Abstract: The present application discloses a cross-media retrieval method based on deep semantic space, which includes a feature generation stage and a semantic space learning stage. In the feature generation stage, a CNN visual feature vector and an LSTM language description vector of an image are generated by simulating a perception process of a person for the image; and topic information about a text is explored by using an LDA topic model, thus extracting an LDA text topic vector. In the semantic space learning phase, a training set image is trained to obtain a four-layer Multi-Sensory Fusion Deep Neural Network, and a training set text is trained to obtain a three-layer text semantic network, respectively. Finally, a test image and a text are respectively mapped to an isomorphic semantic space by using two networks, so as to realize cross-media retrieval. The disclosed method can significantly improve the performance of cross-media retrieval.

Abstract: A video action detection method based on a convolutional neural network (CNN) is disclosed in the field of computer vision recognition technologies. A temporal-spatial pyramid pooling layer is added to a network structure, which eliminates limitations on input by a network, speeds up training and detection, and improves performance of video action classification and time location. The disclosed convolutional neural network includes a convolutional layer, a common pooling layer, a temporal-spatial pyramid pooling layer and a full connection layer. The outputs of the convolutional neural network include a category classification output layer and a time localization calculation result output layer. The disclosed method does not require down-sampling to obtain video clips of different durations, but instead utilizes direct input of the whole video at once, improving efficiency.

Abstract: Disclosed is a boundary filtering method for intra prediction, relating to the video encoding technology filed. Whether boundary filtering is performed on an intra prediction block or not is adaptively selected by means of a rate distortion optimization decision; during filtering, a filter coefficient exponentially attenuated relative to distance to boundary is adopted to perform filtering on the first N rows or the first N columns of the intra prediction block by means of an intra prediction block filter, and different filtering strengths are used according to different sizes of the prediction blocks. Therefore, the boundary distortion problem of intra prediction block is solved, the intra prediction precision is improved, and the encoding efficiency of intra prediction block is increased; and the practicability and the robustness of the boundary filtering technology are improved.

Abstract: The embodiment of the present specification discloses an image synthesis method, apparatus and device for free-viewpoint.

Abstract: The present specification discloses a method, apparatus, and device for video frame interpolation.

Abstract: The present application provides methods, systems, devices and computer-readable mediums for encoding and decoding transform. A method of the present application comprises: performing transform-encoding on a prediction residual block separately using a plurality of transform matrices, to obtain transformed residual blocks; based on the transformed residual block, determining, by a rate-distortion optimization decision, a transform matrix or a combination of transform matrices matching the residual characteristics of the prediction residual block from the plurality of transform matrices, and determining a transformed residual block to be outputted in a bitstream. Compared with the prior art, the method of the embodiments of the present invention performs a residual transform using transform matrices that are more closely matched with the residual characteristic, thereby improving the expression of the residual signal and improving the coding efficiency of the residual block.

Abstract: A method and a device for MCMC framework-based sub-hypergraph matching are provided. Matching of object features is performed by constructing sub-hypergraphs. In a large number of actual images and videos, objects vary constantly, and contain various noise points as well as other interference factors, which makes image object matching and searching very difficult. Perform object feature matching by representing the appearance and positions of objects by sub-hypergraphs allows for faster and more accurate image matching. Furthermore, a sub-hypergraph has several advantages over a graph or a hypergraph: on one hand, a sub-hypergraph has more geometric information (e.g. angle transformation, rotation, scale, etc.) than a graph, and has a lower degree of difficulty and better extensibility than a hypergraph. On the other hand, the disclosed method and device have stronger capabilities to resist interference and good robustness, and are adaptable to more complex settings, especially with outliers.

Abstract: The present application provides a method and a device of encoding and decoding based on free viewpoint, and relates to the technical field of video encoding. The method includes: generating a planar splicing image and splice information based on multiple single-viewpoint videos at a server side; generating a planar splicing video based on the planar splicing image; generating camera side information of the planar splicing video based on camera side information existing in the multiple single-viewpoint videos; and encoding the planar splicing video, the splice information and the camera side information of the planar splicing video to generate a planar splicing video bit stream, and decoding a planar splicing video bit stream to acquire a virtual viewpoint according to viewpoint information of a viewer at client side.

Abstract: A high dielectric constant composite material and method for preparing organic thin film transistor using the material as dielectric. The method includes: using sol-gel method, hydrolyzing terminal group-containing silane coupling agent to form functional terminal group-containing silica sol, cross-linked with organic polymer to form composite sol as material of dielectric of organic thin film transistor; forming film by solution method such as spin coating, dip coating, inkjet printing, 3D printing, etc., forming dielectric after curing; preparing semiconductor and electrode respectively to prepare organic thin film transistor device, which, based on composite dielectric material, has mobility of 5 cm2/V·s, exceeding that of using SiO2, having low threshold voltage and no hysteresis effect. Compared with traditional processes like SiO2 thermal oxidation, above method has advantages of simple process, low cost, suitable for large-area preparation, with great market application value.

Abstract: A supercapacity lithium ion battery cathode material, a preparation method therefor and an application thereof. The supercapacity lithium ion battery cathode material consists of a transition metal-containing lithium ion cathode material and carbon which is coated on the surface of the lithium ion cathode material. The transition metal on the surface of the lithium ion cathode material is coordinated with carbon by means of X—C bonds to form transition metal-X—C chemical bonds, such that carbon stably coats the surface of the cathode material, wherein C is SP3 hybridization and/or SP2 hybridization, and X is at least one selected from among N, O and S.

Abstract: Disclosed are a panoramic video asymmetrical mapping method and a corresponding inverse mapping method that include mapping a spherical surface corresponding to a panoramic image or video A onto a two-dimensional image or video B, projecting the spherical surface onto an isosceles quadrangular pyramid with a square bottom plane, and further projecting the isosceles quadrangular pyramid onto a planar surface, using isometric projection on a main viewpoint region in the projection and using a relatively high sampling density to ensure that the video quality of the region of the main viewpoint is high, while using a relatively low sample density for non-main viewpoint regions so as to reduce bit rate. The panoramic video asymmetrical inverse mapping technique provides a method for mapping from a planar surface to a spherical surface, and a planar surface video may be mapped back to a spherical surface for rendering and viewing.

Abstract: The present disclosure includes a shift register unit circuit, including input storing module, configured to receive an input signal at an input terminal and store the input signal; storage retrieving module, configured to retrieve the input signal from the input storing module under influence of at least a first clock signal; output driving module, configured to transfer the input signal to an first output terminal under control of the storage retrieving module; and pulling-down and maintaining module, configured to pull down a voltage at the output terminal to low voltage level after output operation is completed, and maintain the voltage at low voltage level until the output driving module receives a next input signal. The present disclosure also includes a gate driver circuit including such shift register units and a method for generating gate driving signal.

Abstract: The present application provides methods, systems, devices and computer-readable mediums for deblocking filter. A method of the present application comprises: determining a filtering boundary, and then determining a filter pixel group based on the filtering boundary; determining a filter strength of the filter pixel group, comprising: parsing separately a pixel value difference states of pixel points on both sides of the filtering boundary in the filter pixel group to obtain two one-sided flatness FL and FR; calculating a comprehensive flatness FS of the filter pixel group, wherein FS=FL+FR; calculating the filter strength according to FS; filtering calculation of pixel points included in the filter pixel group according to the filter strength.

Abstract: An integrated package method for MEMS element and ASIC chip includes forming a re-layout layer on a front surface of an ASIC wafer; coating an organic compound layer on the re-layout layer and applying a lithography process to the organic compound layer to from a microcavity array; aligning and bonding an electrode connection pad layer on a front surface of an MEMS element with the microcavity array to form a closed cavity structure; thinning and exposing a silicon substrate on a back surface of the MEMS element to a desired thickness; applying the lithographic process on the MEMS element to expose the electrode connection pad layer and an electrical contact area of the re-layout layer; and manufacturing a metal connection member connected to the electrode connection pad layer and the electrical contact area. An integrated package structure for MEMS element and ASIC chip is also provided.

Abstract: An enhanced graph transformation-based point cloud attribute compression method. For point cloud attribute information, a point cloud is first subjected to airspace division by using a K-dimension (KD) tree; a new graph transformation processing method in combination with spectral analysis is provided; the point cloud is then subjected to spectral clustering on graphs in coded blocks of the point cloud; expansion is performed on the basis of existing graph transformation to implement a local graph transformation scheme; enhanced graph transformation with two transformation modes is formed; the compression performance of graph transformation is improved. The method comprises: performing color space transformation of point cloud attributes; dividing the point cloud by using the KD tree to obtain the coded blocks; performing spectral clustering-based enhanced graph transformation; performing transformation mode decision; and performing uniform quantization and entropy coding.

Abstract: An intra-frame prediction-based point cloud attribute compression method. A new block structure-based intra-frame prediction scheme is provided for point cloud attribute information, where four prediction modes are provided to reduce information redundancy among different coding blocks as much as possible and improve point cloud attribute compression performance. The method comprises: performing point cloud attribute color space conversion; dividing a point cloud by using a K-dimensional (KD) tree to obtain coding blocks; performing block structure-based intra-frame prediction; performing intra-frame prediction mode division; performing conversion, uniform quantization, and entropy coding.

Abstract: Disclosed is a deep discriminative network for person re-identification in an image or a video. Concatenation are carried out on different input images on a color channel by constructing a deep discriminative network, and an obtained splicing result is defined as an original difference space of different images. The original difference space is sent into a convolutional network. The network outputs the similarity between two input images by learning difference information in the original difference space, thereby realizing person re-identification. The features of an individual image are not learnt, and concatenation are carried out on input images on a color channel at the beginning, and difference information is learnt on an original space of the images by using a designed network. By introducing an Inception module and embedding the same into a model, the learning ability of a network can be improved, and a better differentiation effect can be achieved.

Abstract: The present disclosure provides a hybrid framework-based image bit-depth expansion method and device. The invention fuses a traditional de-banding algorithm and a depth network-based learning algorithm, and can remove unnatural effects in an image flat area whilst more realistically restoring numerical information of missing bits. The method comprises the extraction of image flat areas, local adaptive pixel value adjustment-based flat area bit-depth expansion and convolutional neural network-based non-flat area bit-depth expansion. The present invention uses a learning-based method to train an effective depth network to solve the problem of realistically restoring missing bits, whilst using a simple and robust local adaptive pixel value adjustment method in an flat area to effectively inhibit unnatural effects in the flat area such as banding, a ringing and flat noise, improving subjective visual quality of the flat area.

Abstract: A wafer scale ultrasonic sensing device includes a substrate assembly, an ultrasonic component, a first protective layer, a first conductive circuit, a second conductive circuit, a second protective layer, a conductive material, electrical connection layers, and soldering portions. The substrate assembly includes a first wafer and a second wafer, and the second wafer covers a groove on the first wafer to define a hollow chamber. The first wafer, the second wafer, and the first protective layer are coplanar with the first conductive circuit on a first side surface and coplanar with the second conductive circuit on a second side surface. The second protective layer has an opening, where the conductive material is in the opening and is in contact with the ultrasonic component. The electrical connection layers are on the first side surface and the second side surface, and the soldering portions are respectively connected to the electrical connection layers.

Abstract: An intra-frame and inter-frame combined prediction method for P frames or B frames. The method comprises: self-adaptively selecting by means of a rate-distortion optimization (RDO) decision whether to use the intra-frame and inter-frame combined prediction or not; using a method for weighting an intra prediction block and an inter prediction block in the intra-frame and inter-frame combined prediction to obtain a final prediction block; and obtaining the weighting coefficient of the intra prediction block and the inter prediction block according to prediction distortion statistics of the prediction method. Therefore, prediction precision can be improved, and coding and decoding efficiency of the prediction blocks are improved.