Abstract: Systems, methods, and apparatuses relating sparsity based FMA. In some examples, an instance of a single FMA instruction has one or more fields for an opcode, one or more fields to identify a source/destination matrix operand, one or more fields to identify a first plurality of source matrix operands, one or more fields to identify a second plurality of matrix operands, wherein the opcode is to indicate that execution circuitry is to select a proper subset of FP8 data elements from the first plurality of source matrix operands based on sparsity controls from a first matrix operand of the second plurality of matrix operands and perform a FMA.

Abstract: Systems, methods, and apparatuses relating sparsity based FMA. In some examples, an instance of a single FMA instruction has one or more fields for an opcode, one or more fields to identify a source/destination matrix operand, one or more fields to identify a first plurality of source matrix operands, one or more fields to identify a second plurality of matrix operands, wherein the opcode is to indicate that execution circuitry is to select a proper subset of data elements from the first plurality of source matrix operands based on sparsity controls from a first matrix operand of the second plurality of matrix operands and perform a FMA.

Abstract: A student model may be trained in two stages by using two teacher models, respectively. The first teacher model has been trained with a pretraining dataset. The second teacher model has been trained with a training dataset that is specific to a task to be performed by the student model. In the first stage, the student model may be generated based on a structure of the first teacher model. Internal parameters of the student model are adjusted through a pretraining process based on the first teacher model and the pretraining dataset. Weights of the student model may be pruned during the pretraining process. In the second stage, a sparsity mask is generated for the student model to lock the sparsity pattern generated from the first stage. Further, some of the internal parameters of the student model are modified based on the second teacher model and the training dataset.

Abstract: Disclosed embodiments relate to sparse matrix multiplication (SMM) acceleration using column folding and squeezing. In one example, a processor, in response to a SMM instruction having fields to specify locations of first, second, and output matrices, the second matrix being a sparse matrix, uses execution circuitry to pack the second matrix by replacing one or more zero-valued elements with non-zero elements yet to be processed, each of the replaced elements further including a field to identify its logical position within the second matrix, and, the execution circuitry further to, for each non-zero element at row M and column K of the specified first matrix, generate a product of the element and each corresponding non-zero element at row K, column N of the packed second matrix, and accumulate each generated product with a previous value of a corresponding element at row M and column N of the specified output matrix.

Abstract: Disclosed embodiments relate to sparse matrix multiplication (SMM) acceleration using column folding and squeezing. In one example, a processor, in response to a SMM instruction having fields to specify locations of first, second, and output matrices, the second matrix being a sparse matrix, uses execution circuitry to pack the second matrix by replacing one or more zero-valued elements with non-zero elements yet to be processed, each of the replaced elements further including a field to identify its logical position within the second matrix, and, the execution circuitry further to, for each non-zero element at row M and column K of the specified first matrix, generate a product of the element and each corresponding non-zero element at row K, column N of the packed second matrix, and accumulate each generated product with a previous value of a corresponding element at row M and column N of the specified output matrix.

Abstract: A system and method for detecting an object of interest. A system and method may generate a first signature for an object of interest based on an image of the object of interest. A system and method may generate a second signature for a candidate object based on an image of the candidate object. A system and method may calculate a similarity score by relating the first signature to the second signature and may determine the image of the candidate object is an image of the object of interest based on the similarity score.

Abstract: A system and method for detecting an object of interest. A system and method may generate a first signature for an object of interest based on an image of the object of interest. A system and method may generate a second signature for a candidate object based on an image of the candidate object. A system and method may calculate a similarity score by relating the first signature to the second signature and may determine the image of the candidate object is an image of the object of interest based on the similarity score.

Abstract: A system and method for detecting an object of interest. A system and method may generate a first signature for an object of interest based on an image of the object of interest. A system and method may generate a second signature for a candidate object based on an image of the candidate object. A system and method may calculate a similarity score by relating the first signature to the second signature and may determine the image of the candidate object is an image of the object of interest based on the similarity score.

Abstract: A system and method for detecting an object of interest. A system and method may generate a first signature for an object of interest based on an image of the object of interest. A system and method may generate a second signature for a candidate object based on an image of the candidate object. A system and method may calculate a similarity score by relating the first signature to the second signature and may determine the image of the candidate object is an image of the object of interest based on the similarity score.

Abstract: The subject matter discloses a method, comprising obtaining a scene from a video camera and defining at least one point of the scene; creating a first scene terrain model of the scene, said first scene terrain model comprises a typical human object size in pixels in said at least one point of the scene; creating a second scene model of the scene, said second model defines a false positive determination that said at least one point comprises a human object; wherein said second scene model is created when the scene does not contain a human object; obtaining an image of the scene, said image is captured by a video camera; determining whether the human object is detected at the at least one point of said captured image by applying said first scene terrain model and said second scene model on the least one point.

Abstract: The subject matter discloses a method, comprising obtaining a scene from a video camera and defining at least one point of the scene; creating a first scene terrain model of the scene, said first scene terrain model comprises a typical human object size in pixels in said at least one point of the scene; creating a second scene model of the scene, said second model defines a false positive determination that said at least one point comprises a human object; wherein said second scene model is created when the scene does not contain a human object; obtaining an image of the scene, said image is captured by a video camera; determining whether the human object is detected at the at least one point of said captured image by applying said first scene terrain model and said second scene model on the least one point.