A supervised two-channel learning method for hidden Markov model and application on lip reading by Foo, Say Wei, Dong, Liang

“…This method is specially designed to train HMMs for fine recognition from similar observations. The prominent features of this method are 1.) the criterion function is based on the difference between training sequences, and 2.) a twochannel structure is adopted to maintain the validity of the HMM. …”
Get full text
Get full text

Elastic modulus, hardness and creep performance of SnBi alloys using nanoindentation by Shen, Lu, Septiwerdani, Pradita, Chen, Zhong

“…At the intermediate stress region (200–370 MPa), dislocation climb is the dominant creep mechanism with stress exponents around 5–8. When fine lamellar structure is the dominant constituent of the microstructure, phase boundary sliding is identified as the rate-controlling mechanism in the low stress region (<200 MPa).…”
Get full text
Get full text

Knowledge-based reactive planning and re-planning – a case-study approach by Djemai, Ramzi, Vassilev, Vassil, Ouazzane, Karim, Dey, Maitreyee

“…Planning for uncertainties arising from indoor evacuations can be complex as there’s a fine balance to strike between a too-detailed plan and one that’s too vague. …”
Get full text

Vision-language modelling for radiological imaging and reports in the low data regime by Windsor, R, Jamaludin, A, Kadir, T, Zisserman, A

“…Combined, they significantly improve retrieval compared to fine-tuning CLIP, roughly equivalent to training with 10x the data. …”

A comparative analysis of missing data imputation techniques on sedimentation data by Loh, Wing Son, Ling, Lloyd, Chin, Ren Jie, Lai, Sai Hin, Loo, Kar Kuan, Seah, Choon Sen

“…A comparative analysis on the missing fine sediment data imputation performance was made based on four different techniques, namely the k-Nearest Neighbourhood (k-NN), Support Vector Regression (SVR), Multiple Regression (MR), and Artificial Neural Network (ANN), under the single imputation (SI) and multiple imputation (MI) regimes. …”
Get full text

Referring expression segmentation: from conventional to generalized by Liu, Chang

Get full text

Towards semantic, debiased and moment video retrieval by Satar, Burak

“…Our approach tackles this challenge for the first time on long, fine-grained, and untrimmed egocentric videos, while existing methodologies target short, coarse-grained, and trimmed third-person videos. …”
Get full text

Towards optimal scheduling of deep learning training jobs in GPU clusters by Gao, Wei

“…Second, it reuses the fine-tuning runtime of FMF workloads to reduce the significant context switch overhead. …”
Get full text

Cold-formed light gauge steel for rapid deployable shelters by Wu, Hongjun.

Get full text

Use of bamboo in construction by Quek, Ming Hui.

Get full text

Laser Beacon Tracking for High-Accuracy Attitude Determination by Nguyen, Tam, Cahoy, Kerri

“…Advances in attitude determination have led to the development of several CubeSat-sized attitude sensors capable of achieving fine attitude knowledge,most of which utilize natural light sources as references, such as in the case of star trackers and sun sensors. …”
Get full text

Examples out of Thin Air: AI-Generated Dynamic Context to Assist Program Comprehension by Example by Mattis, Toni, Krebs, Eva, Rinard, Martin C., Hirschfeld, Robert

Get full text

4.602 Modern Art and Mass Culture, Spring 2004 by Jones, Caroline

“…It focuses on the way artists use the tension between fine art and mass culture to mobilize a critique of both. …”
Get full text

Surface modulation of hierarchical MoS2 nanosheets by Ni single atoms for enhanced electrocatalytic hydrogen evolution by Zhang, Huabin, Yu, Le, Chen, Tao, Zhou, Wei, Lou, David Xiong Wen

“…Here, a surface modulation strategy is demonstrated through the decoration of isolated Ni atoms onto the basal plane of hierarchical MoS2 nanosheets supported on multichannel carbon nanofibers for boosted hydrogen evolution activity. X-ray absorption fine structure investigation and density functional theory (DFT) calculation reveal that the MoS2 surface decorated with isolated Ni atoms displays highly strengthened H binding. …”
Get full text

A cup of coffee by Yong, Kai Ting

Get full text

Deep robust multilevel semantic hashing for multi-label cross-modal retrieval by Song, Ge, Tan, Xiaoyang, Zhao, Jun, Yang, Ming

“…It seeks to preserve fine-grained similarity among data with rich semantics,i.e., multi-label, while explicitly require distances between dissimilar points to be larger than a specific value for strong robustness. …”
Get full text

Fabrication and characterization of spin-based synaptic devices by Lim, Idayu

“…Spin orbit torque (SOT) induced chiral domain wall (DW) motion in heavy-metal/ferromagnetic racetrack devices is promising for achieving energy-efficient and high-speed computing elements for edge intelligence[1]. By utilizing fine-grained control of the DW positions and hence, variable resistance readouts, analog synapses can be emulated[2]. …”
Get full text

An enhanced deep reinforcement learning ensemble empowered by large language model by Li, Xinyi

“…At its core, LLM-DRE effectively processes and synthesizes disparate forms of market data to fine-tune trading strategies, enabling an enriched assessment of financial environments. …”
Get full text

Annotating videos that teach MS Excel and predicting mouse / keyboard actions by Tan, Genson Yao Jie

“…The research methodology involves exploring the limitations of fine-tuning Flan-T5 for this task, while also utilizing prompt engineering on Large Language Model (LLM) such as Llama 2 as an alternative method. …”
Get full text

Analyzing job roles and skill descriptions using NLP techniques (part 1: data cleaning and pre-processing and part 4: front-end visualization/user interface) - collaboration with A... by Tan, Kenneth Meng Hwee

“…The initial phase emphasizes data cleaning and pre-processing to fine-tune job descriptions and associated skill sets. …”
Get full text