299 results about "Target expression" patented technology

The embodiment of the invention discloses a model training method for synthesizing speaking expressions. Expression characteristics, acoustic characteristics and text characteristics are obtained according to videos containing face action expressions of speakers and corresponding voices. Because the acoustic feature and the text feature are obtained according to the same video, the time interval and the duration of the pronunciation element identified by the text feature are determined according to the acoustic feature. A first corresponding relation is determined according to the time interval and duration of the pronunciation element identified by the text feature and the expression feature, and an expression model is trained according to the first corresponding relation. The expressionmodel can determine different sub-expression characteristics for the same pronunciation element with different durations in the text characteristics; the change patterns of the speaking expressions are added, the speaking expressions generated according to the target expression characteristics is determined by the expression model. The speaking expressions have different change patterns for the same pronunciation element, and therefore the situation that the speaking expressions are excessively unnatural in change is improved to a certain degree.

Novel expression vectors and constructs encoding a chloroplast transit peptide (CTP) operably linked to a monomeric anthranilate synthase are provided. Additionally, novel polynucleotide sequences encoding monomeric anthranilate synthases are provided. Also provided are methods for increasing the levels of free tryptophan in transgenic plants containing the expression vectors and constructs.

The invention relates to a ward visit service robot system and a target searching method thereof. In the method, a way for searching a target by combining the Bayesian theory with multi-mode target expression and priori knowledge is put forward, and a mechanism for actively searching a target in the complex environment of a ward by a method for combining active vision, characteristic extraction and characteristic verification is provided. By using body vision of a robot and RFID (Radio Frequency Identification Device) information, active robot ward visit is realized. A robot positioning system is obtained by a StarGazer system through Kalman filtering; a robot control system expresses an expression target through multiple modes of a target by using the Bayesian theory and controls the robot in combination with the priori knowledge; a target position is obtained while the pose of the robot is controlled, so that the target is positioned by a method for using active vision and combination characteristic; and a camera is controlled by a partition logic method, and a shot picture is sent to a server side for displaying and storing.

Described herein are methods to enhance the production of more highly fermentable carbohydrates in plants, especially forage grasses. The invention provides for transgenic plants transformed with expression vectors containing a DNA sequence encoding ferulic acid esterase I from Aspergillus, preferably A. niger. The expression vectors may optionally comprise a DNA sequence encoding xylanase from Trichoderma, preferably T. reesei. Expression of the enzyme(s) is targeted to specific cellular compartments, in specific tissues and under specific environmental conditions. Uses of this invention include, but are not limited to, forage with improved digestibility for livestock, and enhanced biomass conversion.

The invention relates to an expression image recommendation method and device based on voice emotion recognition, an electronic device and a storage medium. The method comprises the following steps ofacquiring a plurality of latest voice messages in a current interaction window of the instant messaging software, and extracting audio feature vectors of the voice messages; matching the audio feature vector of the voice information with a plurality of emotion feature models, wherein the plurality of emotion feature models respectively correspond to one of a plurality of emotion classifications;taking the emotion classification corresponding to the matched emotion feature model as the emotion classification of the voice information; and determining one or more target expression images basedon the emotion classification of the voice information, and recommending the target expression images to the current user, so that the efficiency of selecting the expression image is improved.

The invention relates to the field of man-machine emotion interaction, intelligent robots and the like, and aims to provide a corresponding solution way for researching generation and control problemsof natural facial expressions of a humanoid robot by taking a three-dimensional face model oriented to a virtual or entity humanoid robot as a carrier. Therefore, the conditional generative adversarial network three-dimensional facial expression motion unit synthesis method comprises the following steps: (1) establishing effective mapping between facial motion unit labels with different intensities and different combinations and facial expression parameter distribution; (2) carrying out game optimization on the generation result of the expression motion parameter generation model; And (3) applying the generated target expression parameters to the three-dimensional face model facing the humanoid robot to realize generation and control of the three-dimensional face complex expression of thehumanoid robot. The method is mainly applied to intelligent robot design and manufacturing occasions.

Computer-implemented methods and computer program products for automatically transferring expressions between rigs with consistent joint structure, and for automatically transferring skin weights between different skin meshes based on joint positioning. A method is provided for transferring an expression between a source rig and a target rig, where each rig characterizes an animated character, and each rig, in turn, is characterized by a set of joints and a skin mesh having a plurality of vertices, with each vertex characterized by a matrix of weights relating a response of the vertex to movement of associated joints. A set of offsets is calculated of joint positions of a goal expression of the source rig relative to a neutral expression of the source rig. A scaling transformation is then applied to the set of offsets to produce a scaled set of offsets, which are added, in turn, to a neutral expression of the target rig. Methods are also provided for transferring a set of skin weights between a source rig and a target rig.

The invention discloses a method and a device for generating an expression animation, belonging to the Internet field. The method disclosed by the invention comprises steps of collecting a deformation animation of a face image, performing characteristic point extraction on the face image included in the deformation animation to obtain a human face characteristic animation, and generating an expression animation based on the human face characteristic point animation and a target expression template, wherein the target expression template is a 2D or 3D expression model having a plurality of control points. The invention obtains the human face characteristic point animation through collecting human face image animation and extracting the human face characteristic points, determines the target expression template to generate the expression animation, reduces the difficulty and cost for generating the expression animation, and enables the user can generate some personalized expression animation on their own.

The invention provides a shooting method and a mobile terminal. The method comprises the following steps of: acquiring a facial image of a target object through a camera; obtaining facial feature data in the facial image; judging whether the facial feature data is matched with target expression feature data or not; and executing shooting operation if the facial feature data is matched with the target expression feature data. According to the embodiment of the invention, the facial feature data is obtained; when the facial feature data is matched with the target expression feature data, a shooting shutter button is started automatically and conveniently, so that shooting operation is carried out; the shooting method provided by the invention is more convenient to perform shooting operation; and furthermore, the shooting method can also be used for shooting a photograph having relatively ideal expression.

The present disclosure provides pharmaceutical compositions comprising nucleic acids capable of targeting IGF-1R expression in M2 cells. The present disclosure also provides methods for the selective reduction of M2 cells by targeting expression of IGF-1R in these cells. The present disclosure further provides methods for treating cancer and enhancing therapeutic by targeting expression of IGF-1R in M2 cells in patients. The pharmaceutical composition of the present invention is effective when administered systemically to subjects in need thereof. The ease of administration of the pharmaceutical composition facilitates treatment and enhances patient compliance.

The embodiment of the invention discloses an expression image generating method, device and a storage medium. The method comprises the following steps: a selected user image is acquired, and a face image in the user image is acquired; three-dimensional reconstruction processing is carried out on the face image to acquire a three-dimensional face model corresponding to the face image; expression parameters are acquired in an expression parameter set, and the expression parameters and the three-dimensional face model are subjected to synthesis processing to generate a first expression image corresponding to the face image; and the first expression image is subjected to image filling processing to acquire a target expression image corresponding to the user image, the target expression image is added to an expression image sequence corresponding to the user image, and the expression image sequence is outputted. Thus, the expression image which meets requirements of the user can be acquired, the operation process is simple and quick, and convenience for expression image acquisition is thus enhanced.

The invention discloses a chat picture control method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining chat information of a current display interface, the chat information comprising one or more of text information, picture information or voice information; identifying a first keyword of the chat information, and matching reply information and a target expression picture mapped by the reply information from a preset database; and when it is detected that an input cursor exists in the chat input box, popping up a target expression picture for auser to select so as to reply the chat information. In the whole process, the picture does not need to be manually searched in the expression library, and the picture capable of being used as the reply is automatically popped up according to content recognition, so that the message reply picture searching time is saved. Chat reply becomes more convenient and faster.

Embodiments of the invention provide a translation method and device and a terminal. The method comprises the following steps of: receiving a content page of a third-party application program; when aselection signal corresponding to a target expression in the content page is received, calling a page callback interface of an operation system to display a translation control; when a first trigger signal corresponding to the translation control is received, obtaining a translation result of the target expression; and displaying the translation result. According to the method, the page callback interface is opened for the third-party application program, the translation control provided by the operation system is obtained and displayed through the interface, users can call out the translationcontrol through specific trigger operations for to-be-translated expressions when having translation demands during page content reading, and the users can obtain translation results of the to-be-translated expressions through triggering an operation control; and the translation is realized without switching between two application programs, so that the operations of the users during the translation can be saved and the translation efficiency is enhanced.

The invention provides a facial expression conversion method based on identity and expression feature conversion, and mainly solves the problem of personalized facial expression. Most of the existingfacial expression synthesis work attempts to learn conversion between expression domains, so that paired samples and marked query images are needed. Identity information and expression feature information of an original image can be stored by establishing the two encoders, and target facial expression features are used as condition tags. The method mainly comprises the following steps: firstly, carrying out facial expression training, preprocessing a neutral expression picture and other facial expression pictures, then extracting identity characteristic parameters and target facial expressioncharacteristic parameters of a neutral expression, and establishing a matching model; Secondly, performing facial expression conversion, inputting the neutral expression picture into a conversion model, and applying model output parameters to expression synthesis to synthesize a target expression image. Pairing data sets of different expressions with the same identity are not limited any more, identity information of an original image can be effectively reserved due to existence of the two encoders, and conversion from a neutral expression to different expressions can be achieved.

The invention provides a facial expression synthesis method based on a geometric comparative generative adversarial network, mainly comprising representation, composition, structuring and setting of the geometric comparative generative adversarial network. The process includes giving input faces and target expressions specified by a group of facial marks; identity maintaining faces can be generated by guidance of a target expression formula; the geometric comparative generative adversarial network is composed of a facial geometric embedded network, an image generator network and an image discriminator network; the facial geometric embedded network is used for mapping the facial marks to semantic manifold in a latent space through comparative learning; the geometric comparative generative adversarial network performs training in multi-task manner, wherein comparative learning, adversarial learning and reconstructive learning are used; a joint target is finally formed. The geometric comparative generative adversarial network is provided herein; the manifold is sensitive to geometric changes in global and local faces; the method is also suitable for other facial expression characteristics; the generated expressions have high fidelity and resolution.