Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.

Abstract: In one embodiment, an apparatus comprises a communication interface and a processor. The communication interface is to communicate with a plurality of devices. The processor is to: receive compressed data from a first device, wherein the compressed data is associated with visual data captured by sensor(s); perform a current stage of processing on the compressed data using a current CNN, wherein the current stage of processing corresponds to one of a plurality of processing stages associated with the visual data, and wherein the current CNN corresponds to one of a plurality of CNNs associated with the plurality of processing stages; obtain an output associated with the current stage of processing; determine, based on the output, whether processing associated with the visual data is complete; if the processing is complete, output a result associated with the visual data; if the processing is incomplete, transmit the compressed data to a second device.

Abstract: A mechanism is described for facilitating protection and recovery of identities in surveillance camera environments according to one embodiment. An apparatus of embodiments, as described herein, includes detection and reception logic to receive a video stream of a scene as captured by a camera, wherein the scene includes persons. The apparatus may further include recognition and application logic to recognize an abnormal activity and one or more persons associated with the abnormal activity in a video frame of the video stream. The apparatus may further include identity recovery logic to recover one or more identities of the one or more persons in response to the abnormal activity, where the one or more identities are recovered from masked data and encrypted residuals associated with the one or more persons.

Abstract: In one embodiment, an apparatus comprises a storage device and a processor. The storage device may store a plurality of compressed images comprising one or more compressed master images and one or more compressed slave images.

Abstract: To address the storage needs of applications that work with noisy data (e.g. image, sound, video data), where errors can be tolerated to a certain extent and performance is more critical than data fidelity, dynamic reliability levels enable storage devices capable of storing and retrieving data with varying degrees of data fidelity to dynamically change the degree of data fidelity in response to an application's request specifying reliability level. By allowing the application to specify the reliability level at which its data is stored and retrieved, dynamic reliability levels can increase read/write performance without sacrificing application accuracy. The application can specify reliability levels for different types or units of data, such as different reliability levels for metadata as opposed to data and so forth.

Abstract: Techniques related to applying computer vision to decompressed video are discussed. Such techniques may include generating a region of interest in an individual video frame by translating spatial indicators of a first detected computer vision result from a reference video frame to the individual video frame and applying a greater threshold within the region of interest than outside of the region of interest for computer vision evaluation in the individual frame.

Abstract: A mechanism is described for facilitating age classification of humans using image depth and human pose according to one embodiment. A method of embodiments, as described herein, includes facilitating, by one or more cameras of a computing device, capturing of a video stream of a scene having persons, and computing overall-depth torso lengths of the persons based on depth torso lengths of the persons. The method may further include comparing the overall-depth torso lengths with a predetermined threshold value representing a separation age between adults and children, and classifying a first set of the persons as adults if a first set of the overall-depth torso lengths associated with the first set of persons is greater than the threshold value.

Abstract: An example apparatus for encoding video frames includes a receiver to receive video frames and a heat map from a camera and expected object regions from a video database. The apparatus also includes a region of interest (ROI) map generator to detect a region of interest in a video frame based on the expected object regions. The ROI map generator can also detect a region of interest in the video frame based on the heat map. The ROI map generator can then generate an ROI map based on the detected regions of interest. The apparatus further includes a parameter adjuster to adjust an encoding parameter based on the ROI map. The apparatus also further includes a video encoder to encode the video frame using the adjusted encoding parameter.

Abstract: An example apparatus for encoding video frames includes a receiver to receive events from a dynamic vision sensor and a video frame from an image sensor. The apparatus also includes a heat map generator to generate a heat map based on the received events. The apparatus further includes a region of interest (ROI) map generator generate a ROI map based on the heat map. The apparatus includes a parameter adjuster to adjust an encoding parameter based on the ROI map. The apparatus also further includes a video encoder to encode the video frame using the adjusted parameter.

Abstract: An example apparatus for estimating poses includes a person estimator to estimate a number of people based on a significant head count of received refined part detections. The apparatus includes a detection clusterer to cluster the refined part detections based on the estimated number of people to generate clustered part detections. The apparatus includes a candidate selector to select candidate person clusters for each clustered part detection based on proximity to the clustered part detection. The apparatus includes a sequential assigner to calculate a cluster affinity score for each combination of candidate person cluster and clustered part detection, and greedily sequentially assign each clustered part detection to a candidate person cluster based on the cluster affinity score to generate person clusters. The apparatus includes a pose generator to generate a pose for each person cluster.

Abstract: Technologies for detecting interactions with surfaces from a spherical view of a room include a compute device. The compute device includes an image capture manager to obtain one or more images that depict a spherical view of a room that includes multiple surfaces. Additionally, the compute device includes a surface interaction detection manager to detect, from the one or more images, a person in the room, generate a bounding box around the person, preprocess the bounding box to represent the person in an upright orientation, determine a pose of the person from the preprocessed bounding box, detect an outstretched hand from the determined pose, and determine, from the detected outstretched hand, a surface of interaction in the room.

Abstract: Methods, apparatus, and systems to create, output, and use animation programs comprising keyframes, objects, object states, and programming elements. Objects, object states, and programming elements may be created through image analysis of image input. Animation programs may be output as videos, as non-linear interactive experiences, and/or may be used to control electronic actuators in articulated armatures.

Abstract: Examples include a determination how to manage storage of a video clip generated from recorded video based upon a sensor event. Managing storage of the video clip may include determining whether to save or delete the video clip based on an imprint associated with an object that indicates whether the object is included in the video clip.

Abstract: An example apparatus for detecting speech includes an image receiver to receive depth information corresponding to a face. The apparatus also includes a landmark detector to detect the face comprising lips and track a plurality of descriptor points comprising lip descriptor points located around the lips. The apparatus further includes a descriptor computer to calculate a plurality of descriptor features based on the tracked descriptor points. The apparatus includes a pattern generator to generate a visual pattern of the descriptor features over time. The apparatus also further includes a speech recognition engine to detect speech based on the generated visual pattern.

Abstract: An electronic device for visual-saliency driven scene description is described. The electronic device includes a property identifier to identify properties of a target platform. The properties include target platform device type and target platform device count. The electronic device also includes a salient region detector to detect a salient region of an input in response to the target platform device type being a graphical processing unit (GPU) and the target platform device count being above one. The electronic device further includes a description provider to provide a fine-grained scene description for the salient region.

Abstract: Systems, apparatuses and methods may provide for training smart objects. More particularly, Systems, apparatuses and methods may provide training smart objects and users to understand actions and commands, using sensors and actuators. Systems, apparatuses and methods may also provide smart objects and users a way to communicate training to other smart objects and users.

Abstract: Methods, apparatus, and systems to create, output, and use animation programs comprising keyframes, objects, object states, and programming elements. Objects, object states, and programming elements may be created through image analysis of image input. Animation programs may be output as videos, as non-linear interactive experiences, and/or may be used to control electronic actuators in articulated armatures.

Abstract: Various systems and methods for frame removal and replacement for stop-action animation are described herein. A system for creating a stop-motion video includes an access module to access a series of frames of an input video, and a processing module to determine whether each frame of the series of frames includes a portion of a hand and composite frames from the series of frames that do not include the portion of the hand to render an output video. A system for creating a video includes an access module to access an input video, and a video processing module to identify a physical object in the input video, track movement of the physical object in the input video to identify a path, identify a three-dimensional model of the physical object, and create an output video with the three-dimensional model in place of the physical object, the three-dimensional model following the path.

Abstract: System, apparatus, method, and computer readable media for on-the-fly captured video summarization. A video stream is incrementally summarized in concurrence with generation of the stream by a camera module. Saliency of the video stream summary is maintained as the stream evolves by updating the summary to include only the most significant frames. In one exemplary embodiment, saliency is determined by optimizing an objective function including terms that are indicative of both the diversity of a selection, and how representative the selection is to the processed portion of the video data corpus. A device platform including a CM and comporting with the exemplary architecture may provide video camera functionality at ultra-low power, and/or with ultra-low storage resources, and/or with ultra-low communication channel bandwidth.

Abstract: System, apparatus, method, and computer readable media for on-the-fly captured video summarization. A video stream is incrementally summarized in concurrence with generation of the stream by a camera module. Saliency of the video stream summary is maintained as the stream evolves by updating the summary to include only the most significant frames. In one exemplary embodiment, saliency is determined by optimizing an objective function including terms that are indicative of both the diversity of a selection, and how representative the selection is to the processed portion of the video data corpus. A device platform including a CM and comporting with the exemplary architecture may provide video camera functionality at ultra-low power, and/or with ultra-low storage resources, and/or with ultra-low communication channel bandwidth.