Abstract: Systems and techniques are described herein for processing video data. For example, an encoding device can obtain a sequence of video data and determine a minimum value in the sequence of video data. The encoding device can, based on the minimum value, identify positions in the sequence of video data associated with entry points for individually entropy codable parcels of a parallel entropy codable sequence of video data. The encoding device can generate the parallel entropy codable sequence of video data. The encoding device can further generate an index for the parallel entropy codable sequence of video data, the index identifying the individually entropy codable parcels within the parallel entropy codable sequence of video data.

Abstract: Systems and techniques are described herein for processing video data. For example, a machine-learning based stereo video coding system can obtain video data including at least a right-view image of a right view of a scene and a left-view image of a left view of the scene. The machine-learning based stereo video coding system can compress the right-view image and the left-view image in parallel to generate a latent representation of the right-view image and the left-view image. The right-view image and the left-view image can be compressed in parallel based on inter-view information between the right-view image and the left-view image, determined using one or more parallel autoencoders.

Abstract: A processor-implemented method for image compression using an artificial neural network (ANN) includes receiving, at an encoder of the ANN, an image and a spatial segmentation map corresponding to the image. The spatial segmentation map indicates one or more regions of interest. The encoder compresses the image according to a controllable spatial bit allocation. The controllable spatial bit allocation is based on a learned quantization bin size.

Abstract: Described are methods and systems are for generating dynamic conversational queries. For example, as opposed to being a simply reactive system, the methods and systems herein provide means for actively determining a user's intent and generating a dynamic query based on the determined user intent. Moreover, these methods and systems generate these queries in a conversational environment.

Abstract: The present invention relates to an enhanced method for the manufacture of a plastic component (135), in particular a cushioning element for sports apparel, the method comprising: opening a mold (100) by a predetermined amount into a loading position, wherein the mold comprises at least two mold parts (110, 112) and wherein the amount by which the mold is opened influences an available loading volume of the mold, loading a material comprising expanded particles (130) into the loading volume, closing the mold into a closed position, wherein during closing of the mold the mold parts are moved together over different distances (140) in different areas of the mold, compressing the expanded particles by closing the mold and fusing at least the surfaces of the expanded particles to mold the plastic component.

Abstract: Methods and systems are described herein for generating dynamic conversational responses. For example, dynamic conversational responses may facilitate an interactive exchange with users. Therefore, the methods and systems used specialized methods to enriched data that may be indicative of a user's intent prior to processing that data through the machine learning model, as well as a specialized architecture for the machine learning models that take advantage of the user interface format.

Abstract: Improved soles for shoes, in particular sports shoes, are described. A sole for a shoe, in particular a sports shoe, is provided that includes a midsole with randomly arranged particles of an expanded material. The sole further includes an element having a higher deformation stiffness in at least one direction than the expanded material. The material of the midsole at least partially surrounds the element.

Abstract: Methods and systems are described for generating dynamic interface options using machine learning models. The dynamic interface options may be generated in real time and reflect the likely goals and/or intents of a user. The machine learning model may provide these features by interpreting multi-modal feature inputs. For example, the machine learning model may include a first machine learning model, wherein the first machine learning model comprises a convolutional neural network, and a second machine learning model, wherein the second machine learning model performs a Weight of Evidence (WOE) analysis.

Abstract: Described are methods for manufacturing a plastic component, in particular a cushioning element for sports apparel, a plastic component manufactured with such methods, for example a sole or a part of a sole for a shoe, and a shoe with such a sole. The method for the manufacture of a plastic component includes loading a mold with a first material includes particles of an expanded material and fusing the surfaces of the particles by supplying energy. The energy is supplied in the form of at least one electromagnetic field.

Abstract: Provided herein are systems and methods for using multi-modal regression to predict customer intent to contact a merchant. Multi-modal data including numerical data and unstructured data are extracted from customer interactions with the merchant. Features of the numerical data and the unstructured data are separately extracted and classified using techniques specific to the data types. The features for each type are then separately used to predict probabilities of customer intent. A neural network is used to combine the predictions into a single set of estimates of customer intent. This set of estimates of customer intents is used to estimate a probability that the customer will contact the merchant. The customer is then contacted based on the estimate.

Abstract: An example computing device may include memory and one or more processors. The one or more processors may be configured to parallel entropy decode encoded video data from a received bitstream to generate entropy decoded data. The one or more processors may be configured to predict a motion vector based on the entropy decoded data. The one or more processors may be configured to decode a motion vector residual from the entropy decoded data. The one or more processors may be configured to add the motion vector residual and motion vector. The one or more processors may be configured to warp previous reconstructed video data with an overlapped block-based warp function using the motion vector to generate predicted current video data. The one or more processors may be configured to sum the predicted current video data with a residual block to generate current reconstructed video data.

Abstract: The invention refers to a method for producing expanded polymer pellets, which comprises the following steps: melting a polymer comprising a polyamide; adding at least one blowing agent; expanding the melt through at least one die for producing an expanded polymer; and pelletizing the expanded polymer. The invention further concerns polymer pellets produced with the method as well as their use, e.g. for the production of cushioning elements for sports apparel, such as for producing soles or parts of soles of sports shoes. A further aspect of the invention concerns a method for the manufacture of molded components, comprising loading pellets of an expanded polymer material into a mold, and connecting the pellets by providing heat energy, wherein the expanded polymer material of the pellets or beads comprises a chain extender. The molded components may be used in broad ranges of application.

Abstract: Methods for manufacturing cushioning elements for sports apparel are described. A method is provided for manufacturing a cushioning element for sports apparel from randomly arranged particles of an expanded material. The method includes positioning a functional element within a mold and loading the mold with the particles of the expanded material, wherein the loading occurs through at least two openings within the mold and/or wherein the loading occurs between different movable parts of the mold.

Abstract: A sensor (220) for a body monitoring system (1), having analyte-measuring microneedles (210) that extend parallel to a main direction (Z) from a substrate (242) and define a working plane (Pt), wherein the sensor (220) has at least one conductivity electrode (600) with a metallic track (602), the end of the metallic track extending along the main direction (Z) to a position strictly between the substrate (242) and the working plane (Pt).

Abstract: Methods and systems are described for generating dynamic conversational responses using two-tier machine learning models. The dynamic conversational responses may be generated in real time and reflect the likely goals and/or intents of a user. The two-tier machine learning model may include a first tier that determines an intent cluster based on a feature input, and a second tier that determines a specific intent from the cluster.

Abstract: Various embodiments relate generally to data science and data analysis, computer software and systems, and wired and wireless network communications to provide an interface between repositories of disparate datasets and computing machine-based entities that seek access to the datasets, and, more specifically, to a computing and data storage platform that facilitates consolidation of one or more datasets, whereby a collaborative data layer and associated logic facilitate, for example, efficient access to, and implementation of, collaborative datasets. In some examples, a system may include data ingestion controller configured to format datasets to form a first and a second atomized dataset, the second atomized dataset including the first atomized dataset and one or more other atomized datasets. The system may include a dataset query engine configured to identify a portion of a dataset relevant to a query, and to retrieve query results from at least one of different data repositories.

Abstract: Some embodiments generate prompts and submit them in queries to a language model trained on code to perform automated program repair. Some embodiments fix syntactic mistakes and semantic mistakes by combining multimodal prompts, iterative querying, test-case-based selection of few-shots, and program chunking. In some cases, edit distance is minimized between an initial flawed program and the automatically created improved version of that program. The initial flawed program is obtained from a programming student, or from a source code generator.

Abstract: The indirect querying of models to determine capabilities possessed by the model. Such indirect queries take the form of model input that potentially includes a natural language input user data. Such model input is structured such that the output of the model is either not natural language at all, or else is natural language that is not semantically responsive to the natural language input. Nevertheless, the output is evaluated to estimate or determine the capability possessed by the model. Thus, models may be more fully utilized to their better potential.

Abstract: Described are soles for a shoe, in particular for a sports shoe, with a midsole. The midsole includes a first sole region, which includes particle foam. The midsole further includes a deformation region within the midsole, wherein the deformation region has a volume greater than that of a single expanded particle and is positioned so that it allows a sideward deformation of the material of the first sole region under a pressure load on the sole.

Abstract: A method for monitoring an energy supply in a motor vehicle. At least one energy reservoir supplies energy to several preferably safety-relevant loads in a partial vehicle electrical system. At least one measured variable of an energy reservoir and/or of at least one load is detected. At least one wiring harness model is provided which models the partial vehicle electrical system. A parameter estimator is provided which assesses at least one characterizing variable of the wiring harness model using the measured variable.