Bias-Compensated Integral Regression for Human Pose Estimation.

In human and hand pose estimation, heatmaps are a crucial intermediate representation for a body or hand keypoint. Two popular methods to decode the heatmap into a final joint coordinate are via an argmax, as done in heatmap detection, or via softmax and expectation, as done in integral regression. Integral regression is learnable end-to-end, but has lower accuracy than detection. This paper uncovers an induced bias from integral regression that results from combining the softmax and the expectation operation. This bias often forces the network to learn degenerately localized heatmaps, obscuring the keypoint's true underlying distribution and leads to lower accuracies. Training-wise, by investigating the gradients of integral regression, we show that the implicit guidance of integral regression to update the heatmap makes it slower to converge than detection. To counter the above two limitations, we propose Bias Compensated Integral Regression (BCIR), an integral regression-based framework that compensates for the bias. BCIR also incorporates a Gaussian prior loss to speed up training and improve prediction accuracy. Experimental results on both the human body and hand benchmarks show that BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.

WSF-7 Inhibits Obesity-Mediated PPARγ Phosphorylation and Improves Insulin Sensitivity in 3T3-L1 Adipocytes.

Peroxisome proliferator-activated receptor γ (PPARγ), the molecular target for antidiabetic thiazolidinediones (TZDs), is a master regulator of preadipocyte differentiation and lipid metabolism. The adverse side effects of TZDs, arising from their potent agonistic activity, can be minimized by PPARγ partial agonists or PPARγ non-agonists without loss of insulin sensitization. In this study, we reported that WSF-7, a synthetic chemical derived from natural monoterpene α-pinene, is a partial PPARγ agonist. We found that WSF-7 binds directly to PPARγ. Activation of PPARγ by WSF-7 promotes adipogenesis, adiponectin oligomerization and insulin-induced glucose uptake. WSF-7 also inhibits obesity-mediated PPARγ phosphorylation at serine (Ser)273 and improves insulin sensitivity of 3T3-L1 adipocytes. Our study suggested that WSF-7 activates PPARγ transcription by a mechanism different from that of rosiglitazone or luteolin. Therefore, WSF-7 might be a potential therapeutic drug to treat type 2 diabetes.