Abstract: System and method for simultaneous object detection and semantic segmentation. The system includes a computing device. The computing device has a processor and a non-volatile memory storing computer executable code. The computer executable code, when executed at the processor, is configured to: receive an image of a scene; process the image using a neural network backbone to obtain a feature map; process the feature map using an object detection module to obtain object detection result of the image; and process the feature map using a semantic segmentation module to obtain semantic segmentation result of the image. The object detection module and the semantic segmentation module are trained using a same loss function comprising an object detection component and a semantic segmentation component.

Abstract: A method for determining an electronic device, a system for determining an electronic device, a computer system, and a computer-readable storage medium, the method includes: acquiring a recognition result by recognizing a first action performed by an operating object through a first electronic device (S201); and determining a second electronic device which is controllable by the first electronic device according to the recognition result (S202).

Abstract: A method, a device, and a non-transitory computer readable medium for item recommendation based on visual elements. The method includes: determining, by one or more processors, visual elements from an item image of an item; generating, by the one or more processors, an element descriptor for the item based on at least a part of the visual elements; and calculating, by the one or more processors, a compatibility value between the element descriptor and one or more other element descriptors for one or more other items.

Abstract: An automatic vending method and apparatus, and a computer-readable storage medium, relating to the field of automatic vending machines. The method includes: obtaining an image from a photographed video stream of commodities in an automatic vending machine; positioning an image of a commodity picked up by a user from the image; obtaining a change value of load weight of a shelf where the commodity is picked up by the user; determining a possible combination of commodities corresponding to the change value of load weight according to a weight of each commodity in the automatic vending machine; recognizing information of the commodity corresponding to the image of the commodity picked up by the user according to a pre-established commodity feature library and in conjunction with the possible combination of commodities; and performing settlement automatically for the user according to the recognized information of the commodity.

Abstract: Embodiments of the present disclosure provide a method and apparatus for processing an image. An embodiment of the method includes: acquiring a two-dimensional garment image, where the two-dimensional garment image includes a style identifier of a garment; selecting a three-dimensional garment model matching the style identifier from a pre-established set of three-dimensional garment models, wherein the three-dimensional garment model includes scatter points labeled thereon; labeling the two-dimensional garment image with scatter points based on a pre-established coordinate mapping relationship between the two-dimensional garment image and the three-dimensional garment model and the scatter points of the selected three-dimensional garment model; generating a three-dimensional garment image of the acquired two-dimensional garment image based on the selected three-dimensional garment model and a result of the labeling.

Abstract: The present disclosure provides an information processing method, including: acquiring a voice test signal, wherein the voice test signal is used for testing an influence parameter of a specified environment on a voice signal; acquiring a voice feedback signal obtained after the voice test signal is reflected by at least one reflecting object, wherein the at least one reflecting object is located in the specified environment; and estimating the influence parameter of the specified environment on the voice signal based on the voice test signal and the voice feedback signal acquired. In addition, the present disclosure also provides an information processing system, a computer system and a computer readable medium.

Abstract: The present disclosure relates to the technical field of multimedia, and provides a video processing method and apparatus. The video processing method according to the present disclosure includes: performing semantic analysis on subtitles of a video to acquire compressed subtitles; determining a weight of each frame of images in the video based on a preset image processing strategy; acquiring a shortened video images by extracting a plurality of image frames in an order of the weights of all frames of images from high to low, according to a preset video shortening proportion; and generating a shortened video according to the shortened video images and the compressed subtitles.

Abstract: The present disclosure provides a page presentation method, including: receiving an access request for a target page, wherein the target page has a plurality of page blocks; and presenting a block snapshot of at least one page block in the target page stored locally in response to the access request, wherein each page block has a respective block snapshot. In addition, the present disclosure also provides a page presentation system, a computer system, and a computer-readable medium.

Abstract: Embodiments of the present disclosure provide an image processing method, apparatus, and device. The method includes: obtaining a scene image in a scene to be displayed; obtaining a three-channel color value and a metallicity coefficient of each pixel point in the scene image; and performing diffuse reflection processing on the scene image according to the three-channel color value and the metallicity coefficient of each pixel point. The method in the embodiments of the present disclosure improves the authenticity of the scene to be displayed, which is more realistic and natural.

Abstract: A system and a method for multimedia data analysis. The system includes a computing device. The computer device includes a processor and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: encode task description and task meta info into concatenated task vectors; encode context text and context meta info into concatenated context text vectors; encode context image and the context meta info into concatenated context image vectors; perform dual coattention on the concatenated task vectors and the concatenated context text and image vectors to obtain attended task vectors and attended context vectors; perform BiLSTM on the attended task vectors and the attended context vectors to obtain task encoding and context encoding; and decode the task encoding and the context encoding to obtain an answer to the task.

Abstract: An embodiment of the invention provides a method and apparatus for partitioning an electronic fence, relating to the technical field of computers. The method in the embodiment of the invention comprises: partitioning a coordinate system of a planimetric map, and taking one vertex of each partition in the same direction as a base point; generalizing, according to a predetermined rule, a station to the base point corresponding to the partition where the station is located; mapping, according to the predetermined rule, a vehicle position to the base point corresponding to the partition where the vehicle position is located, wherein all the stations included in the base point are stations where a vehicle may appear; and acquiring electronic fence information of the stations where the vehicle may appear, and comparing vehicle position information with the electronic fence information of the stations where the vehicle may appear so as to determine whether the vehicle enters or leaves the stations.

Abstract: The present disclosure provides a method for timing control of an electronic device, comprising: receiving a timing control instruction for the electronic device from a user, the timing control instruction comprises controlling the electronic device to operate repeatedly during N continuous time periods with the same certain time duration, wherein N is a positive integer greater than or equal to 2, and each time period at least comprises a first sub-time period and a second sub-time period. Controlling an operation of the electronic device during each time period comprises: controlling the electronic device to perform a first action at a first time point which is a beginning of the time period; controlling the electronic device to perform a second action different from the first action, in response to the first sub-time period having elapsed since the first time point, and controlling the electronic device according to the timing control instruction.

Abstract: The present disclosure relates to a page control method and apparatus, and a computer-readable storage medium, and pertains to the technical field of application software. The method includes detecting an operation of a user on a current page of an application, displaying a label of each of at least one history page visited by the user, in response to detecting that the user triggers a page selection function, and jumping to a page corresponding to a label selected by the user from the current page, in response to detecting that the operation of the user is to select the label.

Abstract: Disclosed in the present application is an order processing method and device, a server, and a storage medium. The method comprises: acquiring order information of a to-be-processed order, the order information including storage-bin region information and volume information of at least one item indicated by the order; base on the storage-bin region information and the volume information, determining whether the order satisfies following conditions: the at least one item indicated by the order being located within one storage-bin region and the a sum of the volumes of the at least one item being smaller than a volume threshold; and in response to the order satisfying the conditions, determining the order as a to-be-processed order, to generate a to-be-processed order set.

Abstract: The present disclosure provides a massive picture processing method, a massive picture processing device, an electronic apparatus and a computer readable storage medium, relating to the technical field of data processing. Said method comprises: acquiring matrixes corresponding to a plurality of channels of respective picture in massive pictures, and performing bit-based layering on respective matrixes; storing, according to an inverted index structure, picture-bit-layered data corresponding to respective channels after bit-based layering, and generating a picture-layer index record file; decoding all the picture-layer indexes of the picture according to the picture-layer index record file and synthesizing the picture according to the decoding result.

Abstract: Disclosed are a method and device for recognizing a video. One specific embodiment of the method comprises: obtaining a video to be identified; inputting said video to a pre-trained local and global representation propagation LGD model to obtain the category of said video, wherein the LGD model learns a spatial-temporal representation in said video based on diffusion between local and global representations. According to this embodiment, the spatial-temporal representation in the video is learned based on diffusion between the local and global representations.

Abstract: Disclosed are an augmented reality-based coloring method and apparatus, an electronic device and a storage medium. The method comprises: acquiring three-dimensional mesh information of a human face, and acquiring position coordinates and texture coordinates of respective vertices of a target portion of the human face based on the three-dimensional mesh information of the human face; constructing a three-dimensional mesh of the target portion according to the position coordinates of respective vertices of the target portion, and determining a normal line of each vertex in the three-dimensional mesh; and coloring the target portion based on the position coordinates, the texture coordinates and a normal line of each vertex in the three-dimensional mesh, a preset shading map of the target portion, and a target RGB value of the target portion, thereby improving the stereoscopic impression and the sense of reality of coloring, and improving the user experience.

Abstract: The present disclosure relates to an automatic unloading carrier and an unmanned aerial vehicle. The automatic unloading carrier includes: a mounting base for being fixed with an unmanned carrying vehicle, a carrying arm driving mechanism and multiple carrying arms connected with the mounting base through the carrying arm driving mechanism, the multiple carrying arms are configured to be unfolded or folded due to the driving of the carrying arm driving mechanism, and the multiple carrying arms are configured to form a space for carrying a carried object during a folded state and release the carried object during an unfolded state.

Abstract: A method and device for storing high-concurrency data. The method comprises: receiving high-concurrency data sent from a plurality of clients (110); pushing the high-concurrency data into a primary data queue, and responding to a corresponding client (120); consuming the high-concurrency data in the primary data queue by using multithreading (130); fragmenting the high-concurrency data according to the number of local queues (140); pushing the fragmented high-concurrency data into the local queues (150); and consuming the high-concurrency data in the local queues and storing the high-concurrency data in a database (160). By means of data asynchronous storage, high-concurrency data is temporarily stored in the primary data queue and the local queues, thereby alleviating pressure on the database, avoiding the problem of a database crash in the case of a high-concurrency storage, and improving the efficiency of storing high-concurrency data.

Abstract: A method and system for generating a three-dimensional (3D) model of a garment. The method includes: providing an image of the garment; generating a 3D garment representation based on the image; registering the 3D garment representation to a 3D model to obtain a preliminary 3D garment model; projecting the preliminary 3D garment model dressed on the 3D model to an 2D projected image; and comparing the 2D projected image with the image of the garment, so as to refine the preliminary 3D garment model to obtain the final 3D model of the garment.