A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Modeling of Personalized Anatomy using Plastic Strains
[article]
2020
arXiv
pre-print
Preserved Fulltext
Example
6m
3(q + r + t) t pr ep
CG
Ours
Hand muscle 237,954
1,143
17.5s 897.5s
9.5s
Hip bone
172,440
1,497
11.4s 408.9s
7.2s
Liver
259,326
1,272
24.4s 1486.7s 10.0s
• Bohan Wang ...
We obtained the scan and the already extracted bone meshes from [Wang et al. 2019 ]; scan resolution is 0.5mm x 0.5mm x 0.5mm . ...
arXiv:2008.00579v1
fatcat:jqrv5ykosfavxjrjadkwa6orwm
Visual Tracking via Shallow and Deep Collaborative Model
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In [23] , Wang
Bayesian interference framework In this paper, object tracking is carried out within the Bayesian inference framework. ...
arXiv:1607.08040v1
fatcat:rtxzdb7jcjgfjbr4paax2in6be
Cinnabar Induces Renal Inflammation and Fibrogenesis in Rats
2015
BioMed Research International
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The purpose of this study was to investigate whether cinnabar causes renal inflammation and fibrosis in rats. Rats were dosed orally with cinnabar (1 g/kg/day) for 8 weeks or 12 weeks. The control rats were treated with solvent (5% carboxymethylcellulose solution) over the same time periods, respectively. Renal mercury (RHg), urinary mercury (UHg), serum creatinine (SCr), urine kidney injury molecule 1 (KIM-1), renal pathology, and renal mediators were examined. At both 8 weeks and 12 weeks,
doi:10.1155/2015/280958
pmid:25734058
pmcid:PMC4334861
fatcat:b2ujmbqb6bhlzihchjlrcawaei
more »
... , UHg, and urine KIM-1 were significantly higher in the cinnabar group than in the control group, although SCr was unchanged. Kidney lesions in the cinnabar-treated rats occurred mainly in the tubules and interstitium, including vacuolization, protein casts, infiltration of inflammatory cells, and slight increase in interstitial collagen. In addition, mild mesangial proliferation was observed in glomeruli. Moreover, the expression of inflammatory and fibrogenic mediators was upregulated in the cinnabar group. In conclusion, cinnabar may cause kidney damage due to the accumulation of mercury, and renal inflammation and slight fibrogenesis may occur in rats. In the clinic, the potential risk of renal injury due to the prolonged consumption of cinnabar should be considered even though the agent is relatively nontoxic.
Supplementary document for Epicenter localization using forward-transmission laser interferometry - 5825074.pdf
2022
figshare.com
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Supplement 1
doi:10.6084/m9.figshare.20060081.v2
fatcat:ggsblof5vjhathmsyl7s7l7mi4
Supplementary document for Epicenter localization using forward-transmission laser interferometry - 5825074.pdf
2022
figshare.com
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Supplement 1
doi:10.6084/m9.figshare.20060081.v1
fatcat:7hwrhy2oovevxdyv2hwc75epdm
Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Uncertainty modeling is critical in trajectory forecasting systems for both interpretation and safety reasons. To better predict the future trajectories of multiple agents, recent works have introduced interaction modules to capture interactions among agents. This approach leads to correlations among the predicted trajectories. However, the uncertainty brought by such correlations is neglected. To fill this gap, we propose a novel concept, collaborative uncertainty(CU), which models the
arXiv:2110.13947v1
fatcat:gyrsmatnovfkjfsyoeozikjthm
more »
... nty resulting from the interaction module. We build a general CU-based framework to make a prediction model to learn the future trajectory and the corresponding uncertainty. The CU-based framework is integrated as a plugin module to current state-of-the-art (SOTA) systems and deployed in two special cases based on multivariate Gaussian and Laplace distributions. In each case, we conduct extensive experiments on two synthetic datasets and two public, large-scale benchmarks of trajectory forecasting. The results are promising: 1) The results of synthetic datasets show that CU-based framework allows the model to appropriately approximate the ground-truth distribution. 2) The results of trajectory forecasting benchmarks demonstrate that the CU-based framework steadily helps SOTA systems improve their performances. Especially, the proposed CU-based framework helps VectorNet improve by 57cm regarding Final Displacement Error on nuScenes dataset. 3) The visualization results of CU illustrate that the value of CU is highly related to the amount of the interactive information among agents.
Fully Quantized Image Super-Resolution Networks
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
[15] Wenzhe Shi, Jose Caballero, Ferenc Huszár, Johannes
Totz, Andrew P Aitken, Rob Bishop, Daniel Rueckert,
and Zehan Wang. ...
[18] Zheng Hui, Xinbo Gao, Yunchu Yang, and Xiumei
Wang. Lightweight image super-resolution with infor-
mation multi-distillation network. ...
arXiv:2011.14265v2
fatcat:h7g4kh42kjbuplvupbimgjqqja
Cinnabar-Induced Subchronic Renal Injury Is Associated with Increased Apoptosis in Rats
2015
BioMed Research International
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The aim of this study was to explore the role of apoptosis in cinnabar-induced renal injury in rats. To test this role, rats were dosed orally with cinnabar (1 g/kg/day) for 8 weeks or 12 weeks, and the control rats were treated with 5% carboxymethylcellulose solution. Levels of urinary mercury (UHg), renal mercury (RHg), serum creatinine (SCr), and urine kidney injury molecule 1 (KIM-1) were assessed, and renal pathology was analyzed. Apoptotic cells were identified and the apoptotic index was
doi:10.1155/2015/278931
pmid:25629042
pmcid:PMC4300031
fatcat:6bxqxrulgbfzzhklb5fjduapq4
more »
... calculated. A rat antibody array was used to analyze expression of cytokines associated with apoptosis. Results from these analyses showed that UHg, RHg, and urine KIM-1, but not SCr, levels were significantly increased in cinnabar-treated rats. Renal pathological changes in cinnabar-treated rats included vacuolization of tubular cells, formation of protein casts, infiltration of inflammatory cells, and increase in the number of apoptotic tubular cells. In comparison to the control group, expression of FasL, Fas, TNF-α, TRAIL, activin A, and adiponectin was upregulated in the cinnabar-treated group. Collectively, our results suggest that prolonged use of cinnabar results in kidney damage due to accumulation of mercury and that the underlying mechanism involves apoptosis of tubular cells via a death receptor-mediated pathway.
DyRep: Bootstrapping Training with Dynamic Re-parameterization
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks. Despite the prevalence, current Rep methods simply re-parameterize all operations into an augmented network, including those that rarely contribute to the model's performance. As such, the price to pay is an expensive computational overhead to manipulate these unnecessary behaviors. To eliminate the above caveats, we aim to bootstrap the training with minimal cost by devising a dynamic
arXiv:2203.12868v1
fatcat:qbsqnqfsyrblthaapchtwybvcq
more »
... arameterization (DyRep) method, which encodes Rep technique into the training process that dynamically evolves the network structures. Concretely, our proposal adaptively finds the operations which contribute most to the loss in the network, and applies Rep to enhance their representational capacity. Besides, to suppress the noisy and redundant operations introduced by Rep, we devise a de-parameterization technique for a more compact re-parameterization. With this regard, DyRep is more efficient than Rep since it smoothly evolves the given network instead of constructing an over-parameterized network. Experimental results demonstrate our effectiveness, e.g., DyRep improves the accuracy of ResNet-18 by 2.04% on ImageNet and reduces 22% runtime over the baseline. Code is available at: https://github.com/hunto/DyRep.
Piecewise linear activations substantially shape the loss surfaces of neural networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Xiao Zhang, Yaodong Yu, Lingxiao Wang, and Quanquan Gu. Learning one-hidden-layer relu net-
works via gradient descent. ...
Gang Wang, Georgios B Giannakis, and Jie Chen. Learning relu networks on linearly separable
data: Algorithm, optimality, and generalization. ...
arXiv:2003.12236v1
fatcat:r54rh2tczzbkhgbduhwcocl3zm
Botanical materials based on biomechanics
2017
ACM Transactions on Graphics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Wang. ...
ACKNOWLEDGEMENTS This research was sponsored in part by the National Science Foundation (CAREER-1055035, IIS-1422869), the Sloan Foundation, the Okawa Foundation, and USC Annenberg Graduate Fellowship to Bohan ...
Wang and colleagues [2015] inferred materials of solid threedimensional objects from point-cloud sequences. ...
doi:10.1145/3072959.3073655
fatcat:bboaezpk3fblphk6eo6pfhihjy
Editorial for application-driven knowledge acquisition
2020
World wide web (Bussum)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
T Wu, H Wang and their colleagues proposed a complete general technical framework for constructing knowledge graph from multiple online encyclopedias, including knowledge rule extraction, live knowledge ...
Y Wang, W Chen and their colleagues detailed the use of DBN to obtain correlations between medical variables from electronic health records (EHRs) and measure fine-grained patient similarity using RNN. ...
doi:10.1007/s11280-020-00827-6
fatcat:gdt63za6mrewriu7frir2nhkby
An Improved Distributed Query for Large-Scale RDF Data
2020
Journal on Big Data
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The rigid structure of the traditional relational database leads to data redundancy, which seriously affects the efficiency of the data query and cannot effectively manage massive data. To solve this problem, we use distributed storage and parallel computing technology to query RDF data. In order to achieve efficient storage and retrieval of large-scale RDF data, we combine the respective advantage of the storage model of the relational database and the distributed query. To overcome the
doi:10.32604/jbd.2020.010358
fatcat:n5djqu5lp5er7kznzjqqmvjpwy
more »
... ntages of storing and querying RDF data, we design and implement a breadth-first path search algorithm based on the keyword query on a distributed platform. We conduct the LUBM query statements respectively with the selected data sets. In experiments, we compare query response time in different conditions to evaluate the feasibility and correctness of our approaches. The results show that the proposed scheme can reduce the storage cost and improve query efficiency.
Evaluation of Mobile Phone Performance for Near-Infrared Fluorescence Imaging
2017
IEEE Transactions on Biomedical Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Srikanth Vasudevan Jessica Ramella-Roman, Scott Mathews, and Stanley Wang for their contributions to this project. ...
doi:10.1109/tbme.2016.2601014
pmid:28113231
pmcid:PMC5360525
fatcat:y3h2pzlfgnhn3aqmpqfnx5zmsq
Automated Progressive Learning for Efficient Training of Vision Transformers
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Automated Progressive Learning for Efficient Training of Vision Transformers Supplementary Material Changlin Li 1,2,3 Bohan Zhuang 3 † Guangrun Wang 4 Xiaodan Liang 5 Xiaojun Chang 2 Yi Yang 6 1 Baidu ...
arXiv:2203.14509v1
fatcat:g3tx62qekzhzbhkg33d6oa2bs4
« Previous
Showing results 1 — 15 out of 769 results