413 results about "Subtitle" patented technology

The invention discloses an intelligent television video resource searching method and system. The intelligent television video resource searching method comprises receiving a first searching key word input through a user; searching a subtitle file which is matched with the first searching key word in a prestored text subtitle file; obtaining video resource information which is corresponding to the subtitle file; sending the resource information to an intelligent television terminal and displaying. The intelligent television video resource searching method is convenient and flexible due to the fact that the user can search videos according to words in the videos.

The present invention provides a method, device and terminal for adding subtitles to video. Specifically, first generate a number of transparent subtitle pictures named after the time range. For example, T1 and T2 represent two time points, and T1<=T2. The generated picture T1-T2.png indicates that in the time range from T1 to T2, the video The subtitles in the picture T1-T2.png will be displayed; then the video to which the subtitles will be added is decoded; the time stamp of the decoded video frame is compared with the time range of the subtitle picture; then the time range includes the time stamp of the video frame The subtitle picture is synthesized with the video frame to obtain the video frame with subtitles; the video with subtitles can be obtained by encoding the video frame with subtitles. Because the technical solution proposed by the present invention is concise, fast, and consumes less resources, it can meet the requirement of quickly adding subtitles to videos on a mobile terminal.

The invention discloses a subtitle dramatizing method based on the closed outline of Bezier, which belongs to the technical field of subtitle editing and broadcasting of a television program manufacture and broadcasting agent in television and film industries. The method of the invention comprises the following steps: firstly, converting subtitle objects into vector outline information which consists of first power, second power or third power Bezier line sections and comprises N closed vector outlines; then, converting the first power and the third power Bezier line sections into second power Bezier line sections; next, deleting or cutting the closed annular paths contained in the self intersected closed outlines in the vector outline information; regulating and sorting the intersected closed outlines in the vector outline information so that the closed outlines are not intersected mutually; and finally, converting the intersected closed outlines in the vector outline information into polygons, and dramatizing the subtitles after adding the inner edges or the outer edges on the polygons. When being adopted, the method of the invention can improve the subtitle dramatizing efficiency, can enhance the subtitle dramatizing effect, and can meet the high-grade application requirement of the subtitle.

The embodiment of the invention discloses a subtitle output method and device. Audio data in a media file are acquired and the audio data are identified as characters. When an instruction of playing the media file is received, the media file is played, and the identified characters act as subtitles of the media file to be synchronously outputted with the audio data so as to provide the subtitles to the media file without subtitles and provide more information to users.

The embodiment of the invention provides a method and a device for displaying live broadcast subtitles, a server and a medium, and relates to the technical field of information processing. The methodaccording to the embodiment comprises the steps of receiving a live broadcast task instruction sent by a live broadcast management system, receiving and caching audio data and video frame data sent bythe live broadcast management system based on the live broadcast task instruction, performing voice recognition on the audio data; text data corresponding to the audio data is obtained; and accordingto the timestamp of the text data and the timestamp of the video frame data, superposing the text data to the video frame data with the same timestamp as the text data to obtain the video frame datacarrying the subtitle information, and outputting a media stream composed of the video frame data carrying the subtitle information and the audio data. By adopting the method, subtitles can be displayed for the live video.

The invention discloses a simultaneous subtitle translation method, a smart television and a storage medium. The method comprises the steps: receiving an operation instruction of a user for selectinga target language, collecting voice information in a playing resource, and transmitting the target language and the voice information to a cloud server; receiving target subtitles returned by the cloud server, wherein the cloud server is used for translating the voice information into the target subtitles corresponding to the target language; and matching the target caption with the time axis of the playing resource in real time, and synchronously displaying the target caption in the playing process. According to the invention, the voice information in the playing resources is collected; according to language subtitles required by a user, the voice information is sent to a cloud server to be synchronously translated into target subtitles corresponding to a target language selected by the user, and the target subtitles are synchronously displayed during playing, so that the user can easily understand content information expressed by audios and videos of different languages, and convenient watching or learning is realized.

Aspects described herein may provide systems, methods, and device for facilitating language learning using videos. Subtitles may be displayed in a first, target language or a second, native language during display of the video. On a pause event, both the target language subtitle and the native language subtitle may be displayed simultaneously to facilitate understanding. While paused, a user may select an option to be provided with additional contextual information indicating usage and context associated with one or more words of the target language subtitle. The user may navigate through previous and next subtitles with additional contextual information while the video is paused. Other aspects may allow users to create auto-continuous video loops of definable duration, and may allow users to generate video segments by searching an entire database of subtitle text, and may allow users create, save, share, and search video loops.

The invention provides a method and system for improving video question-answering precision based on a multi-modal fusion model, and the method comprises the steps: collecting video data and questionfeatures, and obtaining a video question-answering question; extracting visual features and subtitle features from the video data; performing fusion processing on the visual features and the subtitlefeatures to obtain fused visual features and fused subtitle features; inputting the fused visual features, the fused caption features and the problem features into a multi-modal fusion model for training to obtain a trained multi-modal fusion model; inputting the questions of the video questions and answers into the trained multi-modal fusion model to obtain answers to the questions; different target entity instances are focused for different questions according to the characteristics of the questions, so that the accuracy of selecting answers by the model is improved.

The invention relates to a video generation method and device, computer equipment and a storage medium. By adopting the method and the device, a user does not need to spend a long time for editing andediting, and does not need to make subtitles synchronized with a time axis, so that a large amount of video editing and editing time is saved for the user, and the video making efficiency is improved. The method comprises the steps of displaying a template editing page corresponding to a video shooting template selected by a user, and displaying a shooting page in response to a first shooting instruction triggered by the user on the template editing page, wherein a preset composition reference line is displayed on the shooting page; displaying preset subtitles on the shooting page according to a preset time node, and obtaining original data which is input by the user according to the preset composition reference line and is used for generating a video; and generating a video based on theoriginal data and the preset subtitles.

An apparatus comprising an estimation circuit, a rate control circuit, a queue circuit, and an encoder circuit. The estimation circuit may be configured to generate a size value in response to an input signal comprising (i) a plurality of frames and (ii) a plurality of embedded subtitle elements. The rate control circuit may be configured to (i) generate a control signal, (ii) pass through the plurality of frames, (iii) present a first one or more of subtitle elements for current processing in response to the size value, and (iv) present a second one or more of subtitle elements for subsequent processing. The queue circuit may be configured to (i) receive the second one or more subtitle elements, (ii) present the second one or more of subtitle elements for current processing when the control signal is in a first state and (iii) hold a second one or more subtitle elements for subsequent processing when the control signal is in a second state. The encoder circuit may be configured to generate an output signal in response to (i) the plurality of frames, (ii) the first one or more subtitle elements, and (iii) the second one or more subtitle elements.

One embodiment of the present disclosure sets forth a technique for generating translation suggestions. The technique includes receiving a sequence of source-language subtitle events associated with a content item, where each source-language subtitle event includes a different textual string representing a corresponding portion of the content item, generating a unit of translatable text based on a textual string included in at least one source-language subtitle event from the sequence, translating, via software executing on a machine, the unit of translatable text into target-language text, generating, based on the target-language text, at least one target-language subtitle event associated with a portion of the content item corresponding to the at least one source-language subtitle event, and generating, for display, a subtitle presentation template that includes the at least one target-language subtitle event.

A process receives, with a processor, audio corresponding to media content. Further, the process converts, with the processor, the audio to text. In addition, the process concatenates, with the processor, the text with one or more time codes. The process also parses, with the processor, the concatenated text into one or more text chunks according to one or more subtitle parameters. Further, the process automatically translates, with the processor, the parsed text from a first spoken language to a second spoken language. Moreover, the process determines, with the processor, if the language translation complies with the one or more subtitle parameters. Additionally, the process outputs, with the processor, the language translation to a display device for display of the one or more text chunks as one or more subtitles at one or more times corresponding to the one or more time codes.

The invention discloses a technology for realizing real-time subtitle overlay during a video call and applications of the technology. The technology comprises subtitle software, and comprises the following steps: S1, a voice recognition algorithm, namely, through a machine learning algorithm, capturing audio data in a video in real time, and converting the audio data into language data with practical meaning; S2, a character converting algorithm, namely, carrying out algorithm processing on the acquired voice data so that character information is obtained through converting in real time; S3, asubtitle display algorithm, namely, carrying out real-time character-by-character or word-by-word display on the character information; S4, an automatic sentence punctuating algorithm, namely, analyzing an audio file, so that the starting and pausing points of one sentence are acquired; and S5, a character and audio/video overlay method, namely, directly displaying characters to a video interfacein an overlay manner, so that video captions are formed, wherein the video interface does not assign the display positions of the character subtitles. Through the technology for realizing real-time subtitle overlay during a video call and the applications of the technology, after the complete sentence is acquired, all the displayed characters can be updated according to the meaning of the complete sentence.

The invention discloses a subtitle correction method, a subtitle display method, a subtitle correction device, a subtitle display device, equipment and medium. The subtitle correction method comprisesthe following steps: acquiring audio stream data and video picture data in video data; performing voice recognition on the audio stream data to obtain first subtitle information; performing text recognition on the video picture data; and correcting the first subtitle information according to the text recognition result to obtain second subtitle information. The subtitle display method comprises the following steps: acquiring video data and second subtitle information; and when the video data is played, displaying the second subtitle information. According to the invention, the subtitle information recognized by voice is corrected based on text recognition of the video picture content, the subtitle information related to the video picture content can be corrected, the consistency between the subtitles recognized by voice and the video content is improved, the accuracy of the subtitle content is improved, the watching experience of a user is improved, and the subtitle correction method,the subtitle display method, the subtitle correction device, the subtitle display device, the equipment and the medium can be widely applied to the technical field of the Internet.

The invention discloses a cross-modal image multi-style subtitle generation method and system. The method comprises the steps that an image of subtitles to be generated is acquired; the image of subtitles to be generated is input into a pre-trained multi-style subtitle generation model, and multi-style subtitles of the image are output; wherein the pre-trained multi-style caption generation modelis obtained after training based on an adversarial generative network; the training step comprises the steps of firstly training the image objective information expression capability of the multi-style subtitle generation model, and then training the stylized subtitle generation capability of the multi-style subtitle generation model.

The invention belongs to the field of video questions and answers, and particularly relates to a method for performing multi-mode video question answering by using frame-subtitle self-supervision. The method includes the following steps: extracting video frame features, question and answer features, subtitle features and subtitle suggestion features; obtaining frame features with attention and caption features with attention, and obtaining fusion features; calculating and obtaining a time attention score based on the fusion feature; calculating and obtaining the time boundary of the question by using the time attention score; calculating and obtaining answers to the questions by adopting the fusion features and the time attention scores; training a neural network by using the time boundary of the question and the answer of the question; and optimizing network parameters of the neural network, performing video question answering by using the optimal neural network, and delimiting a time boundary. The time boundary related to the problem is generated according to the self-designed time attention score instead of using time annotation with high annotation cost. In addition, more accurate answers are obtained by mining the relation between the subtitles and the corresponding video content.

The invention discloses a method for extracting conceptual words from video subtitles, which comprises the following steps of: carrying out word segmentation processing on a subtitle text, and deleting punctuation marks; stop words and part-of-speech tagging are carried out on the caption text after word segmentation; calculating co-occurrence characteristics of the target word and the adjacent word; calculating the semantic similarity between the target word and the adjacent word; performing concept word marking on a small number of subtitle texts subjected to word segmentation to serve as atraining set; and training a pre-established semi-supervised learning framework based on a conditional random field according to the training set to obtain a conceptual word prediction model, and obtaining a conceptual word prediction result corresponding to the subtitle text output by the conceptual word prediction model. Based on the method for extracting the conceptual words provided by the invention, the workload of manually labeling corpora is reduced, the accuracy of extracting the conceptual words in the MOOC video subtitle scene is improved, and the actual requirements are met.

The invention provides a personalized image and subtitle generating method based on a context sequence memory network. The personalized image and subtitle generating method based on the context sequence memory network mainly comprises the following steps: construction of a database, construction of the context sequence memory network, sequence generation based on states and network training. According to the process, an image database is constructed by using an application interface in a social medium and a crawler device at first, redundant information is filtered, labels and subtitles are predicted by an image memory vector, an context memory vector and a character output vector, high frequency words are found out from a keyword dictionary, and therefore, personalized new words with the highest matching degree for the user are generated. Synchronous prediction of the labels and the subtitles can be processed, a frame of the context memory network is provided to solve the character matching problem, and meanwhile, the prediction precision of generated corresponding images and subtitles is improved.

The invention relates to an evaluation method for the watching comfort level caused by rolling subtitles of different speed based on an EEG. The evaluation method comprises the steps that three-dimensional materials are made, and the rolling subtitles are enabled to roll to the other side of a screen from one side of the screen according to different angular speed; as for different angular speed of the rolling subtitles, a testee is enabled to perform subjective evaluation on the watching comfort level; the subjective experimental result of the testee is analyzed, i.e. the comfort level of the rolling subtitles under different angular speed is analyzed so that the range of the angular speed causing watching discomfort can be obtained; the rolling subtitle materials of different angular speed are selected for measuring the brain wave of the testee, and EEG signals are preprocessed; the frequency domain characteristics are extracted out of the preprocessed EEG signals; as for the subjective experimental result, the obtained data samples are marked as the comfort class and the discomfort class; and data dimension reduction is performed by using a Fisher ratio method, and a SVM classifier is established and trained.

The embodiment of the invention provides a video recording method, device and equipment and a readable storage medium, and relates to the technical field of computers. The method comprises steps of receiving a video recording trigger signal which is used for triggering a video recording operation; collecting a video image frame and voice data according to the video recording trigger signal; determining a timestamp range of a video image frame corresponding to the acquired voice data in the video recording operation; performing text recognition on the voice data to obtain subtitle content of the recorded video in a timestamp range; and generating a target video according to the video image frame, the voice data and the subtitle content. According to the method, the voice data is recognized in real time to obtain the corresponding subtitle content, and the subtitle content is displayed as the subtitle in the timestamp range corresponding to the voice data, so a problem of tedious subtitle generation process caused by manual input of the subtitle content is avoided, and subtitle generation efficiency is improved.

The invention discloses a method for annotating subtitles in a news video. The method comprises the following steps of: gathering the news video; decoding the news video to obtain single-frame video images; extracting candidate subtitle areas from the video images to locate news subtitle areas; matching the news subtitle areas with template images in a news template base; if the news subtitle areas are matched with the template images, annotating the news subtitle areas according to the annotation formats of the template images; and if the news subtitle areas are not matched with the template images, annotating the news subtitle areas. By adopting the technical scheme disclosed by the invention, the accuracy of annotating the subtitles in the video can be increased, the artificial check time is reduced, and a news video retrieval effect is enhanced.