CLAROS - bringing classical art to a global public by Kurtz, D, Parker, G, Shotton, D, Klyne, G, Schroff, F, Zisserman, A, Wilks, Y

“…CLAROS uses CIDOC CRM (http://cidoc.ics.forth.gr/), developed under UNESCO's ICOM (http://icom.museum/), to map across datasets and a portfolio of Open Source software to deliver them swiftly to a broad range of global users. …”

Splatter image: ultra-fast single-view 3D reconstruction by Szymanowicz, S, Rupprecht, C, Vedaldi, A

“…Our main innovation is the surprisingly straightforward design of this network, which, using 2D operators, maps the input image to one 3D Gaussian per pixel. …”

Heights via anabelian geometry and local Bloch-Kato Selmer sets by Betts, L

“…</p> <p>On the geometric side, we also prove a number of foundational results on local constancy or analyticity of various non-abelian Kummer maps for pro-unipotent etale or Betti–de Rham fundamental groups of arbitrary smooth varieties.…”

Topography of social touching depends on emotional bonds between humans by Suvilehto, JT, Glerean, E, Dunbar, RIM, Hari, R, Nummenmaa, L

“…Here we reveal quantified, relationship-specific maps of bodily regions where social touch is allowed in a large cross-cultural dataset (N = 1,368 from Finland, France, Italy, Russia, and the United Kingdom). …”

On fundamental aspects of quantum extreme learning machines by Xiong, W, Facelli, G, Sahebi, M, Agnel, O, Chotibut, T, Thanasilp, S, Holmes, Z

“…Their appeal lies in the rich feature map induced by the dynamics of a quantum substrate—the quantum reservoir—and the efficient post-measurement training via linear regression. …”

Redefining Ancient Epirus

“…Through this approach, the volume effectively moves Epirus from the border to the centre of the map of current archaeo-historical research, as well as offering a starting point for further historical investigations in the field.…”

Comparison of different deep learning object detection algorithms on fruit drying characterization by Umair, Mohammad Yamin, Norazlianie, Sazali, Kettner, Maurice, Mohd Azraai, Mohd Razman, Weiβ, Robert

“…YOLOv5m demonstrated superior performance compared to SSD MobileNet and EfficientDet, achieving a mean average precision (mAP) of 0.99589. SSD MobileNet demonstrated exceptional performance in real-time object detection, accurately detecting the majority of objects with a high level of confidence. …”
Get full text

Looking for a better future: modeling migrant mobility by Loaiza Saa, Isabella, Novak, Matej, Morales, Alfredo J., Pentland, Alex

“…For this purpose it is crucial to map and understand geographic patterns of migration, including spatial mobility and dynamics over time. …”
Get full text

Probabilistic Volumetric Fusion for Dense Monocular SLAM by Rosinol, Antoni, Leonard, John J., Carlone, Luca

“…We show that the resulting depth uncertainty provides an excellent signal to weight the depth-maps for volumetric fusion. Without our depth uncertainty, the resulting mesh is noisy and with artifacts, while our approach generates an accurate 3D mesh with significantly fewer artifacts. …”
Get full text

Unsupervised learning based performance analysis of n-support vector regression for speed prediction of a large road network by Asif, M. T., Oran, A., Fathi, E., Xu, M., Dhanya, M. M., Mitrovic, N., Jaillet, P., Dauwels, Justin, Goh, Chong Yang

“…We propose unsupervised learning techniques by employing k-means clustering, principal component analysis (PCA), and self organizing maps (SOM) to overcome this insufficiency. We establish the effectiveness of the developed methods by evaluation of spatial and temporal characteristics of prediction performance of the proposed variable window v-SVR method.…”
Get full text
Get full text

Vector coloring the categorical product of graphs by Godsil, Chris, Roberson, David E., Rooney, Brendan, Šámal, Robert, Varvitsiotis, Antonios

“…For a graph H and a vector t-coloring p1, … , pn of G, the map taking (i, ℓ) ∈ V(G) × V(H) to pi is a vector t-coloring of the categorical product G× H. …”
Get full text

Toward achieving robust low-level and high-level scene parsing by Shuai, Bing, Ding, Henghui, Liu, Ting, Wang, Gang, Jiang, Xudong

“…Meanwhile, we propose a convolutional context network (CCN) and place it on top of pre-trained CNNs, which is used to aggregate contexts for high-level feature maps so that robust high-level parsing can be achieved. …”
Get full text

Deep learning speech enhancement in satellite radio communication by Low, Yuki Yu Jun

“…Wave-U-Net repeatedly resamples feature maps to calculate and integrate features at different time scales [1]. …”
Get full text

Matriptase activation of Gq drives epithelial disruption and inflammation via RSK and DUOX by Ma, Jiajia, Scott, Claire A., Ho, Ying Na, Mahabaleshwar, Harsha, Marsay, Katherine S., Zhang, Changqing, Teow, Christopher K. J., Ng, Ser Sue, Zhang, Weibin, Tergaonkar, Vinay, Partridge, Lynda J., Roy, Sudipto, Amaya, Enrique, Carney, Tom J.

“…Finally, we identify RSK kinases as MAPK targets disrupting adherens junctions in hai1a mutants. Our work maps novel signalling cascades mediating the potent effects of Matriptase on epithelia, with implications for tissue damage response and carcinoma progression.…”
Get full text

Road-network-based rapid geolocalization by Li, Yongfei, Yang, Dongfang, Wang, Shicheng, He, Hao, Hu, Jiaxing, Liu, Huaping

“…We match roads in the onboard images to the reference road vector map, and realize successful localization over areas as large as a whole city. …”
Get full text

Annual dilated convolution neural network for newbuilding ship prices forecasting by Gao, Ruobin, Liu, Jiahui, Bai, Xiwen, Yuen, Kum Fai

“…Finally, the convoluted features are fed into a linear layer which maps the features to future values. The annual dilated convolution filter owns a vision across one year and integrates all variables’ temporal information. …”
Get full text

Person re-identification via pose-aware multi-semantic learning by Luo, Xiangzhong, Duong, Luan H. K., Liu, Weichen

“…First, taking into account multiple semantics, we propose Multi-semantic Fusion Network (MFN) as the backbone, employing several shortcuts to reserve bypass feature maps for subsequent fusion. Second, to learn a pose-sensitive embedding, pose-aware clues are considered, forming the complete PMFN and investigating the well-aligned global and local body regions. …”
Get full text

Prehistoric human migration between Sundaland and South Asia was driven by sea-level rise by Kim, Hie Lim, Li, Tanghua, Kalsi, Namrata, Nguyen, Hung Tran The, Shaw, Timothy Adam, Ang, Khai C., Cheng, Keith C., Ratan, Aakrosh, Peltier, W. Richard, Samanta, Dhrubajyoti, Pratapneni, Mahesh, Schuster, Stephan Christoph, Horton, Benjamin Peter

“…Here, we create a paleogeographic map, focusing on sea-level changes during the period spanning the LGM to the present-day and infer the human population history in Southeast and South Asia using 763 high-coverage whole-genome sequencing datasets from 59 ethnic groups. …”
Get full text

Half-body portrait relighting with overcomplete lighting representation by Song, Guoxian, Cham, Tat-Jen, Cai, Jianfei, Zheng, Jianmin

“…Rather than following classical inverse rendering methodology that involves estimating normals, albedo and environment maps, we implicitly encode the subject and lighting in a latent space, and use these latent codes to generate relighted images by neural rendering. …”
Get full text

Deep transcriptome profiling reveals limited conservation of A-to-I RNA editing in Xenopus by Nguyen, Tram Anh, Heng, Joel Jia Wei, Ng, Yan Ting, Sun, Rui, Fisher, Shira, Oguz, Gokce, Kaewsapsak, Pornchai, Xue, Shifeng, Reversade, Bruno, Ramasamy, Adaikalavan, Eisenberg, Eli, Tan, Meng How

“…Results: Here, we identify millions of editing events in Xenopus with high accuracy and systematically map the editome across developmental stages, adult organs, and species. …”
Get full text