Abstract: A comprehensive utilization method for iron separation tailings from magnetizing-roasted red mud includes the following steps: performing a wet magnetic separation for tailing discarding on iron separation tailings from magnetizing-roasted red mud, to obtain a rough concentrate and non-magnetic minerals; performing a purification by gravity separation on the rough concentrate to obtain a wet iron concentrate and light minerals; dehydrating the wet iron concentrate to obtain an iron concentrate; combining, and then dehydrating, drying, and disintegrating the non-magnetic minerals and the light minerals, to obtain iron extraction tailings; uniformly mixing the iron extraction tailings, and crushed, ground, and dried limestone, clay, and quartz sand separation tailings according to a predetermined ratio to obtain a cement raw meal; pressing, and then calcining and quenching the cement raw meal to obtain a cement clinker; and mixing the cement clinker and a gypsum followed by a dry grinding to obtain a silicate c

Abstract: A foundational tabular data model is trained on a plurality of different data sets that may include non-simulated, real-world data. The tabular data model processes an input including a set of context data samples with corresponding labels and a query to be processed with the contexts and label as an example. The tabular data model may be applied to new data sets outside the training data using only the context of the new data set. To do so, the tabular data model is trained with training batches that include data samples from the plurality of data sets with different data fields (columns) selected as the target for tabular prediction of differing tasks and inputting data samples with inputs excluding the selected target, enabling the tabular data model to learn complex and varied relationships from real data without predefined labels or task objectives.

Abstract: A composite quaternary ammonium salt cationic collector and its preparation method and uses involve: adding a halogenated alkyl group into an alkyl tertiary amine containing amido group to carry out a quaternization reaction to obtain an intermediate; and adding a catalyst into the intermediate to carry out a catalytic reaction to obtain a first mixture; adding an alkyl benzylamine into the first mixture to carry out an amidation reaction to obtain a second mixture; and desalting the second mixture to obtain a composite quaternary ammonium salt cationic collector; a molar ratio of the alkyl tertiary amine, the halogenated alkyl group, and the alkyl benzylamine is (1-1.4):(0.8-1.2):(1-1.4).

Abstract: A text-video recommendation model determines relevance of a text to a video in a text-video pair (e.g., as a relevance score) with a text embedding and a text-conditioned video embedding. The text-conditioned video embedding is a representation of the video used for evaluating the relevance of the video to the text, where the representation itself is a function of the text it is evaluated for. As such, the input text may be used to weigh or attend to different frames of the video in determining the text-conditioned video embedding. The representation of the video may thus differ for different input texts for comparison. The text-conditioned video embedding may be determined in various ways, such as with a set of the most-similar frames to the input text (the top-k frames) or may be based on an attention function based on query, key, and value projections.

Abstract: An example operation may include one or more of identifying dimensional parameters of a memory of an artificial intelligence (AI) model, receiving tabular data for execution by the AI model, determining a subset of data from within the tabular data that fits within the dimensional parameters of the memory, extracting the subset of data from the tabular data and converting the subset of data into at least one vector, and executing the AI model on the subset of data to generate a predictive result.

Abstract: An example operation may include at least one of storing tabular data in a database, receiving an input sequence by a transformer model that includes global context, generating a query vector from the input sequence, wherein the query vector corresponds to a data record within the tabular data, generating local context comprising at least one additional vector from the input sequence within a proximity threshold to the query vector within vector space, replacing the global context of the transformer model with the local context, and generating an output based on execution of the transformer model with the local context on the query vector and the tabular data.

Abstract: An example operation may include one or more of storing a table comprising a plurality of columns corresponding to a plurality of attributes and a plurality of rows of data corresponding to a plurality of records, receiving a target record to be executed by an artificial intelligence (AI) model, identifying a subset of records in the table that are similar to the target record based on a comparison of attribute values within the subset of records to corresponding attribute values within the target record, executing the AI model on the subset of records to generate a trained AI model, and executing the trained AI model on the target record to generate a predicted result for the target record.

Abstract: An example operation may include one or more of storing a table comprising a plurality of columns corresponding to a plurality of attributes and a plurality of rows corresponding to a plurality of records, receiving a target record of a task of an artificial intelligence (AI) model, converting the plurality of records into a plurality of embeddings in multi-dimensional vector space, converting the target record into a target embedding in the multi-dimensional vector space, identifying a subset of records from among the plurality of records that are nearest to the target record in content based on distances between embeddings of the subset of records and the target embedding within the multi-dimensional vector space, and executing the AI model on the subset of records to generate a predicted output with respect to the task.

Abstract: An example operation may include at least one of executing an AI model include a transformer with a self-attention mechanism that includes global context, receiving a query point associated with an input sequence, creating local context for the query point, the local context including kNN data points within the input sequence, generating a context-aware representation of the input sequence based on execution of the self-attention mechanism with the local context, and inputting the context-aware representation to a feedforward network (FFN).

Abstract: An example operation may include one or more of storing a table comprising a plurality of records, receiving a target record to be executed by an artificial intelligence (AI) model to perform a task, retrieving a subset of records from the plurality of records within the table based on content values in the target record and corresponding content values in the subset of records, identifying a first group of records among the subset of records that are related to the target record based on attributes associated with the target record and attributes associated with the first group of records, weighting the first group of records greater than other records within the subset of records to generate a weighted subset of records, and executing the AI model on the weighted subset of records to generate a predictive result.

Abstract: Context-based tabular data models use a context to evaluate a queried data point. Rather than a randomized or full context of domain data points, a local context of data points is selected that is customized for a particular data query. The system uses a pre-trained model, such as a TabPFN, that is trained on a classification for different types of data sets along with a “context” for applying the model with the nearest neighbors of that data point. The number of neighbors may vary and may be determined based on the distance of data points to the query point. The system also optimizes fine-tuning of tabular data models with neighborhood data so that local context can be used to select training batches of data using a common context. This allows local context fine-tuning without excess training costs of single-item training batches.

Abstract: Context-based tabular data models use a context to evaluate a queried data point. Rather than a randomized or full context of domain data points, a local context of data points is selected that is customized for a particular data query. The system uses a pre-trained model, such as a TabPFN, that is trained on a classification for different types of data sets along with a “context” for applying the model with the nearest neighbors of that data point. The number of neighbors may vary and may be determined based on the distance of data points to the query point. The system also optimizes fine-tuning of tabular data models with neighborhood data so that local context can be used to select training batches of data using a common context. This allows local context fine-tuning without excess training costs of single-item training batches.

Abstract: A text-video recommendation model determines relevance of a text to a video in a text-video pair (e.g., as a relevance score) with a text embedding and a text-conditioned video embedding. The text-conditioned video embedding is a representation of the video used for evaluating the relevance of the video to the text, where the representation itself is a function of the text it is evaluated for. As such, the input text may be used to weigh or attend to different frames of the video in determining the text-conditioned video embedding. The representation of the video may thus differ for different input texts for comparison. The text-conditioned video embedding may be determined in various ways, such as with a set of the most-similar frames to the input text (the top-k frames) or may be based on an attention function based on query, key, and value projections.

Abstract: A tabular modeling system uses a tabular data model to predict data sample classification for input data samples. When applied, the tabular data model receives a context and an input data point and outputs a classification of the input data. When the tabular data model is applied to a new training set, the tabular modeling system optimizes the context for the new training set by fixing model parameters while modifying context points with respect to the training data set. This enables the tabular data model to learn effective contexts for different data sets.

Abstract: A video localization system localizes actions in videos based on a classification model and an actionness model. The classification model is trained to make predictions of which segments of a video depict an action and to classify the actions in the segments. The actionness model predicts whether any action is occurring in each segment, rather than predicting a particular type of action. This reduces the likelihood that the video localization system over-relies on contextual information in localizing actions in video. Furthermore, the classification model and the actionness model are trained based on weakly-labeled data, thereby reducing the cost and time required to generate training data for the video localization system.

Abstract: A tabular data model, which may be pre-trained on a different data set, is used to generate data samples for a target class with a given set of context data points. The tabular data model is trained to predict class membership of a given data point with a set of context data points. Rather than use the predicted class directly, the class predictions are used to determine a class-conditional energy for a synthetic data point with respect to the target class. The synthetic data point may then be updated based on the class-conditional energy with a stochastic update algorithm, such as stochastic gradient Langevin dynamics or Adaptive Moment Estimation with noise. The value of the synthetic data point is sampled as a data point for the target class. This permits effective data augmentation for tabular data for downstream models.

Abstract: A video localization system localizes actions in videos based on a classification model and an actionness model. The classification model is trained to make predictions of which segments of a video depict an action and to classify the actions in the segments. The actionness model predicts whether any action is occurring in each segment, rather than predicting a particular type of action. This reduces the likelihood that the video localization system over-relies on contextual information in localizing actions in video. Furthermore, the classification model and the actionness model are trained based on weakly-labeled data, thereby reducing the cost and time required to generate training data for the video localization system.

Abstract: Provided are a method and device employing a smart contract to realize identity-based key management. The method comprises: running a smart contract, and executing a key management process, wherein the key management process comprises: when a key of a target user requires an update and the target user is not a supervised user, generating a master public key and a master private key pertaining to the target user; acquiring, from a blockchain, identity information of the target user; generating a first target private key according to the master public key and the master private key pertaining to the target user and the identity information of the target user; and replacing a current private key of the target user with the first target private key.

Abstract: There is shown and described a deep learning based system and method for skin diagnostics as well as testing metrics that show that such a deep learning based system outperforms human experts on the task of apparent skin diagnostics. Also shown and described is a system and method of monitoring a skin treatment regime using a deep learning based system and method for skin diagnostics.

Abstract: A text-video recommendation model determines relevance of a text to a video in a text-video pair (e.g., as a relevance score) with a text embedding and a text-conditioned video embedding. The text-conditioned video embedding is a representation of the video used for evaluating the relevance of the video to the text, where the representation itself is a function of the text it is evaluated for. As such, the input text may be used to weigh or attend to different frames of the video in determining the text-conditioned video embedding. The representation of the video may thus differ for different input texts for comparison. The text-conditioned video embedding may be determined in various ways, such as with a set of the most-similar frames to the input text (the top-k frames) or may be based on an attention function based on query, key, and value projections.