PGMoGen: pose-guided human motion generation by Yin, Jiarui

“…Furthermore, to increase the diversity and quantity of the training motions, we have re-labelled the HuMMan dataset and utilized it as an additional training dataset for our PGMoGen model. …”
Get full text

Self-pretraining of 3D transformer variations with masked autoencoders for multiple instances in medical image analysis by Li, Linyuan

“…Masked Autoencoder (MAE) shows its ability to be used effectively in pre-training Vision Transformers (ViT) for analysing natural images. …”
Get full text

Development and implementation of a 3d-HDR brachytherapy program for cervical cancer in a sub-Saharan African centre by Joseph, A, Balogun, O, Adegboyega, B, Salako, O, Irabor, OC, Ajose, A, Adeneye, S, Alabi, A, Ohazurike, E, Ogamba, CF, Oladipo, A, Fagbemide, O, Habeebu, M, Puthoff, D, Onitilo, A, Ngwa, W, Nwachukwu, C

“…Strategies such as remote training and proactive resource management, are critical for overcoming implementation barriers.…”

To assess the impact of physical factors on velocity, speed, and accuracy of tennis serve by Ma, Xudong, Yaacob, Azhar, Tengku Kamalden, Tengku Fadilah, Ng, Yee Guan

“…Objective: This study investigates the coordination of racquet and ball speed, examining how physical attributes and training impact serve performance. Methods: An exhaustive review was conducted using Google Scholar, analyzing 25 key papers related to tennis serve velocity, biomechanics, and training programs. …”
Get full text

One-class knowledge distillation for face presentation attack detection by Li, Zhi, Cai, Rizhao, Li, Haoliang, Lam, Kwok-Yan, Hu, Yongjian, Kot, Alex Chichung

“…Under this framework, a teacher network is trained with source domain samples to provide discriminative feature representations for face PAD. …”
Get full text

Investigation on ImageNet Remaining Errors with TRAK by Ma, Lingyi

“…However, not many studies have dived into fixing labels for the training set, largely due to its large scale. The proposed thesis aims to understand the remaining errors that models are still making on the ImageNet dataset and investigate the labeling problems in the Imagenet training set, utilizing TRAK- a recently developed efficient data attribution method to help identify problematic images among the 1.4 million images in Imagenet training set.…”
Get full text

Uncertainty-Inclusive Contrastive Learning for Leveraging Synthetic Images by Cai, Fiona X.

“…Recent advancements in text-to-image generation models have sparked a growing interest in using synthesized training data to improve few-shot learning performance. …”
Get full text

Investigating Fine-Tuning of Language Models for Multiple-Choice Questions by Wang, Ivy A.

“…We specifically investigate training data properties related to positional bias in fine-tuned language model performance on correctly answering MCQs. …”
Get full text

Scene text detection using neural network by Tan, Yi Hong

“…The second is to use supervised pre-training followed by domain-specific finetuning to coaching giant convolutional neural networks once the tagged training information is lean [1]. we tend to train a replacement model supported a dataset collected by ourselves from google web site. …”
Get full text

FedCBO: reaching group consensus in clustered Federated learning through Consensus-Based Optimization by Carrillo, JA, Trillos, NG, Li, S, Zhu, Y

“…In clustered federated learning, one assumes an additional unknown group structure among users, and the goal is to train models that are useful for each group, rather than simply training a single global model for all users. …”

Free3D: consistent novel view synthesis without 3D representation by Zheng, C, Vedaldi, A

“…Similar to Zero-1-to-3, we start from a pre-trained 2D image generator for generalization, and fine-tune it for NVS. …”

Model-based convolutional neural network approach to underwater source-range estimation by Chen, R., Schmidt, H.

“…When tested with data simulated in environments that deviate slightly from the training environment, this approach shows improved prediction accuracy and lower mean-absolute-error (MAE) compared to MFP. …”
Get full text

An interpretable Neural Fuzzy Hammerstein-Wiener network for stock price prediction by Xie, Chen, Rajan, Deepu, Chai, Quek

“…Conventional offline neuro-fuzzy systems are only able to generate implications based on fuzzy rules induced during training, which requires the training data to be able to adequately represent all system behaviors. …”
Get full text

Experimenting on weighted PCA on Yale face database by Moe Thu Zar.

“…The main idea is to find the principal components of the distribution of faces or the eigenvectors of the covariance matrix of the set of training images.…”
Get full text

Proposal for an initiative to encourage and support the growth of popular scientific culture in the Commonwealth by Jegede, Olugbemiro., Solomon, Joan.

Get full text
Get full text

Competency requirements for professionals in logistics and supply chain management by Thai, Vinh Van

“…With business environments subject to continued rapid change, it is critical that logistics professionals are well trained and equipped with the most relevant and important skills and knowledge. …”
Get full text
Get full text

Profile of Australian Library Technician students by Carroll, Mary

“…The profile of the Library Technician student was then compared with the broader training package student cohort to examine any similarities or differences particular to Library Technician students. …”
Get full text

Artificial intelligence monitoring at the edge for smart nation deployment by Chua, Jeremy Chin Yew

“…This project aims to improve the model training process using data augmentation via mixing noise into the training data, then implement the model prediction in a Raspberry Pi. …”
Get full text

Report on business attachment with CS First Boston. by Chiang, Waipeng.

“…The purpose of the report is to provide a summary of the business training experience and an overview of the organisation. …”
Get full text

RES.TLL-008 Social and Ethical Responsibilities of Computing (SERC), Fall 2022 by Shah, Julie, Kaiser, David

“…Social and Ethical Responsibilities of Computing (SERC), a cross-cutting initiative of the MIT Schwarzman College of Computing, works to train students and facilitate research to assess the broad challenges and opportunities associated with computing, and improve design, policy, implementation, and impacts. …”
Get full text