Crowd counting still confronts two primary challenges: limited ability to deal with cross density levels caused by fixed density maps and lack of fine-grained or coarse-grained guidance for density estimation. In this paper, a novel end-to-end crowd counting framework via multi-level regression with latent Gaussian maps is proposed, which is consisted of GaussianNet, EstimateNet and Discriminator. GaussianNet is composed of masked Gaussian convolutional blocks and vanillia convolutional layers, to generate latent Gaussian maps adaptively for various density levels. The latent Gaussian maps are then treated as the ground truth density maps for EstimateNet, which outputs density estimations and follows the principle of adversarial learning with Discriminator. Moreover, multi-level losses are combined for density map regression guidance. Extensive experiments on the major public datasets outperform state-of-the-art ones, illustrating the superior validity of the proposed framework.
Caerulomycin H (2) and its 4-yl α-L-rhamnopyranoside [cyanogriside K (1)] are two microbial natural products from marine-derived Actinoalloteichus cyanogriseus WH1-2216-6. Cyanogriside K (1) shows good antiproliferative activity against tumor cells, whereas the yield is very low and the synthesis has not been reported. Thus, enough caerulomycin H (2) was first obtained by optimazing the fermentation condition of the mutant strain CRM05 of A. cyanogriseus WH1-2216-6. The yield of caerulomycin H (2) reached 272 mg/L (increased by 5 times) in the optimal solid medium consisted of corn pellets (80 g) and liqiud medium 5# for actinomycetes (100 mL). Then cyanogriside K (1) was synthesized with 25.6% total yield from caerulomycin H (2) by six steps reactions including deoximation, rhamnosylation, oximation and deacetylation. The structure of cyanogriside K (1) was identified by NMR, HRESIMS and specific rotation data. It is the same compound as the reported natural product. Furthermore, cyanogriside K (1) showed good bioactivity against the proliferation of the tumor cell lines PA-TU8988T, 786-O, 5673, DU145, A-375, FaDu and SF126, with the half maximal inhibitory concentration (IC50) values ranging from 1.07 μmol/L to 1.78 μmol/L.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.