3-D Human Pose Estimation Using Iterative Conditional Squeeze and Excitation Networks.

We propose a new method for single-camera real-world 3-D human pose estimation. Our method uses multitask training together with iterative pose refinement using a novel conditional attention mechanism. For iterative pose refinement, the output of each convolutional layer is conditioned on the latest pose estimate, using a conditioned squeeze-and-excitation network architecture that incorporates novel feedback connections. Multitask training on both an in-the-wild 2-D pose dataset and a controlled 3-D pose dataset allows for real-world 3-D pose estimation without the need for a large-scale in-the-wild 3-D pose dataset, which is unavailable. Experiments are performed on several real-world datasets, as well as the Human 3.6 Million and HumanEva-I datasets, to show that the combined attention mechanism, iterative refinement scheme, and multitask training allow us to achieve robust and competitive performance with only a simple network architecture. In addition, we show that our method is efficient enough to run on commodity hardware, producing pose estimates in real time.

Largest Matching Areas for Illumination and Occlusion Robust Face Recognition.

In this paper, we introduce a novel approach to face recognition which simultaneously tackles three combined challenges: (1) uneven illumination; (2) partial occlusion; and (3) limited training data. The new approach performs lighting normalization, occlusion de-emphasis and finally face recognition, based on finding the largest matching area (LMA) at each point on the face, as opposed to traditional fixed-size local areabased approaches. Robustness is achieved with novel approaches for feature extraction, LMA-based face image comparison and unseen data modeling. On the extended YaleB and AR face databases for face identification, our method using only a single training image per person, outperforms other methods using a single training image, and matches or exceeds methods which require multiple training images. On the labeled faces in the wild face verification database, our method outperforms comparable unsupervised methods. We also show that the new method performs competitively even when the training images are corrupted.

Dense Multiperson Tracking with Robust Hierarchical Linear Assignment.

We introduce a novel dual-stage algorithm for online multitarget tracking in realistic conditions. In the first stage, the problem of data association between tracklets and detections, given partial occlusion, is addressed using a novel occlusion robust appearance similarity method. This is used to robustly link tracklets with detections without requiring explicit knowledge of the occluded regions. In the second stage, tracklets are linked using a novel method of constraining the linking process that removes the need for ad-hoc tracklet linking rules. In this method, links between tracklets are permitted based on their agreement with optical flow evidence. Tests of this new tracking system have been performed using several public datasets.

Aldosterone-receptor antagonism and end-stage renal disease.

Blockade of aldosterone effect with either spironolactone or eplerenone is an approach that is being used more frequently in the treatment of hypertension and congestive heart failure; however, sparse information exists pertaining to efficacy or side-effects of this line of treatment for patients with chronic kidney disease and/or end-stage renal disease (ESRD). Hyperkalemia is, by far, the most worrisome complication of therapy with either of these compounds and, not surprisingly, hinders their use in moderate-to-advanced renal failure. However, patients with anuric ESRD should theoretically not be at risk for hyperkalemia. To this end, pilot safety studies with aldosterone-receptor antagonists in ESRD patients have begun. These studies imply that spironolactone can be safely used in carefully selected and closely monitored patients. Eplerenone has not been studied in ESRD in a therapeutic or safety capacity. Additional studies are needed with these compounds in the ESRD population before their use can be considered safe.