Tencent Technology (shenzhen) Company Limited

Tfi Digital Media Limited

Tencent Technology Company Limited

Xuyuan Xu

Tao Wu

Guoping Gong

Yang Fang

Wei Shan Dong

Hon Wah Wong

Yiu Fai Yuen

Hok Kwan Cheung

Yuming Li

Hon Tung Luk

Chang Zhou

Yurong Yang

Kin Wai Lau

Yexin Wang

Lai Man Po

Ye Su

Mengyang Liu

Peicheng Zhang

A deep learning-based video editing method can allow for automated editing of a video, reducing or eliminating user input, saving time and labor investments, and thereby improving video editing efficiency. Attribute recognition is performed on an object in a target video using a deep learning model. A target object is selected that satisfies an editing requirement of the target video. A plurality of groups of pictures associated with the target object from the target video are obtained using editing. An edited video corresponding to the target video is generated using the plurality of groups of pictures.

Deep learning-based video editing method, related device, and storage medium

A watermark detection method includes identifying, among plural stored videos, a second video having a second video feature matching a first video feature of a first video, the second video comprising watermark information. The method further includes comparing the first video and the second video to obtain a video conversion parameter, the video conversion parameter indicating a difference between the first video and the second video. The method also includes converting the first video based on the video conversion parameter to obtain a third video, and performing watermark detection on the third video to obtain watermark information in the third video. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

Restoring a video for improved watermark detection

This application discloses a multimedia resource matching method performed at a computing device. The method includes: searching a first media resource set among a multimedia resource set, first target image frames of all media resources in the first media resource set meeting a target condition, and features of the first target image frames matching features in image frames of a to-be-matched multimedia resource according to a first matching condition; determining, among the first target image frames, second target image frames whose features match the features in the image frames of the to-be-matched multimedia resource according to a second matching condition; and obtaining matching information of the second target image frames and an identifier of a target media resource among the multimedia resource set, the matching information being used for indicating a total duration and a playback moment of the second target frame image in the target media resource.

Multimedia resource matching method and apparatus, storage medium, and electronic apparatus

A multimedia information processing method includes: parsing multimedia information to separate an audio from the multimedia information; converting the audio to obtain a mel spectrogram corresponding to the audio; determining, according to the mel spectrogram corresponding to the audio, an audio feature vector corresponding to the audio; and determining, based on an audio feature vector corresponding to a source audio in source multimedia information and an audio feature vector corresponding to a target audio in target multimedia information, a similarity between the target multimedia information and the source multimedia information.

Method and apparatus for detecting similarity between multimedia information, electronic device, and storage medium

Aspects of the disclosure provide a method and an apparatus for training a feature extraction model, a computer device, and a computer-readable storage medium that belong to the field of video processing technologies. The method can include detecting a plurality of images in one or more sample videos and obtaining at least two images including the same object. The method can further include determining the at least two images including the same object as sample images, and training according to the determined sample images to obtain the feature extraction model, where the feature extraction model is used for extracting a video feature of the video.

Method and apparatus for training feature extraction model, computer device, and computer-readable storage medium

Embodiments of this application disclose a video detection method and a server. The method includes: obtaining first video data to be detected; decoding the first video data, to obtain audio data of the first video data; analyzing and identifying the audio data, to obtain audio fingerprint data corresponding to the audio data; querying an audio fingerprint library; obtaining a video label and a time parameter corresponding to the audio data when the audio fingerprint library comprises the audio fingerprint data; querying a video copyright library, to obtain a first picture that is corresponding to the video label and that satisfies the time parameter, and extracting a second picture that is in the first video data and that satisfies the time parameter; separately extracting a first feature parameter of the first picture and a second feature parameter of the second picture; and comparing the first feature parameter with the second feature parameter, and determining, based on a comparison result, whether the first video data is consistent with a video in the video copyright library.

Video detection method, server and storage medium

The present disclosure relates to a method for image patch selection for training a neural network for image quality assessment. The method includes receiving an input image and extracting one or more image patches from the input image. The moment of the extracted image patches is measured. There is a decision to accept or decline the extracted image patches according to the measured moment. Additional image patches are extracted until a minimum number, N, of extracted image patches are accepted. Alternatively, selection criteria are adjusted until the minimum number of extracted image patches are accepted. The selected image patches are input into a neural network with a corresponding image quality value of the input image, and the neural network is trained with the image patches and image quality value. Also provided is a method for image quality assessment using a neural network trained as set forth above.

Patch selection for neural network based no-reference image quality assessment

Growing community of inventors

Shenzhen, China

Xuyuan Xu