Rendering is the process of generating 2D images from 3D assets, simulated in a virtual environment, typically with a graphics pipeline. By inverting such renderer, one can think of a learning ...approach to predict a 3D shape from an input image. However, standard rendering pipelines involve a fundamental discretization step called rasterization, which prevents the rendering process to be differentiable, hence suitable for learning. We present the first non-parametric and truly differentiable rasterizer based on silhouettes. Our method enables unsupervised learning for high-quality 3D mesh reconstruction from a single image. We call our framework `soft rasterizer' as it provides an accurate soft approximation of the standard rasterizer. The key idea is to fuse the probabilistic contributions of all mesh triangles with respect to the rendered pixels. When combined with a mesh generator in a deep neural network, our soft rasterizer is able to generate an approximated silhouette of the generated polygon mesh in the forward pass. The rendering loss is back-propagated to supervise the mesh generation without the need of 3D training data. Experimental results demonstrate that our approach significantly outperforms the state-of-the-art unsupervised techniques, both quantitatively and qualitatively. We also show that our soft rasterizer can achieve comparable results to the cutting-edge supervised learning method and in various cases even better ones, especially for real-world data.
In the 'Big Data' era, many real-world applications like search involve the ranking problem for a large number of items. It is important to obtain effective ranking results and at the same time ...obtain the results efficiently in a timely manner for providing good user experience and saving computational costs. Valuable prior research has been conducted for learning to efficiently rank like the cascade ranking (learning) model, which uses a sequence of ranking functions to progressively filter some items and rank the remaining items. However, most existing research of learning to efficiently rank in search is studied in a relatively small computing environments with simulated user queries. This paper presents novel research and thorough study of designing and deploying a Cascade model in a Large-scale Operational E-commerce Search application (CLOES), which deals with hundreds of millions of user queries per day with hundreds of servers. The challenge of the real-world application provides new insights for research: 1). Real-world search applications often involve multiple factors of preferences or constraints with respect to user experience and computational costs such as search accuracy, search latency, size of search results and total CPU cost, while most existing search solutions only address one or two factors; 2). Effectiveness of e-commerce search involves multiple types of user behaviors such as click and purchase, while most existing cascade ranking in search only models the click behavior. Based on these observations, a novel cascade ranking model is designed and deployed in an operational e-commerce search application. An extensive set of experiments demonstrate the advantage of the proposed work to address multiple factors of effectiveness, efficiency and user experience in the real-world application.
Ranking is a fundamental and widely studied problem in scenarios such as search, advertising, and recommendation. However, joint optimization for multi-scenario ranking, which aims to improve the ...overall performance of several ranking strategies in different scenarios, is rather untouched. Separately optimizing each individual strategy has two limitations. The first one is lack of collaboration between scenarios meaning that each strategy maximizes its own objective but ignores the goals of other strategies, leading to a sub-optimal overall performance. The second limitation is the inability of modeling the correlation between scenarios meaning that independent optimization in one scenario only uses its own user data but ignores the context in other scenarios. In this paper, we formulate multi-scenario ranking as a fully cooperative, partially observable, multi-agent sequential decision problem. We propose a novel model named Multi-Agent Recurrent Deterministic Policy Gradient (MA-RDPG) which has a communication component for passing messages, several private actors (agents) for making actions for ranking, and a centralized critic for evaluating the overall performance of the co-working actors. Each scenario is treated as an agent (actor). Agents collaborate with each other by sharing a global action-value function (the critic) and passing messages that encodes historical information across scenarios. The model is evaluated with online settings on a large E-commerce platform. Results show that the proposed model exhibits significant improvements against baselines in terms of the overall performance.
Deep neural networks are increasingly used on mobile devices, where computational resources are limited. In this paper we develop CondenseNet, a novel network architecture with unprecedented ...efficiency. It combines dense connectivity with a novel module called learned group convolution. The dense connectivity facilitates feature re-use in the network, whereas learned group convolutions remove connections between layers for which this feature re-use is superfluous. At test time, our model can be implemented using standard group convolutions, allowing for efficient computation in practice. Our experiments show that CondenseNets are far more efficient than state-of-the-art compact convolutional networks such as MobileNets and ShuffleNets.
Tasks such as search and recommendation have become increas- ingly important for E-commerce to deal with the information over- load problem. To meet the diverse needs of di erent users, person- ...alization plays an important role. In many large portals such as Taobao and Amazon, there are a bunch of di erent types of search and recommendation tasks operating simultaneously for person- alization. However, most of current techniques address each task separately. This is suboptimal as no information about users shared across di erent tasks. In this work, we propose to learn universal user representations across multiple tasks for more e ective personalization. In partic- ular, user behavior sequences (e.g., click, bookmark or purchase of products) are modeled by LSTM and attention mechanism by integrating all the corresponding content, behavior and temporal information. User representations are shared and learned in an end-to-end setting across multiple tasks. Bene ting from better information utilization of multiple tasks, the user representations are more e ective to re ect their interests and are more general to be transferred to new tasks. We refer this work as Deep User Perception Network (DUPN) and conduct an extensive set of o ine and online experiments. Across all tested ve di erent tasks, our DUPN consistently achieves better results by giving more e ective user representations. Moreover, we deploy DUPN in large scale operational tasks in Taobao. Detailed implementations, e.g., incre- mental model updating, are also provided to address the practical issues for the real world applications.
OBJECTIVE: To determine the clinical efficacy and safety of electro-scalp acupuncture in the treatment of patients with acute ischemic stroke. METHODS: Totally 74 patients with acute ischemic stroke ...were enrolled and divided into either body acupuncture (Control) or electro-scalp acupuncture (ESA) groups according to randomized controlled principle. The patients in the control group were given body acupuncture treatment once daily for 28 d, whereas except for the body acupuncture, electro-scalp acupuncture was additional treatment given to the ESA group. Neurological deficits, everyday motor function and muscle strength were evaluated at baseline and the 28th d by NIH Stroke Scale (NIHSS), FugI-Meyer Assessment (FMA) and Modified Barthel Index Score (MBI), respectively. RESULTS: There were not obvious between-group differences in the baseline efficacy parameters (NI- HSS, FMA and MBI) (all P 〉 0.05), whereas signifi- cant between-group differences were found in post-treatment NIHSS, FMA-UE and MBI scores (all P 〈 0.05). After acupuncture treatment, systematic within-group improvements were found in the two groups for any of the efficacy parameters assessed (all P 〈 0.01), and the ESA group showed higher significant improvements in NIHSS, FMA-UE and MBI scores (all P 〈 0.05). CONCLUSION: Electro-scalp acupuncture was efficacious in the treatment of acute ischemic stroke, which resulted in meaningful improvements in neurologic function, motor function and activities of daily living of patients.
Abstract
Two-dimensional semiconductors, including transition metal dichalcogenides, are of interest in electronics and photonics but remain nonmagnetic in their intrinsic form. Previous efforts to ...form two-dimensional dilute magnetic semiconductors utilized extrinsic doping techniques or bulk crystal growth, detrimentally affecting uniformity, scalability, or Curie temperature. Here, we demonstrate an in situ substitutional doping of Fe atoms into MoS
2
monolayers in the chemical vapor deposition growth. The iron atoms substitute molybdenum sites in MoS
2
crystals, as confirmed by transmission electron microscopy and Raman signatures. We uncover an Fe-related spectral transition of Fe:MoS
2
monolayers that appears at 2.28 eV above the pristine bandgap and displays pronounced ferromagnetic hysteresis. The microscopic origin is further corroborated by density functional theory calculations of dipole-allowed transitions in Fe:MoS
2
. Using spatially integrating magnetization measurements and spatially resolving nitrogen-vacancy center magnetometry, we show that Fe:MoS
2
monolayers remain magnetized even at ambient conditions, manifesting ferromagnetism at room temperature.
Human hnRNP A2/B1 is an RNA-binding protein that plays important roles in many biological processes, including maturation, transport, and metabolism of mRNA, and gene regulation of long noncoding ...RNAs. hnRNP A2/B1 was reported to control the microRNAs sorting to exosomes and promote primary microRNA processing as a potential m
A "reader." hnRNP A2/B1 contains two RNA recognition motifs that provide sequence-specific recognition of RNA substrates. Here, we determine crystal structures of tandem RRM domains of hnRNP A2/B1 in complex with various RNA substrates, elucidating specific recognitions of AGG and UAG motifs by RRM1 and RRM2 domains, respectively. Further structural and biochemical results demonstrate multivariant binding modes for sequence-diversified RNA substrates, supporting a RNA matchmaker mechanism in hnRNP A2/B1 function. Moreover, our studies in combination with bioinformatic analysis suggest that hnRNP A2/B1 may mediate effects of m
A through a "m
A switch" mechanism, instead of acting as a direct "reader" of m
A modification.