No abstract

No abstract

In this work, we construct a large-scale dataset for vehicle re-identification (ReID), which contains 137k images of 13k vehicle instances captured by UAV-mounted cameras. To our knowledge, it is the largest UAV-based vehicle ReID dataset. To increase intra-class variation, each vehicle is captured by at least two UAVs at different locations, with diverse view-angles and flight-altitudes. We manually label a variety of vehicle attributes, including vehicle type, color, skylight, bumper, spare tire and luggage rack. Furthermore, for each vehicle image, the annotator is also required to mark the discriminative parts that helps them to distinguish this particular vehicle from others. Besides the dataset, we also design a specific vehicle ReID algorithm to make full use of the rich annotation information. It is capable of explicitly detecting discriminative parts for each specific vehicle and significantly outperforms the evaluated baselines and state-of-the-art vehicle ReID approaches.

a b s t r a c t miR-362-5p is down-regulated in high-risk neuroblastoma and can function as a tumor suppressor. However, its role remains poorly understood. We show that miR-362-5p is down-regulated in metastatic neuroblastoma compared with primary neuroblastoma. Overexpression of miR-362-5p inhibits cell proliferation, migration and invasion of neuroblastoma cells in vitro and suppresses tumor growth of neuroblastoma in vivo. Phosphatidylinositol 3-kinase (PI3K)-C2b is a target of miR-362-5p. Knockdown of PI3K-C2b by siRNA had a similar effect to overexpression of miR-362-5p on SH-SY5Y cells. Overexpression of PI3K-C2b partially reversed tumor-suppressive effects of miR-362-5p. We suggest that miR-362-5p suppresses neuroblastoma cell growth and motility, partially by targeting PI3K-C2b.