Video segment recognization

A computing device, comprising a memory, a processor, and computer instructions stored in the memory and capable of running on the processor, wherein when executing the computer instructions, the processor perform operations comprising:

• dividing a received initial video into at least one video segment;
• obtaining, based on a feature extraction model, a first modal feature, a second modal feature, and a third modal feature that correspond to each video segment in the at least one video segment, wherein the first modal feature is an audio feature, the second modal feature is an image feature, and the third modal feature is a structured feature, and wherein the obtaining, based on a feature extraction model, a first modal feature, a second modal feature, and a third modal feature that correspond to each video segment in the at least one video segment comprises:
• extracting image information of each video segment in the at least one video segment, wherein the image information comprises a video picture and a key area picture;
• inputting the video picture into a first image feature extraction model to obtain a video picture feature corresponding to each video segment;
• inputting the key area picture into a second image feature extraction model to obtain a key area picture feature corresponding to each video segment;
• and
• fusing the video picture feature and the key area picture feature that correspond to each video segment, to obtain the image feature corresponding to each video segment;
• and
• inputting, into a recognition model, the first modal feature, the second modal feature, and the third modal feature that correspond to each video segment, to obtain a video score corresponding to each video segment, and determining a target video segment in the initial video based on the video score.

A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, which when executed by a processor, cause the processor to perform operations comprising:

• dividing a received initial video into at least one video segment;
• obtaining, based on a feature extraction model, a first modal feature, a second modal feature, and a third modal feature that correspond to each video segment in the at least one video segment, wherein the first modal feature is an audio feature, the second modal feature is an image feature, and the third modal feature is a structured feature, and wherein the obtaining, based on a feature extraction model, a first modal feature, a second modal feature, and a third modal feature that correspond to each video segment in the at least one video segment comprises:
• extracting image information of each video segment in the at least one video segment, wherein the image information comprises a video picture and a key area picture;
• inputting the video picture into a first image feature extraction model to obtain a video picture feature corresponding to each video segment;
• inputting the key area picture into a second image feature extraction model to obtain a key area picture feature corresponding to each video segment;
• and
• fusing the video picture feature and the key area picture feature that correspond to each video segment, to obtain the image feature corresponding to each video segment;
• and
• inputting, into a recognition model, the first modal feature, the second modal feature, and the third modal feature that correspond to each video segment, to obtain a video score corresponding to each video segment, and determining a target video segment in the initial video based on the video score.