Abstract: Methods and systems for estimation of a 3D hand pose are disclosed. A 2D image containing a detected hand is processed using a U-net network to obtain a global feature vector and a heatmap for the keypoints of the hand. Information from the global feature vector and the heatmap are concatenated to obtain a set of input tokens that are processed using a transformer encoder to obtain a first set of 2D keypoints representing estimated 2D locations of the keypoints in a first view. The first set of 2D keypoints are inputted as a query to a transformer decoder, to obtain a second set of 2D keypoints representing estimated 2D locations of the keypoints in a second view. The first and second sets of 2D keypoints are aggregated to output the set of estimated 3D keypoints.

Abstract: Methods and systems for estimation of a 3D hand pose are disclosed. A 2D image containing a detected hand is processed using a U-net network to obtain a global feature vector and a heatmap for the keypoints of the hand. Information from the global feature vector and the heatmap are concatenated to obtain a set of input tokens that are processed using a transformer encoder to obtain a first set of 2D keypoints representing estimated 2D locations of the keypoints in a first view. The first set of 2D keypoints are inputted as a query to a transformer decoder, to obtain a second set of 2D keypoints representing estimated 2D locations of the keypoints in a second view. The first and second sets of 2D keypoints are aggregated to output the set of estimated 3D keypoints.

Abstract: An integrated circuit includes laterally adjacent first and second devices. The first device includes a first source or drain region, a first gate structure, and a first inner spacer between the first source or drain region and the first gate structure. The second device includes a second source or drain region, a second gate structure, and a second inner spacer between the second source or drain region and the second gate structure. In an example, the first source or drain region has a width that is at least 1 nanometer different from a width of the second source or drain region, and/or the first inner spacer has a width that is at least 1 nanometer different from a width of the second inner spacer.

Abstract: Systems and methods for temporal action localization of video data are described. A feature representation extracted from video data has a temporal dimension and a spatial dimension. The feature representation is self-aligned in the spatial dimension. Spatial multi-sampling is performed to obtain a plurality of sparse samples of the self-aligned representation along the spatial dimension, and the multi-sampled representation is fused with the self-aligned representation. Attention-based context information aggregation is applied on the fused representation to obtain a spatially refined representation. Local temporal information aggregation is applied on the self-aligned representation to obtain a temporally refined representation. Action localization is performed on a concatenation of the spatially refined representation and the temporally refined representation.

Abstract: Systems, methods, and computer media of processing a video are disclosed. An example method may include: receiving a plurality of video frames of a video; generating a plurality of first input features based on the plurality of video frames; generating a plurality of second input features based on reversing a temporal order of the plurality of first input features; generating a first set of joint attention features based on the plurality of first input features; generating a second set of joint attention features based on the plurality of second input features; and concatenating the first set of joint attention features and the second set of joint attention features to generate a final set of joint attention features.

Abstract: Methods, devices and processor-readable media for an integrated teacher-student machine learning system. One or more teacher-student modules are trained as part of the teacher neural network training. Each student sub-network uses a portion of the teacher neural network to generate an intermediate feature map, then provides the intermediate feature map to a student sub-network to generate inferences. The student sub-network may use a feature enhancement block to map the intermediate feature map to a subsequent feature map. A compression block may be used to compress intermediate feature map data for transmission in some embodiments.

Abstract: The present invention relates to antimicrobial compositions comprising graphene-silver cation nanocomposites and uses for same as an antimicrobial agent. The antimicrobial agent is particularly useful as a disinfectant or for use as a coating to confer antimicrobial activity to a substrate. The antimicrobial agent can further be used to enhance filtration efficiency in PPE, face masks, and filters in air filtration (HVAC) systems, and other airflow membranes and filters to reduce the transmission of microbial pathogens.

Abstract: Methods and devices are described for computer vision-based gesture detection. From a frame of image data, extracted locations of keypoints of a detected hand are obtained. The extracted locations are normalized to obtain normalized features. The normalized features are processed using a trained decision tree ensemble to generate a probability of a valid gesture for the detected hand. The generated probability is compared with a defined decision threshold to generate a binary classification to classify the detected hand as a valid gesture or invalid gesture.

Abstract: Methods and devices for machine vision-based selection of content are described. One or more hands are detected in a current frame of video data. A respective fingertip location is determined for each of up to two of the detected hands. A content selection gesture is determined corresponding to the up to two detected hands. Selected content is extracted, as indicated by the content selection gesture and based on the up to two fingertip locations. The device may be a smartphone, a tablet, a laptop, a smart light device, a reader device, etc.

Abstract: Method and devices for training a keypoint estimation network are described. In each training iteration, synthetic images are generated by a generator, each synthetic image being assigned respective assigned keypoints by the generator. Using a prior-iteration of the keypoint estimation network, a set of predicted keypoints is obtained for each synthetic image. Based on an error score between the predicted keypoints and the assigned keypoints, poor quality synthetic images are discarded. The remaining synthetic images, together with real world images, are used to train an updated keypoint estimation network. The performance of the updated keypoint estimation network is validated, and the training iterations are performed until a convergence criteria is satisfied.

Abstract: Methods and systems are described for performing video retrieval together with video grounding. A word-based query for a video is and encoded into a query representation using a trained query encoder. One or more similar video representations are identified, from a plurality of video representations that are similar to the query representation. Each similar video representation represents a respective relevant video. A grounding is generated for each relevant video by forward propagating each respective similar video representation together with the query representation through a trained grounding module. The relevant videos or identifiers of the relevant videos are outputted together with the grounding generated for each relevant video.

Abstract: Methods and systems are described for performing video retrieval together with video grounding. A word-based query for a video is and encoded into a query representation using a trained query encoder. One or more similar video representations are identified, from a plurality of video representations that are similar to the query representation. Each similar video representation represents a respective relevant video. A grounding is generated for each relevant video by forward propagating each respective similar video representation together with the query representation through a trained grounding module. The relevant videos or identifiers of the relevant videos are outputted together with the grounding generated for each relevant video.

Abstract: Systems, methods, and computer media of processing a video are disclosed. An example method may include: receiving a plurality of video frames of a video; generating a plurality of first input features based on the plurality of video frames; generating a plurality of second input features based on reversing a temporal order of the plurality of first input features; generating a first set of joint attention features based on the plurality of first input features; generating a second set of joint attention features based on the plurality of second input features; and concatenating the first set of joint attention features and the second set of joint attention features to generate a final set of joint attention features.

Abstract: Methods, devices and processor-readable media for an integrated teacher-student machine learning system. One or more teacher-student modules are trained as part of the teacher neural network training. Each student sub-network uses a portion of the teacher neural network to generate an intermediate feature map, then provides the intermediate feature map to a student sub-network to generate inferences. The student sub-network may use a feature enhancement block to map the intermediate feature map to a subsequent feature map. A compression block may be used to compress intermediate feature map data for transmission in some embodiments.

Abstract: In accordance with one embodiment of the present disclosure, an oxygen carrying material may include a primary active mass, a primary support material, and a secondary support material. The oxygen carrying material may include about 20% to about 70% by weight of the primary active mass, the primary active mass including a composition having a metal or metal oxide selected from the group consisting of Fe, Co, Ni, Cu, Mo, Mn, Sn, Ru, Rh, and combinations thereof. The oxygen carrying material may include about 5% to about 70% by weight of a primary support material. The oxygen carrying material may include about 1% to about 35% by mass of a secondary support material.

Abstract: In accordance with one embodiment of the present disclosure, an oxygen carrying material may include a primary active mass, a primary support material, and a secondary support material. The oxygen carrying material may include about 20% to about 70% by weight of the primary active mass, the primary active mass including a composition having a metal or metal oxide selected from the group consisting of Fe, Co, Ni, Cu, Mo, Mn, Sn, Ru, Rh, and combinations thereof. The oxygen carrying material may include about 5% to about 70% by weight of a primary support material. The oxygen carrying material may include about 1% to about 35% by mass of a secondary support material.

Abstract: In accordance with one embodiment of the present disclosure, an oxygen carrying material may include a primary active mass, a primary support material, and a secondary support material. The oxygen carrying material may include about 20% to about 70% by weight of the primary active mass, the primary active mass including a composition having a metal or metal oxide selected from the group consisting of Fe, Co, Ni, Cu, Mo, Mn, Sn, Ru, Rh, and combinations thereof. The oxygen carrying material may include about 5% to about 70% by weight of a primary support material. The oxygen carrying material may include about 1% to about 35% by mass of a secondary support material.

Abstract: High efficiency electricity generation processes and systems with substantially zero CO2 emissions are provided. A closed looping between the unit that generates gaseous fuel (H2, CO, etc) and the fuel cell anode side is formed. In certain embodiments, the heat and exhaust oxygen containing gas from the fuel cell cathode side are also utilized for the gaseous fuel generation. The systems for converting fuel may comprise reactors configured to conduct oxidation-reduction reactions. The resulting power generation efficiencies are improved due to the minimized steam consumption for the gaseous fuel production in the fuel cell anode loop as well as the strategic mass and energy integration schemes.

Abstract: High efficiency electricity generation processes and systems with substantially zero CO2 emissions are provided. A closed looping between the unit that generates gaseous fuel (H2, CO, etc) and the fuel cell anode side is formed. In certain embodiments, the heat and exhaust oxygen containing gas from the fuel cell cathode side are also utilized for the gaseous fuel generation. The resulting power generation efficiencies are improved due to the minimized steam consumption for the gaseous fuel production in the fuel cell anode loop as well as the strategic mass and energy integration schemes.

Abstract: In accordance with one embodiment of the present disclosure, an oxygen carrying material may include a primary active mass, a primary support material, and a secondary support material. The oxygen carrying material may include about 20% to about 70% by weight of the primary active mass, the primary active mass including a composition having a metal or metal oxide selected from the group consisting of Fe, Co, Ni, Cu, Mo, Mn, Sn, Ru, Rh, and combinations thereof. The oxygen carrying material may include about 5% to about 70% by weight of a primary support material. The oxygen carrying material may include about 1% to about 35% by mass of a secondary support material.