Abstract: Examples described herein relate to processing packets. In some examples, based on receipt of a Hypertext Transfer Protocol (HTTP) packet at a network interface device, the HTTP packet comprising an HTTP body and HTTP header: provide the HTTP header, but not the HTTP body, for processing in user space; modify solely the HTTP header in user space; and in kernel space, combine the modified HTTP header and the HTTP body prior to transmission of the HTTP packet with modified HTTP header to a client.

Abstract: Methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement dynamic triplet convolution for convolutional neural networks are disclosed. An example apparatus disclosed herein for a convolutional neural network is to calculate one or more scalar kernels based on an input feature map applied to a layer of the convolutional neural network, ones of the one or more scalar kernels corresponding to respective dimensions of a static multidimensional convolutional filter associated with the layer of the convolutional neural network. The disclosed example apparatus is also to scale elements of the static multidimensional convolutional filter along a first one of the dimensions based on a first one of the one or more scalar kernels corresponding to the first one of the dimensions to determine a dynamic multidimensional convolutional filter associated with the layer of the convolutional neural network.

Abstract: Techniques related to 3D pose estimation from a 2D input image are discussed. Such techniques include incrementally adjusting an initial 3D pose generated by applying a lifting network to a detected 2D pose in the 2D input image by projecting each current 3D pose estimate to a 2D pose projection, applying a residual regressor to features based on the 2D pose projection and the detected 2D pose, and combining a 3D pose increment from the residual regressor to the current 3D pose estimate.

Abstract: Embodiments are generally directed to methods and apparatuses for dynamic normalization and relay in a neural network. An embodiment of an apparatus for dynamic normalization and relay in a neural network including a hyper normalization layer comprises: a compute engine to: generate a hidden state and a cell state for the hyper normalization layer based on an input feature map for the hyper normalization layer as well as a previous hidden state and a previous cell state; and normalize the input feature map in the hyper normalization layer with the hidden state and the cell state for the hyper normalization layer.

Abstract: Processes and systems are disclosed. The processes and systems are arranged to apply convolution for a CNN where the CNN is simplified using sparse techniques, quantization techniques or both sparse and quantization techniques. A location vector (LV) table is provided to record the coordinates of non-zero weights. A look up table is provided to recover the real weight value from the weight identification. Convolution is applied by retrieving the coordinates of the next non-zero weight and the associated real weight value and by accumulating the multiplication of the real weight value and the input value across the input activation plane.

Abstract: Techniques are provided for adaptive distribution of video analysis workload over a network of video processor nodes. The nodes may include, for example, internet protocol (IP) cameras, video recorders and/or data centers. The network may also include a management system configured to assign video analysis tasks to the nodes based on the node resources and predictive modelling of the node workload. The management system may re-distribute the tasks based on performance monitoring. Some assigned tasks may be bound to the node while other tasks may be transferrable, by the node, to other nodes. The nodes may be configured to determine which of the transferrable tasks will be locally executed or transferred based on a check of resource usage against a usage policy that specifies thresholds for the determinations. The nodes may be configured to transmit video analysis packets, including image data, analysis completion status and analysis results, to other nodes.

Abstract: Techniques are provided for adaptive distribution of video analysis workload over a network of video processor nodes. The nodes may include, for example, internet protocol (IP) cameras, video recorders and/or data centers. The network may also include a management system configured to assign video analysis tasks to the nodes based on the node resources and predictive modelling of the node workload. The management system may re-distribute the tasks based on performance monitoring. Some assigned tasks may be bound to the node while other tasks may be transferrable, by the node, to other nodes. The nodes may be configured to determine which of the transferrable tasks will be locally executed or transferred based on a check of resource usage against a usage policy that specifies thresholds for the determinations. The nodes may be configured to transmit video analysis packets, including image data, analysis completion status and analysis results, to other nodes.