Abstract: Padded materials and corresponding systems and methods for forming the same are provided herein. A padded material comprises a first web of paper-based material defining a first and a second surface, and a second web of paper-based material defining a first and a second surface. The padded material defines a plurality of consecutive panel sections formed of a first edge, a second edge, a first panel breakline and a second panel breakline. A first adhesive is positioned between corresponding portions of the first web and the second web. A starch-based padding is sandwiched between the first web and the second web with a second adhesive. The starch-based padding defines a non-uniform placement density along the first web between 15%-40%. The placement density is the ratio of area covered by the starch-based particles to the web area defined between the first edge, second edge, first panel breakline, and second panel breakline.

Abstract: A computer-implemented method for recovering a three-dimensional (3D) mesh of N humans in a 3D scene, includes: receiving a two-dimensional (2D) image of the scene captured by an image capturing device, the 2D image including a plurality of regions; by one or more processors, encoding the received image and extracting features for each of the plurality of regions; by one or more processors, detecting the N humans in N respective regions among the plurality of regions; by one or more processors, based on the features in the N respective regions and the features for each of the plurality of regions, determining distribution parameters for distributions of body model and depth parameters for each of the N detected humans using a probabilistic network; providing the distribution parameters for the body model parameters for each of the N detected humans to a 3D parametric model for generating N 3D meshes.

Abstract: Padded materials and corresponding systems and methods for forming the same are provided herein. A padded material comprises a first web of paper-based material defining a first and a second surface, and a second web of paper-based material defining a first and a second surface. The padded material defines a plurality of consecutive panel sections formed of a first edge, a second edge, a first panel breakline and a second panel breakline. A first adhesive is positioned between corresponding portions of the first web and the second web. A starch-based padding is sandwiched between the first web and the second web with a second adhesive. The starch-based padding defines a non-uniform placement density along the first web between 15%-40%. The placement density is the ratio of area covered by the starch-based particles to the web area defined between the first edge, second edge, first panel breakline, and second panel breakline.

Abstract: A method includes: performing unsupervised pre-training of a model, the model including and a decoder including: obtaining a first image and a second image under different conditions or from different viewpoints; encoding, by the encoder, the first image into a representation of the first image and the second image into a representation of the second image; transforming the representation of the first image into a transformed representation; decoding, by the decoder, the transformed representation into a reconstructed image, where the transforming of the representation of the first image and the decoding of the transformed representation is based on the representation of the first image and the representation of the second image; and adjusting one or more parameters of at least one of the encoder and the decoder based on minimizing a loss; and fine-tuning the model, initialized with a set of task specific encoder parameters, for a geometric vision task.

Abstract: A method for training a model for generating a representation of long-term motion from a text input comprises: training a motion encoder of an autoencoder to compress and map an input motion into a latent representation comprising a sequence of latent vectors in a discrete latent space, each latent vector representing a fixed length of motion; training a quantization module to quantize the latent vectors to a sequence of quantized latent vectors in quantized latent space; and training a motion decoder to reconstruct the quantized sequence as a sequence of single-frame pose representations. A text encoder is trained to predict a latent sequence conditioned on a text input and a duration using the mapped latent representation as a target.

Abstract: A method for recovering a 3D mesh of N humans in a 3D scene comprises: encoding a 2D image from an image capturing device to extract embedded features for each of a plurality of regions; detecting N humans in N respective regions among the plurality of regions; processing the embedded features in the N respective regions and the embedded features for each of the plurality of regions to predict body model and depth parameters using a decoder comprising a cross-attention module; providing the predicted body model parameters to a 3D parametric model for generating 3D meshes; and placing the generated 3D meshes at respective 3D spatial locations based on the predicted depth parameters.

Abstract: A motion generation system includes: a model configured to generate a rendering of a human performing an action in a space, the model including: an encoder module configured to encode input into encodings; a prediction module configured to generate predicted trajectories of the human performing the action based on the encodings using a latent space; a decoder module configured to generate decodings based on the predicted trajectories; and a rendering module configured to generate the rendering based on the decodings; and a training module configured to: (a) train the model based on input video including humans performing actions; and (b), after (a), train the model based on geometry of a scene, one or more target actions for performance by a human in the scene, and observations of the human during performance of the one or more target actions in the scene.

Abstract: A training system includes: a transformer module having the transformer architecture and configured to perform a vision task; and a training module configured to: receive a training image having a predetermined resolution; determine N windows of tokens of pixels in the training image and mask the tokens of all of the other pixels of the training image that are outside of the N windows, where N is an integer greater than or equal to 2; input the N windows of tokens to the transformer module; train the transformer module based on an output of the transformer module generated based on the N windows of tokens; and test the transformer module using a test image having the predetermined resolution.

Abstract: A training system includes: an iterative attention module configured to, based on first features in input images, determine ordered sets of second features using iterative attention over T iterations, where T is an integer greater than or equal to two; and a training module configured to: selectively input pairs of matching images to the iterative attention module; selectively input non-matching images to the iterative attention module; and based on the ordered sets generated by the iterative attention module based on the input pairs of matching images and the input non-matching images, train the iterative attention module based on minimizing at least one of: a contrastive loss; and a cosine similarity loss.

Abstract: A method and system for automatically building a three-dimensional pose dataset for use in text to pose retrieval or text to pose generation for a class of poses includes (a) inputting three-dimensional keypoint coordinates of class-centric poses; (b) extracting, from the inputted three-dimensional keypoint coordinates of class-centric poses, posecodes, the posecodes representing a relation between a specific set of joints; (c) selecting extracted posecodes to obtain a discriminative description; (d) aggregating selected posecodes that share semantic information; (e) converting the aggregated posecodes by electronically obtaining individual descriptions by plugging each posecode information into one template sentence, picked at random from a set of possible templates for a given posecode category; (f) concatenating the individual descriptions in random order, using random pre-defined transitions; and (g) mapping the concatenated individual descriptions to class-centric poses to create the three-dimensional po

Abstract: Am image retrieval system includes: a neural network (NN) module configured to generate local features based on an input image; an iterative attention module configured to, via T iterations, generate an ordered set of super features in the input image based on the local features, where T is an integer greater than 1; and a selection module configured to select a second image from a plurality of images in an image database based on the second image having a second ordered set of super features that most closely match the ordered set of super features in the input image, where the super features in the set of super features do not include redundant local features of the input image.

Abstract: Padded materials and corresponding systems and methods for forming the same are provided herein. A padded material comprises a first web of paper-based material defining a first and a second surface, and a second web of paper-based material defining a first and a second surface. The padded material defines a plurality of consecutive panel sections formed of a first edge, a second edge, a first panel breakline and a second panel breakline. A first adhesive is positioned between corresponding portions of the first web and the second web. A starch-based padding is sandwiched between the first web and the second web with a second adhesive. The starch-based padding defines a non-uniform placement density along the first web between 15%-40%. The placement density is the ratio of area covered by the starch-based particles to the web area defined between the first edge, second edge, first panel breakline, and second panel breakline.

Abstract: A training system includes: a model; and a training module configured to: construct a first pair of images of at least a first portion of a first human captured at different times; construct a second pair of images of at least a second portion of a second human captured at the same time from different points of view; input the first and second pairs of images to the model; the model configured to: generate first and second reconstructed images of the at least the first portion of the first human based on the first and second pairs, respectively, and the training module is configured to selectively adjust one or more parameters of the model based on: the first reconstructed image and the second reconstructed image.

Abstract: A method includes: performing unsupervised pre-training of a model, the model including and a decoder including: obtaining a first image and a second image under different conditions or from different viewpoints; encoding, by the encoder, the first image into a representation of the first image and the second image into a representation of the second image; transforming the representation of the first image into a transformed representation; decoding, by the decoder, the transformed representation into a reconstructed image, where the transforming of the representation of the first image and the decoding of the transformed representation is based on the representation of the first image and the representation of the second image; and adjusting one or more parameters of at least one of the encoder and the decoder based on minimizing a loss; and fine-tuning the model, initialized with a set of task specific encoder parameters, for a geometric vision task.

Abstract: A motion generation system includes: a model configured to generate latent indices for a sequence of images including an entity performing an action based on an action label and a duration of the sequence; and a decoder module configured to: decode the latent indices and to generate the sequence of images including the entity performing the action based on the latent indices; and output the sequence of images including the entity performing the action to a display control module configured to display the sequence of images including the entity performing the action sequentially on a display.

Abstract: Padded materials and corresponding systems and methods for forming the same are provided herein. A padded material comprises a first web of paper-based material defining a first and a second surface, and a second web of paper-based material defining a first and a second surface. A first layer of heat seal coating is disposed on the second surface of the first web, and a second layer of heat seal coating is disposed on the second surface of the second web. A starch-based padding is sandwiched between the first web and the second web such that the starch-based padding is positioned between the first surface of the first web and the second layer of heat seal coating disposed on the second surface of the second web. The padded material may be formed into a roll stock that is used in an automated packaging machine, such as an automated mailer formation device.

Abstract: Am image retrieval system includes: a neural network (NN) module configured to generate local features based on an input image; an iterative attention module configured to, via T iterations, generate an ordered set of super features in the input image based on the local features, where T is an integer greater than 1; and a selection module configured to select a second image from a plurality of images in an image database based on the second image having a second ordered set of super features that most closely match the ordered set of super features in the input image, where the super features in the set of super features do not include redundant local features of the input image.

Abstract: A method of semi-supervised learning includes inputting an image; generating a weak augmentation version and a strong augmentation version of the inputted image; predicting a class of the weak augmentation version of the inputted image; determining if the predicted class of the weak augmentation version of the inputted image is confident; using a pseudo-label to train a model using the strong augmentation version of the inputted image when the predicted class of the weak augmentation version of the selected image is confident; and using a self-supervised loss based on deep clustering to train a model using the strong augmentation version of the selected image when the predicted class of the weak augmentation version of the selected image is not confident.

Abstract: A method of producing an engineered T cell population includes obtaining a cell population comprising a CD8+ T cell, isolating the CD8+ T cell from the obtained cell population, activating the isolated CD8+ T cell, introducing a nucleic acid encoding a T cell receptor (TCR) binding to an antigen in a complex with an MHC molecule into the activated CD8+ T cell, and expanding the introduced CD8+ T cell to obtain the engineered T cell population.

Abstract: A peripheral bracket member provided in conjunction with a liner-type pool, having a body whose outwardly facing surface directly substantially engages, and has a contour that substantially conforms to the contour of the inwardly facing surface of the pool wall and which is mounted on the pool wall to form a border adjacent to the top of the pool wall. A channel structure extends along a lower region of the inwardly facing surface of the bracket body at a level below the normal water line of the pool which receives and holds a bead provided at the liner edge. An elongate cap is affixed to the bead-receiving bracket structure. The tile and bracket structure also provides aesthetic junctions with and secure watertight seals at the skimmer openings and other pool wall terminations such as stairs and wall ladders.