Wheat is the third most producing crop in China after maize and rice. In order to enhance the nitrogen use efficiency (NUE) and grain yield of winter wheat, a two-year field experiment was conducted to investigate the effect of different nitrogen ratios and doses at various development stages of winter wheat (Triticum aestivum L.). A total of five N doses (0, N75, N150, N225, and N300 kg ha−1) as main plots and two N ratios were applied in split doses (50%:50% and 60%:40%, referring to 50% at sowing time and 50% at jointing stage, 50% at sowing time + 50% at flowering stage, 50% at sowing time + 50% at grain filling stage, and 60% + 40% N ratio applied as a 60% at sowing time and 40% at jointing stage, 60% at sowing time and 40% at flowering stage, and 60% at sowing time and 40% at grain filling stage in subplots). The results of this study revealed that a nitrogen dose of 225 kg ha−1 significantly augmented the plant height by 27% and above ground biomass (ABG) by 24% at the grain filling stage, and the leaf area was enhanced by 149% at the flowering stage under 60 + 40% ratios. Furthermore, the N225 kg ha−1 significantly prompted the photosynthetic rate by 47% at the jointing and flowering stages followed by grain filling stage compared to the control. The correlation analysis exhibited the positive relationship between nitrogen uptake and nitrogen content, chlorophyll, and dry biomass, revealing that NUE enhanced and ultimately increased the winter wheat yield. In conclusion, our results depicted that optimizing the nitrogen dose (N225 kg/ha−1) with a 60% + 40% ratio at jointing stage increased the grain yield and nitrogen utilization rate.

/pdf/improving-winter-wheat-photosynthesis-nitrogen-use-1jmydps8.pdf

Improving Winter Wheat Photosynthesis, Nitrogen Use Efficiency, and Yield by Optimizing Nitrogen Fertilization

Unsupervised Domain Adaptation Regression (DAR) aims to bridge the domain gap between a labeled source dataset and an unlabelled target dataset for regression problems. Recent works mostly focus on learning a deep feature encoder by minimizing the discrepancy between source and target features. In this work, we present a different perspective for the DAR problem by analyzing the closed-form ordinary least square~(OLS) solution to the linear regressor in the deep domain adaptation context. Rather than aligning the original feature embedding space, we propose to align the inverse Gram matrix of the features, which is motivated by its presence in the OLS solution and the Gram matrix's ability to capture the feature correlations. Specifically, we propose a simple yet effective DAR method which leverages the pseudo-inverse low-rank property to align the scale and angle in a selected subspace generated by the pseudo-inverse Gram matrix of the two domains. We evaluate our method on three domain adaptation regression benchmarks. Experimental results demonstrate that our method achieves state-of-the-art performance. Our code is available at https://github.com/ismailnejjar/DARE-GRAM.

pdf/dare-gram-unsupervised-domain-adaptation-regression-by-2fc3t2zj.pdf

DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices

Robotics education has received widespread attention in K-12 education. Studies have pointed out that in robotics courses, learners face challenges in learning abstract content, such as constructing a robot with a good structure and writing programs to drive a robot to complete specific learning tasks. The present study proposed the embodied learning-based computer programming approach and applied it to the LEGO Mindstorms EV3 robotics course. To evaluate its effectiveness, a quasi-experiment was conducted in one public primary school to explore its effects on students’ learning achievement, learning motivation, learning attitudes, learning engagement, and cognitive load. The experimental group (40 students) adopted the embodied learning-based computer programming approach, while the control group (40 students) adopted the conventional computer programming approach. The results showed that the experimental group had significantly better learning achievement in robotics than the control group, and that there was no significant difference in the cognitive load of the two groups. In terms of learning motivation, although both groups showed improvement, the experimental group had higher intrinsic learning motivation. In addition, the experimental group outperformed the control group with regard to learning attitudes and learning engagement (including cognitive, behavioral, and emotional engagement). Accordingly, this study could contribute to future research for developing more effective robotics teaching approaches and computer programming activity design.

Engaging Young Students in Effective Robotics Education: An Embodied Learning-Based Computer Programming Approach

Conventional appearance-based 3D gaze estimation methods generally use the roll of the head pose to represent the eyeball’s roll status by default. To reduce degrees of freedom of head poses, a normalization step was proposed to apply global transformations to images to make heads upright and eyelids horizontal. However, due to the ocular countering-rolling (OCR) response, the eyeball will rotate in the opposite direction when the head tilts to the side. After normalization, the eyeball will have an extra roll compared to the roll status of the eyeball when the head is not tilted. This roll from the OCR response causes a changed orientation of the eyeball in normalized eye images, which represents the roll status of the anatomical structure inside the eyeball and consequently affects gaze directions. Thus in this work, we propose a pipeline to regress the person-dependent anatomical variation as a calibration process with considering the OCR response, which can work with our proposed eye-image-based person-independent gaze estimator trained with real and synthetic eye images. The proposed method firstly brings the OCR response into the gaze estimation task, achieving better performances on the two benchmark datasets with fewer parameters under the real-time scenarios. With a replacement of a deeper network, compared to state-of-the-art methods, the proposed method is more efficient, achieving a). better average estimate (3.9% and 2.5% improvement), b). much better standard deviation (lower by 59.0% and 44.2%) and c). a much lower number of parameters (reduced by 88.0%). 

Kappa Angle Regression with Ocular Counter-Rolling Awareness for Gaze Estimation

Head pose estimation plays a vital role in biometric systems related to facial and human behavior analysis. Typically, neural networks are trained on head pose datasets. Unfortunately, manual or sensor-based annotation of head pose is impractical. A solution is synthetic training data generated from 3D face models, which can provide an infinite number of perfect labels. However, computer generated images only provide an approximation of real-world images, leading to a performance gap between training and application domain. Therefore, there is a need for strategies that allow simultaneous learning on labeled synthetic data and unlabeled real-world data to overcome the domain gap. In this work we propose relative pose consistency, a semi-supervised learning strategy for head pose estimation based on consistency regularization. Consistency regularization enforces consistent network predictions under random image augmentations, including pose-preserving and pose-altering augmentations. We propose a strategy to exploit the relative pose introduced by pose-altering augmentations between augmented image pairs, to allow the network to benefit from relative pose labels during training on unlabeled data. We evaluate our approach in a domain-adaptation scenario and in a commonly used cross-dataset scenario. Furthermore, we reproduce related works to enforce consistent evaluation protocols and show that for both scenarios we outperform SOTA. 

Domain Adaptation for Head Pose Estimation Using Relative Pose Consistency

Planting rice (OryzasativaL.) is an effective and feasible approach for improving salt-affected soils, especially in saline-sodic soils. Improved rice is the main biological measure for rapid treatment and utilization of a saline-sodic paddy field. Reasonable application of nitrogen fertilizer is an important measure for obtaining saline-sodic soil high yield. Dongdao 4 (D-4), Dongdao 2 (D-2), Changbai 9 (C-9), and Baijing 1 (B-1)) were studied by a field experiment in this paper. On the growth, yield, and yield component responses of different nitrogen levels (150 kg N/ha, 225 kg N/ha and 300 kg N/ha), and the nitrogen uptake of four saline-tolerant rice cultivars at different nitrogen application levels was calculated, which provided a useful reference for the rational application of nitrogen fertilizer in a salinesodic paddy field. The results showed that: biomass of four kinds of rice accumulates over time and reached their maximums in September, with the biomasses of D-2 and D-4 reaching the maximum of 225 kg N/ha, and C-9 and B-1 reaching the maximum at 300 kg N/ha, which is related to rice varieties; the yields of four salt-tolerant rice plants reached the highest in 150 kg N/ha; applied nitrogen fertilizer reasonably was beneficial to increase the number of spikes and the number of effective grains per spike, in this experiment, the optimum amount of nitrogen is 150 kg N/ha, and the number of spikes and the number of effective grains per spike also were major factors in increasing production. With 1000-grain weight, primary and secondary branches made no significant contribution to the yield; the N uptake of four kinds of rice gradually increased over time and reached the maximum in September. There was no significant difference in the nitrogen grain production efficiency of 4 rice varieties under different nitrogen application rates; with the increase of nitrogen application rate, partial productivity of nitrogen fertilizer *e-mail: baoyiweicas@163.com DOI: 10.15244/pjoes/85203 ONLINE PUBLICATION DATE: 2018-08-31

http://www.pjoes.com/pdf-85203-32452?filename=How Different Nitrogen.pdf

How Different Nitrogen Application RatesAffect Yield Composition and Nitrogen Uptakeof Rice (Oryza sativa L.) in a Saline-SodicPaddy Field

Deep neural networks have demonstrated superior perfor- mance on appearance-based gaze estimation tasks. However, due to variations in person, illuminations, and background, performance degrades dramatically when applying the model to a new domain. In this paper, we discover an interesting gaze jitter phenomenon in cross-domain gaze estimation, i.e. , the gaze predictions of two similar images can be severely deviated in target domain. This is closely related to cross-domain gaze estimation tasks, but surprisingly, it has not been noticed yet previously. Therefore, we innovatively propose to utilize the gaze jitter to analyze and optimize the gaze domain adaptation task. We ﬁnd that the high-frequency component (HFC) is an important factor that leads to jitter. Based on this discovery, we add high-frequency components to input images using the adversarial attack and employ contrastive learning to encourage the model to obtain similar representa-tions between original and perturbed data, which reduces the impacts of HFC. We evaluate the proposed method on four cross-domain gaze estimation tasks, and experimental results demonstrate that it signiﬁcantly reduces the gaze jitter and improves the gaze estimation performance in target domains.

pdf/jitter-does-matter-adapting-gaze-estimation-to-new-domains-mf3078qs.pdf

Jitter Does Matter: Adapting Gaze Estimation to New Domains

Robot illustrated: Exploring elementary students’ perceptions of robots via the draw-a-robot test

This study explored elementary school students' perceptions of robots via drawing analysis. A total of 100 sixth graders from China participated in this Draw-a-robot Test. A coding checklist with four categories and forty-two subcategories was developed to analyze the features of students' drawings. Data analysis reveals: (1) both male and female students in sixth grade depicted special robots most frequently rather than industry robots; (2) the most common activities robots did were doing housework or navigating/guiding; (3) more than half of the drawings did not have any people involved; (4) the robots were mostly located at home or restaurant/canteen; (5) there was also a difference in the depiction of features of different categories between male and female students' drawings. The findings yielded in this study have practical implications for the development and implementation of future robot education outreach efforts.

Exploring Elementary Students’ Perceptions of Robots: The Draw-A-Robot Test

Although recent deep learning based gaze estimation approaches have achieved much improvement, we still know little about how gaze features are connected to the physics of gaze. In this paper, we try to answer this question by analyzing the gaze feature manifold. Our analysis revealed the insight that the geodesic distance between gaze features is consistent with the gaze differences between samples. According to this finding, we construct the Physics- Consistent Feature (PCF) in an analytical way, which connects gaze feature to the physical definition of gaze. We further propose the PCFGaze framework that directly optimizes gaze feature space by the guidance of PCF. Experimental results demonstrate that the proposed framework alleviates the overfitting problem and significantly improves cross-domain gaze estimation accuracy without extra training data. The insight of gaze feature has the potential to benefit other regression tasks with physical meanings.

pdf/pcfgaze-physics-consistent-feature-for-appearance-based-gaze-3gcz3cjhc3.pdf

PCFGaze: Physics-Consistent Feature for Appearance-based Gaze Estimation

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Yiwei Bao

Author Tools

Chat about Author