13 results about "Video eeg" patented technology

This invention discloses a method for studying visual attention mechanisms based on EEG microstates, comprising: collecting EEG signals from subjects while watching videos and preprocessing them; extracting saliency maps from the videos, and extracting statistical features from the perspectives of spatial saliency information in the local temporal domain and spatiotemporal saliency information changes in the global time series, respectively, to obtain sIQR features and tsIQR features; converting the preprocessed EEG signals into EEG topology map sequences and performing spatial clustering to extract EEG microstate templates, determining the number of templates and selecting the final microstate templates, and then backfitting them to the EEG signals to obtain microstate sequences; extracting microstate features and depth features from the microstate sequences, examining the statistical differences between microstate features and sIQR and tsIQR features, constructing decoding models based on microstate features or depth features, and using the decoding models to decode segments and videos respectively to obtain segment labels and video labels.

The invention relates to a video restoration method and device based on bullet screen feedback, equipment and a medium, and the method comprises the steps: collecting bullet screen data in a video playing process, and recognizing feedback data used for feeding back a video quality problem from the bullet screen data, the feedback data comprising a bullet screen text and bullet screen time; determining a problem type and a problem severity degree of a video quality problem according to the bullet screen text, and determining a problem region of the video quality problem according to the bullet screen text and the bullet screen time; and determining a repair strategy according to the question type and the question severity, and performing video repair on the question region according to the repair strategy. Through a bullet screen semantic recognition mechanism, subjective feedback information of a user on image quality in a video watching process is converted into quantifiable quality problem description, information mapping from subjective perception to objective restoration is realized, and the problem that faults exist between subjective quality feedback of the user and an objective video restoration technology during video restoration is solved.

The present invention relates to a method for screening mobile terminal visual attention abnormalities in children based on multimodal data learning. A calibration video and a testing video are set up, and a head-face video of children while watching the calibration video and the testing video on smartphones is recorded, respectively. An eye-tracking estimation model is constructed to predict the fixation point location from the head-face video corresponding to the testing video frame by frame and to extract the eye-tracking features. Facial expression features and head posture features are extracted. A Long Short-Term Memory (LSTM) network is used to fuse different modal features and realize the mapping from multimodal features to category labels. In the testing stage, the head-face video of children to be classified while watching the videos on smartphones is recorded, and the features are extracted and input into the post-training model to determine whether they are abnormal.

The invention relates to a language learning system, which comprises a learning system, a video player and a foreign language video material, and is characterized in that the output end of the learning system is electrically connected with the video player, and the foreign language video material is in data connection with the learning system and the video player through a data memory. By adopting the translation algorithm module and the subtitle display module, an English learning program is highly simplified, English learning becomes closer to a native language learning process, information of a foreign language video material is decomposed, extracted, translated and combined, a learner can comprehensively and accurately learn the foreign language video material, and meanwhile, the learning efficiency is improved. The translated subtitle information is transmitted to the video player in real time to be displayed, so that a learner can view the translated subtitle information while watching the video, and the learning efficiency and effect are improved.

The invention discloses an electroencephalogram signal enhanced intelligent video abstraction method and system, relates to the technical field of video content understanding and electroencephalogram emotion analysis, and aims to solve the technical problems that in the prior art, video abstraction cannot reflect subjective emotion experience of viewers, electroencephalogram and video time axes are difficult to align, and heterogeneous data are difficult to fuse. Acquiring an electroencephalogram signal of a viewer in a video watching process, synchronizing the electroencephalogram signal with a video clip, and extracting and generating a structured video abstract based on multi-modal content; frequency domain features, time domain features, time frequency features and spatial correlation features are obtained according to the electroencephalogram signals, and electroencephalogram feature visual representation is generated; and fusing the video content abstract, the video key event timestamp and the electroencephalogram feature visual representation, deducing the emotional state and aligning the emotional state with the video event, and outputting a personalized video abstract reflecting the real emotional experience of a viewer. The method can be used for application scenes such as intelligent video abstraction, video platform recommendation, immersive content understanding and emotion calculation.

The invention relates to a digital human interaction method, device and system based on a video stream and electronic equipment. The method comprises the following steps: performing visual feature analysis processing on continuous video frames of a video stream, and determining a target spatial position of a digital human embedded in the video stream; performing time domain feature analysis and / or scene switching detection on the continuous video frames, and determining a target time point of the digital human embedded in the video stream; generating a to-be-embedded digital human based on the action detection result and the scene classification result of the continuous video frames, and embedding the to-be-embedded digital human into the video stream based on the target spatial position and the target time point; acquiring a video frame associated with the user behavior data from the video stream; and based on the user behavior data and the video frame associated with the user behavior data, generating corresponding digital human interaction content and transmitting the digital human interaction content to the digital human embedded in the video stream, and executing an interaction operation by the digital human. According to the invention, real-time interaction between the digital person and the audience can be realized, so that the audience can instantly interact with the digital person while watching the video.

The application discloses a content generation method, device, storage medium and program product. First, in response to a video playing instruction of target video content, a historical viewing breakpoint moment of the target video content is determined, and viewed video content before the historical viewing breakpoint moment in the target video content is determined. Then, semantic information including a plot script and / or a key frame of the viewed video content is extracted. Finally, a plot abstract of the viewed video content is generated according to the semantic information. Thus, the plot abstract of the viewed video content is generated by using the semantic information of the viewed video content before the historical viewing breakpoint moment in the target video content, so that the user can quickly review the historical video content that has been played and viewed according to the plot abstract at a current viewing starting moment, thereby making it easier for the user to connect the plot of a long video, improving the possibility of breakpoint continuation playing of the long video, and finally improving the completion rate of the long video.

The application discloses a prediction method and device, a training method and device, and an electronic device, and belongs to the field of artificial intelligence. The prediction method comprises the following steps: generating input features based on video data features of a target video and behavior data features of a user watching the video within a preset time period; inputting the input features into an embedding layer to convert the input features into embedding vectors; inputting the embedding vectors into an intermediate layer to obtain N fusion feature vectors based on the embedding vectors; inputting the N fusion feature vectors into a tower layer to obtain a first prediction value of a first play parameter and a second prediction value of the first play parameter based on a first fusion feature vector, and to obtain a third prediction value of a second play parameter based on a second fusion feature vector; and inputting the first prediction value, the second prediction value and the third prediction value into an output layer to determine a prediction value of the first play parameter based on the first prediction value via the output layer, and to determine a prediction value of the second play parameter based on the second prediction value and the third prediction value.

A video content analysis system according to a scene reaction of video content according to one embodiment of the present invention comprises: a video processing unit which divides video content into a plurality of scenes and classifies each of the divided scenes for each preset reaction; an information collection unit for collecting biometric data of a viewer reacting while the video content is reproduced to the viewer; a reaction analysis unit for analyzing a reaction for each scene from the biometric data collected by the information collection unit; and a scene analysis unit for comparing and analyzing the reaction classified by the video processing unit and the reaction with respect to the biometric data analyzed by the reaction analysis unit for each scene.

The embodiment of the invention discloses a video recommendation method and device, electronic equipment and a medium, and relates to the technical field of computers, and one specific implementation mode of the method comprises the steps of obtaining user video watching data in a first preset time period; based on user watching data of a first video in the user video watching data, determining whether the video type of the first video is a hot video; when the video type of the first video is a hot video, sampling and pairing processing is carried out on a watching user set in the user watching data to obtain a watching user pair, and a similarity score between the first video and the second video is determined based on a watching video set of the watching user pair; and based on the similarity score, obtaining candidate recommended videos from a video library, and generating video recommendation information by using the candidate recommended videos. The efficient landing of the recall algorithm under the scene of millions of users and millions of video candidate sets is realized, and the real-time performance and reliability of video recommendation are improved.

[Problem] To provide: an intra-video space calibration system that performs calibration processing relating to a mutual positional relationship and video timing so that deviations in position and time do not occur between users viewing video relating to XR via viewing devices; a user assistance system in which AI provides related information on the basis of acquired information; and a display function in which AI superimposes and arranges content related to real-world objects. [Solution] The present invention comprises: a viewing device that is worn by a user and enables the user to view the video; and a current information acquisition device that recognizes current defining information of each user wearing the viewing device. The viewing device is configured to include: a display means that displays video; a calibration means that calibrates position information and time information in a space constituted by video of each user; and an information holding means that holds each of the calibrated user position information in the space constituted by video, the position information and the time information at which content is displayed, video, and the like.

The present invention relates to Smart E-Learning system using adaptive video lecture delivery based on attentiveness of the viewer. The attentiveness of the viewer is increased, who is watching a video lecture (204) in an E-learning scenario where viewer's attentiveness score (205) is captured based on facial expressions, cognitive responses etc. The video content (209) are changed dynamically to increase the attentiveness of the viewer in real time without viewer's knowledge. To change content segments, next segment predictor (206) has prior knowledge of the main video with its break points and supporting videos (207). It (206) uses viewer's attentiveness (210) and selects the next segment (209) which is played for the viewer, before proceeding with the main content. Incremental Learning with AI / MML techniques are used for next segment prediction. The feedback of attentiveness score after content segment change is used by the Next Segment Predictor (206) for further learning process.