EP-4742680-A1 - VIDEO DETECTION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM

EP4742680A1EP 4742680 A1EP4742680 A1EP 4742680A1EP-4742680-A1

Abstract

Embodiments of the present disclosure provide a method and apparatus for video detection, an electronic device and a storage medium. With the method, a first video is obtained; video detection is performed based on the first video to obtain at least one second video and reference information corresponding to the second video, the second video containing at least one target video clip, the target video clip being associated with the first video, the reference information characterizing a playback position of the target video clip in the second video; a first video clip in the first video and the target video clip in the corresponding second video are synchronously played based on the reference information within a target interface.

Inventors

HE, SHENGFAN
QIU, Shimei

Assignees

Lemon Inc.

Dates

Publication Date: 20260513
Application Date: 20240704

Claims (14)

A method for video detection, comprising: obtaining a first video; performing, based on the first video, video detection to obtain at least one second video and reference information corresponding to the second video, wherein the second video contains at least one target video clip, the target video clip is associated with the first video, and the reference information characterizes a playback position of the target video clip in the second video; and synchronously playing, within a target interface and based on the reference information, a first video clip in the first video and the target video clip in the corresponding second video.
The method according to claim 1, wherein at least one of a first playback control corresponding to the first video or a second playback control corresponding to the second video is arranged within the target interface, wherein the first playback control is used for, in response to a first triggering operation, jump-playing target content in the first video clip; and the second playback control is used for, in response to the first triggering operation, playing the target content in the target video clip, the first triggering operation being an operation with respect to the first playback control or the second playback control.
The method according to claim 1, wherein the target video clip is associated with the first video, comprising: the target video clip having a high similarity with the first video clip in the first video.
The method according to claim 2, wherein synchronously playing, based on the reference information, the first video clip in the first video and the target video clip in the corresponding second video comprises: displaying, within the second playback control of the target interface and based on the reference information, a playback interval identification of the target video clip in the second video, the playback interval identification characterizing a start position and an ending position of the target video clip in the second video; in response to a first jump operation with respect to the playback interval identification, obtaining a corresponding first playback position; and synchronously playing, within the target interface, the target video clip with the first playback position as a starting point and the first video clip with the second playback position as a starting point, wherein content of an image frame corresponding to the second playback position is the same as content of an image frame corresponding to the first playback position.
The method according to claim 4, wherein the first playback control comprises a movable first control element, and the second playback control comprises a movable second control element; wherein in response to the first jump operation with respect to the playback interval identification, obtaining a corresponding first playback position comprises: in response to a first jump operation with respect to the playback interval identification, moving the second control element to a first element position corresponding to the first jump operation; and obtaining, based on the first element position, a corresponding first playback position; and the method further comprising: obtaining the second playback position corresponding to the first playback position; and moving the first control element to a second element position corresponding to the second playback position.
The method according to claim 4, further comprising: in response to a second jump operation, obtaining a corresponding third playback position, the third playback position being after the ending position corresponding to the target video clip; and synchronously playing, within the target interface, the second video with the third playback position as a starting point and the first video with a fourth playback position as a starting point, wherein a distance from the fourth playback position to the ending position of the first video clip is equal to a distance from the first playback position to the ending position of the target video clip.
The method according to claim 1, wherein performing, based on the first video, video detection to obtain at least one second video and reference information corresponding to the second vide comprises: obtaining a target image frame in the first video; detecting, based on the target image frame, at least one to-be-detected video to obtain at least one second video, the second video at least containing a matching image frame corresponding to the target image frame, an image similarity between the matching image frame and the target image frame being greater than a first threshold; and obtaining, based on a playback timestamp of the matching image frame, the reference information corresponding to the second video.
The method according to claim 7, wherein obtaining the target image frame in the first video comprises: obtaining a hit count of at least one key frame in the first video, the hit count being a count that the key frame has been detected as having a corresponding matching image frame; and determining a key frame with the hit count greater than a first number as the target image frame.
The method according to claim 7, wherein the target image frame comprises at least two consecutive key frames in the first video; wherein detecting, based on the target image frame, the at least one to-be-detected video to obtain at least one second video comprises: obtaining, based on a time interval between the at least two consecutive key frames, a corresponding number of second image frames in the to-be-detected video; and obtaining an image similarity between the key frames and the corresponding second image frames; in response to the number of second image frames with the image similarity greater than the first threshold being greater than a second number, determining the to-be-detected video corresponding to the second image frame as the second video.
The method according to claim 1, further comprising: obtaining a variable-speed coefficient corresponding to the target video clip, the variable-speed coefficient characterizing a video content playback rate of the target video clip relative to the first video clip; and obtaining, according to the variable-speed coefficient, a target playback speed of the first video clip; and wherein synchronously playing, within a target interface, a first video clip in the first video and the target video clip in the corresponding second video comprises: playing, based on the target playback speed and within the target interface, the first video clip in the first video.
A video detection apparatus comprising: an obtaining module for obtaining a first video; a processing module for performing, based on the first video, video detection to obtain at least one second video and reference information corresponding to the second video, wherein the second video contains at least one target video clip, the target video clip is associated with the first video, and the reference information characterizes a playback position of the target video clip in the second video; and an interaction module for synchronously playing, within a target interface and based on the reference information, a first video clip in the first video and the target video clip in the corresponding second video.
An electronic device comprising: a processor, and a memory communicatively coupled to the processor; the memory stores computer-executed instructions; the processor executes the memory-stored computer-executed instructions to implement the video detection method according to any of claims 1 to 10.
A computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, implement the video detection method as claimed in any one of claims 1 to 10.
A computer program product, comprising a computer program which, when executed by a processor, carries out the video detection method as claimed in any of claims 1 to 10.

Description

This application claims priority to Chinese Application No. 202310828406.8 filed July 6, 2023, the disclosure of which is incorporated herein by reference in its entirety. FIELD Embodiments of the present disclosure relate to the Internet technical field, and more specifically, to a method and apparatus for video detection, electronic device and storage medium. BACKGROUND With the emerging of user-generated content, a large number of self-produced videos have been uploaded by users on various Internet platforms. On the one hand, platform users can get various interesting content, thereby improving user experience. On the other hand, however, self-produced videos might contain abnormal content materials, leading to security issues. In the prior art, regarding self-produced videos uploaded by users, video platforms usually compare and detect these videos by manually comparing them frame by frame, thereby determining whether these self-produced videos contain abnormal content materials. However, the solution for detecting self-produced videos in the prior art requires manual video synchronization and comparison, giving rise to the problems of complicated interaction process and low detection efficiency. SUMMARY The embodiments of the present disclosure provide a method and apparatus for video detection, an electronic device and a storage medium, so as to overcome the problems of complicated check interaction process and low detection efficiency. In a first aspect, an embodiment of the present disclosure provides a video detection method, including: obtaining a first video; performing, based on the first video, video detection to obtain at least one second video and reference information corresponding to the second video, wherein the second video contains at least one target video clip, the target video clip is associated with the first video, and the reference information characterizes a playback position of the target video clip in the second video; and synchronously playing, within a target interface and based on the reference information, a first video clip in the first video and the target video clip in the corresponding second video. In a second aspect, an embodiment of the present disclosure provides an apparatus for video detection, including: an obtaining module configured for obtaining a first video; a processing module for performing, based on the first video, video detection to obtain at least one second video and reference information corresponding to the second video, wherein the second video contains at least one target video clip, the target video clip is associated with the first video, and the reference information characterizes a playback position of the target video clip in the second video; and an interaction module configured for synchronously playing, within a target interface and based on the reference information, a first video clip in the first video and the target video clip in the corresponding second video. In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor, and a memory communicatively connected with the processor; the memory storing computer executable instructions; the processor executing the computer executable instructions stored in the memory so as to perform the method for video detection according to the first aspect and various possible designs of the first aspect. In a fourth aspect, an embodiment of the present disclosure provides a computer readable storage medium in which computer executable instructions are stored, the computer executable instructions, when executed by a processor, performing the method for video detection according to the first aspect and various possible designs of the first aspect. In a fifth aspect, an embodiment of the present disclosure provides a computer program product, comprising a computer program which, when executed by a processor, performs the method for video detection according to the first aspect and various possible designs of the first aspect. With the video detection method and apparatus, electronic device and storage medium provided by the embodiments of the present disclosure, a first video is obtained; video detection is performed based on the first video to obtain at least one second video and reference information corresponding to the second video, wherein the second video contains at least one target video clip, the target video clip is associated with the first video, and the reference information characterizes a playback position of the target video clip in the second video; a first video clip in the first video and the target video clip in the corresponding second video are synchronously played based on the reference information within a target interface. By performing detection based on the first video, a second video containing a similar clip and reference information characterizing a playback position of the similar clip are obtained, and then based on the ref