We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

/pdf/stacked-hourglass-networks-for-human-pose-estimation-dlf71xnitp.pdf

Stacked Hourglass Networks for Human Pose Estimation

In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

/pdf/the-multimodal-brain-tumor-image-segmentation-benchmark-2gfraj98dk.pdf

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

/pdf/spatial-temporal-graph-convolutional-networks-for-skeleton-1mh8rphegh.pdf

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem. Our large and highly varied training dataset allows the classifier to estimate body parts invariant to pose, body shape, clothing, etc. Finally we generate confidence-scored 3D proposals of several body joints by reprojecting the classification result and finding local modes. The system runs at 200 frames per second on consumer hardware. Our evaluation shows high accuracy on both synthetic and real test sets, and investigates the effect of several training parameters. We achieve state of the art accuracy in our comparison with related work and demonstrate improved generalization over exact whole-skeleton nearest neighbor matching.

/pdf/real-time-human-pose-recognition-in-parts-from-single-depth-16ej02o3m1.pdf

Real-time human pose recognition in parts from single depth images

We propose a new method to quickly and accurately predict human pose---the 3D positions of body joints---from a single depth image, without depending on information from preceding frames. Our approach is strongly rooted in current object recognition strategies. By designing an intermediate representation in terms of body parts, the difficult pose estimation problem is transformed into a simpler per-pixel classification problem, for which efficient machine learning techniques exist. By using computer graphics to synthesize a very large dataset of training image pairs, one can train a classifier that estimates body part labels from test images invariant to pose, body shape, clothing, and other irrelevances. Finally, we generate confidence-scored 3D proposals of several body joints by reprojecting the classification result and finding local modes.The system runs in under 5ms on the Xbox 360. Our evaluation shows high accuracy on both synthetic and real test sets, and investigates the effect of several training parameters. We achieve state-of-the-art accuracy in our comparison with related work and demonstrate improved generalization over exact whole-skeleton nearest neighbor matching.

/pdf/real-time-human-pose-recognition-in-parts-from-single-depth-28r3ot7giz.pdf

We describe two new approaches to human pose estimation. Both can quickly and accurately predict the 3D positions of body joints from a single depth image without using any temporal information. The key to both approaches is the use of a large, realistic, and highly varied synthetic set of training images. This allows us to learn models that are largely invariant to factors such as pose, body shape, field-of-view cropping, and clothing. Our first approach employs an intermediate body parts representation, designed so that an accurate per-pixel classification of the parts will localize the joints of the body. The second approach instead directly regresses the positions of body joints. By using simple depth pixel comparison features and parallelizable decision forests, both approaches can run super-real time on consumer hardware. Our evaluation investigates many aspects of our methods, and compares the approaches to each other and to the state of the art. Results on silhouettes suggest broader applicability to other imaging modalities.

https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/main-39.pdf

Efficient Human Pose Estimation from Single Depth Images

Technology is described for providing realistic occlusion between a virtual object displayed by a head mounted, augmented reality display system and a real object visible to the user's eyes through the display. A spatial occlusion in a user field of view of the display is typically a three dimensional occlusion determined based on a three dimensional space mapping of real and virtual objects. An occlusion interface between a real object and a virtual object can be modeled at a level of detail determined based on criteria such as distance within the field of view, display size or position with respect to a point of gaze. Technology is also described for providing three dimensional audio occlusion based on an occlusion between a real object and a virtual object in the user environment.

Realistic occlusion for a head mounted augmented reality display

A system recognizes human beings in their natural environment, without special sensing devices attached to the subjects, uniquely identifies them and tracks them in three dimensional space. The resulting representation is presented directly to applications as a multi-point skeletal model delivered in real-time. The device efficiently tracks humans and their natural movements by understanding the natural mechanics and capabilities of the human muscular-skeletal system. The device also uniquely recognizes individuals in order to allow multiple people to interact with the system via natural movements of their limbs and body as well as voice commands/responses.

Mark J. Finocchio

Papers

Real-time human pose recognition in parts from single depth images

Real-time human pose recognition in parts from single depth images

Efficient Human Pose Estimation from Single Depth Images

Realistic occlusion for a head mounted augmented reality display

Device for identifying and tracking multiple humans over time