Human life is populated with articulated objects. Current Category-level Articulation Pose Estimation (CAPE) methods are studied under the singleinstance setting with a fixed kinematic structure for each category. Considering these limitations, we reform this problem setting for real-world environments and suggest a CAPE-Real (CAPER) task setting. This setting allows varied kinematic structures within a semantic category, and multiple instances to co-exist in an observation of real world. To support this task, we build an articulated model repository ReArt-48 and present an efficient dataset generation pipeline, which contains Fast Articulated Object Modeling (FAOM) and Semi-Authentic MixEd Reality Technique (SAMERT). Accompanying the pipeline, we build a large-scale mixed reality dataset ReArtMix and a real world dataset ReArtVal. We also propose an effective framework ReArtNOCS that exploits RGB-D input to estimate part-level pose for multiple instances in a single forward pass. Extensive experiments demonstrate that the proposed ReArtNOCS can achieve good performance on both CAPER and CAPE settings. We believe it could serve as a strong baseline for future research on the CAPER task.

No abstract

As one of the major frauds in financial services, cash-out fraud is that users pursue cash gains with illegal or insincere means. Conventional solutions for the cash-out user detection are to perform subtle feature engineering for each user and then apply a classifier, such as GDBT and Neural Network. However, users in financial services have rich interaction relations, which are seldom fully exploited by conventional solutions. In this paper, with the real datasets in Ant Credit Pay of Ant Financial Services Group, we first study the cashout user detection problem and propose a novel hierarchical attention mechanism based cash-out user detection model, called HACUD. Specifically, we model different types of objects and their rich attributes and interaction relations in the scenario of credit payment service with an Attributed Heterogeneous Information Network (AHIN). The HACUD model enhances feature representation of objects through meta-path based neighbors exploiting different aspects of structure information in AHIN. Furthermore, a hierarchical attention mechanism is elaborately designed to model user’s preferences towards attributes and meta-paths. Experimental results on two real datasets show that the HACUD outperforms the state-of-the-art methods.

SWEET genes are a recently identified plant gene family that play an indispensable role in sugar efflux. However, no systematic study has been performed in pear. In this research, 18 SWEET transporters identified in pear, almost twice the number found in woodland strawberry and Japanese apricot, were divided into four clades. Conserved motifs and six exons of the SWEET transporters were found in six species. SWEET transporters contained seven transmembrane segments (TMSs) that evolved from an internal duplication of an ancestral three-TMSs unit, connected by TMS4. This is the first direct evidence identifying internal repeats through bioinformatics analysis. Whole-genome duplication (WGD) or segmental duplication and dispersed duplication represent the main driving forces for SWEET family evolution in six species, with former duplications more important in pear. Gene expression results suggested that PbSWEET15 and PbSWEET17 have no expression in any tissues because of critical lost residues and that 62.5% of PbSWEET duplicate gene pairs have functional divergence. Additionally, PbSWEET6, PbSWEET7 and PbSWEET14 were found to play important roles in sucrose efflux from leaves, and the high expression of PbSWEET1 and PbSWEET2 might contribute to unloading sucrose from the phloem in the stem. Finally, PbSWEET5, PbSWEET9 and PbSWEET10 might contribute to pollen development. Overall, our study provides important insights into the evolution of the SWEET gene family in pear and four other Rosaceae, and the important candidate PbSWEET genes involved in the development of different tissues were identified in pear.

No abstract