement classification model to perform classification, to obtain a body movement recognition result corresponding to the to-be-recognized video.

Method and apparatus for recognizing body movement

A method for video frame interpolation, a related electronic device and a storage medium is disclosed. A video is obtained. An (i&#x2212;1)frame and an iframe of the video are obtained. Visual semantic feature maps and depth maps of the (i&#x2212;1)frame and the iframe are obtained. Frame interpolation information is obtained based on the visual semantic feature maps and the depth maps. An interpolated frame between the (i&#x2212;1)frame and the iframe is generated based on the frame interpolation information and the (i&#x2212;1)frame and is inserted between the (i&#x2212;1)frame and the iframe.

Method for video frame interpolation, related electronic device and storage medium

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.

Growing community of inventors

Beijing, China

Dongliang He