Abstract: Provided is a human posture detection method including: acquiring a plurality of frames of image data; acquiring a plurality of human posture reference maps output by a human posture detection model responsive to inputting a current frame of image data to the human posture detection model with reference to human posture confidence maps of a previous frame of image data, wherein different human posture reference maps correspond different human-posture key points; identifying a human-posture key point in each of the human posture reference maps; and generating human posture confidence maps of the current frame of image data based on credibility of the human-posture key points, wherein the human posture confidence maps of the current frame of image data is configured to participate in generation of human posture confidence maps of a next frame of image data.

Abstract: A video quality evaluation method comprises acquiring an image sequence and audio information by decoding a to-be-evaluated video, wherein the to-be-evaluated video is non-offending video; extracting an action feature vector and a face feature vector from the image sequence, and extracting an audio feature vector from the audio information; constructing a video feature vector according to at least one of the action feature vector, the face feature vector and the audio feature vector; and determining a quality score of the to-be-evaluated video according to the video feature vector.

Abstract: A video quality evaluation method comprises acquiring an image sequence and audio information by decoding a to-be-evaluated video, wherein the to-be-evaluated video is non-offending video; extracting an action feature vector and a face feature vector from the image sequence, and extracting an audio feature vector from the audio information; constructing a video feature vector according to at least one of the action feature vector, the face feature vector and the audio feature vector; and determining a quality score of the to-be-evaluated video according to the video feature vector.

Abstract: A method for recognizing actions in a video is provided. The method comprises, determining, based on key points of skeleton of at least one video frame in a video to be recognized, shallow features of the at least one video frame; acquiring image features of the at least one video frame; acquiring action features of the at least one video frame based on the shallow features and the image features; acquiring an action recognition result of the at least one video frame by inputting the action features of the at least one video frame into an action recognition model, wherein the action recognition result includes states and state probabilities of actions in the at least one video frame; and determining an execution state of a target action in the at least one video frame based on the action recognition result of the at least one video frame.

Abstract: A method for processing images, including: acquiring an original image and auxiliary information of the original image; acquiring an object feature map by inputting the original image into a main path of a first visual task processing model, and acquiring an auxiliary feature map by inputting the auxiliary information into a branch path of the first visual task processing model; and acquiring a response map of the original image by fusing the object feature map and the auxiliary feature map and inputting fused object feature map and auxiliary feature map into the main path of the first visual task processing model.

Abstract: Provided is a human posture detection method including: acquiring a plurality of frames of image data; acquiring a plurality of human posture reference maps output by a human posture detection model responsive to inputting a current frame of image data to the human posture detection model with reference to human posture confidence maps of a previous frame of image data, wherein different human posture reference maps correspond different human-posture key points; identifying a human-posture key point in each of the human posture reference maps; and generating human posture confidence maps of the current frame of image data based on credibility of the human-posture key points, wherein the human posture confidence maps of the current frame of image data is configured to participate in generation of human posture confidence maps of a next frame of image data.