A boundary-fragment-model for object detection by Opelt, A, Pinz, A, Zisserman, A

“…The generative aspect of the model is used to determine an approximate segmentation.</p> <p>We demonstrate the following results: (i) the BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance; and (ii) in comparison with other published results on several object classes (airplanes, cars-rear, cows) the BFM detector is able to exceed previous performances, and to achieve this with less supervision (such as the number of training images).…”

SHREC’21: Quantifying shape complexity by Arslan, Mazlum Ferhat, Haridis, Alexandros, Rosin, Paul L., Tari, Sibel, Brassey, Charlotte, Gardiner, James D., Genctav, Asli, Genctav, Murat

“…The dataset consists of three collections: 1800 perturbed cube and sphere models classified into 4 categories, 50 shapes inspired from the fields of architecture and design classified into 2 categories, and the data from the Princeton Segmentation Benchmark, which consists of 19 natural object categories. …”
Get full text

Deep learning for scene flow estimation on point clouds: a survey and prospective trends by Li, Zhiqi, Xiang, Nan, Chen, Honghua, Zhang, Jianjun, Yang, Xiaosong

“…Furthermore, this paper investigates various higher-level scene understanding tasks, including object tracking, motion segmentation, etc. and concludes with an overview of foreseeable research trends for scene flow estimation.…”
Get full text

Causalqa: a causal framework for question answering by Dutta, Angshuk

“…Neural networks have proven their success in various fundamental applications such as object detection, image segmentation, image and text generation and several NLP tasks. …”
Get full text

Recognition of human actions by Xiao, Xu

“…Based on it, modification was implemented; instead of using whole MHI image to get Hu Moments, the MHI image of human body is segmented into 4 body parts – head, arm, torso and leg. …”
Get full text

Market outlook of VLCCs in the next 5 years by Cheah, Peifang.

“…This can be achieved by segmenting the market into 5 bands based on historical Time Charter Equivalent (TCE) namely very weak, weak, steady, strong and very strong condition and a forecast of the strength of the freight market will be derived (ie the band the market will fall in). …”
Get full text

Spin carbon nanotubes into CNT fibers by Lim, Johnathan See Kwan.

“…After densifying, each strand of fiber were tested for their mechanical properties before they were divided into smaller segments and twisted together to form multi-ply fibers, ranging from a 2 ply CNT yarn to a 10 ply CNT yarn. …”
Get full text

Multi-linear regression models for traffic prediction in large-scale networks by Zhao, XinYue

“…Various methods have been practice in the traffic forecasting study and some algorithms that used in other fields like In this paper we apply 3 multi-linear regression models on the speed data collected from 266 road segments in Singapore, which are Partial Least Square, High-Order Partial Least Square and N-way Partial Least Square model. …”
Get full text

National Day parades : we the citizens of Singapore by Low, Annabel Hui Xin

“…This will be done through the examination of how three segments of the National Day parade – the military showcase, performances and National Day songs – have been used and adapted over the years to further the government’s nation building efforts in Singapore.…”
Get full text

Vision enhancement using artificial intelligence techniques by Yu, Xiaohan

“…So they proposed an algorithm using super pixel segmentation to increase the robust of towards rain occlusion and fast camera motion. …”
Get full text

As firm as their foundations: creating transferable adversarial examples across downstream tasks with CLIP by Hu, A, Gu, J, Pinto, F, Kamnitsas, K, Torr, PHS

“…Solely based on open-sourced CLIP vision encoders, this method can produce highly effective adversaries that simultaneously fool more than 20 downstream models spanning 4 common vision-language tasks (semantic segmentation, object detection, image captioning and visual question-answering). …”

Fine-scale population structure and widespread conservation of genetic effect sizes between human groups across traits by Hu, S, Ferreira, LAF, Shi, S, Hellenthal, G, Marchini, J, Lawson, DJ, Myers, SR

“…To estimate the similarity of genetic effect sizes between groups, we developed ANCHOR, which estimates changes in the predictive power of an existing PGS in distinct local ancestry segments. ANCHOR infers highly similar (estimated correlation 0.98 ± 0.07) effect sizes between UK Biobank participants of African and European ancestry for 47 of 53 quantitative phenotypes, suggesting that gene–environment and gene–gene interactions do not play major roles in poor cross-ancestry PGS transferability for these traits in the United Kingdom, and providing optimism that shared causal mutations operate similarly in different populations.…”

Instabilities in tidal turbine wakes by Smyth, ASM, Nishino, T, Young, AM

“…Unsteady inflow causes the turbine blades to shed vorticity of time-varying strength into the wake, which in turn leads to a spatial variation in wake vortex strength, such that the vorticity of adjacent returning wake segments can differ. This spatial variation triggers the instability of tip vortices, the characteristics of which are shown to be governed by the ’frequency ratio’ ω/ΩNB (where ω is harmonic inflow frequency, Ω is turbine rotational frequency and NB is the number of blades). …”

Search of the early O3 LIGO data for continuous gravitational waves from the Cassiopeia A and Vela Jr. supernova remnants by Sudhir, Vivishek

“…We carry out the searches in the LIGO data from the first six months of the third Advanced LIGO and Virgo observing run, using the Weave semi-coherent method, which sums matched-filter detection-statistic values over many time segments spanning the observation period. No gravitational wave signal is detected in the search band of 20--976 Hz for assumed source ages greater than 300 years for Cas A and greater than 700 years for Vela Jr. …”
Get full text

Generation of vascularized 3-dimensional (3D) kidney organoids from human pluripotent stem cells by Low, Jian Hui

“…Here, we present the establishment of a highly efficient protocol for differentiating hPSCs into kidney organoids comprised of segmented nephrons, vasculature, and interstitial cells. …”
Get full text

Semantic map for indoor positioning system (floorplan enhancement with semantic SLAM) by Lim, Han Quan

“…In combination with semantic segmentation, semantically labelled point clouds are possible. …”
Get full text

A two-stage automatic color thresholding technique by Pootheri, Shamna, Ellam, Daniel, Grübl, Thomas, Liu, Yang

“…Accurately performing background suppression in PCA boards facilitates the inspection of digital images with small objects of interest, such as text or microcontrollers on a PCA board. The segmentation of skin cancer lesions will help doctors to automate skin cancer detection. …”
Get full text

A structural interpretation of the aftershock "cloud" of the 1992 Mw 7.3 Landers earthquake by Liu, Jing, Sieh, Kerry, Hauksson, Egill

“…Low b-values occur along segments that are simple, whereas higher b-values correlate with sections that are more complex. …”
Get full text
Get full text

Unearthing roots by Lim, Ling Ern

“…The installation consists of three main segments:The first is an interactive physical display of a range of selected herbs and common kitchen ingredients widely available and affordable in Singapore. …”
Get full text

3-way respiratory sound classification using machine learning algorithms by Tu, Yixuan

“…This dissertation also shows the signal processing progress before the respiratory sound could be classified, which includes audio value extraction, data choosing, signal processing, segmentation, feature extraction, etc.…”
Get full text