3 citations · 7 across the 10 of their papers we have counts for
11 papers
Front-to-Back: Benchmarking Vision-Language Models for Asymmetric Cross-View Vehicle Re-Identification
Moseli Mots'oehli, Thulani Babeli
Matching the same vehicle across front and rear cameras is difficult because the cameras do not share a view and the vehicle's appearance changes substantially. We introduce Front2…
LLMs and Agentic AI in Insurance Decision-Making: Opportunities and Challenges For Africa
Graham Hill, JingYuan Gong, Thulani Babeli +2
In this work, we highlight the transformative potential of Artificial Intelligence (AI), particularly Large Language Models (LLMs) and agentic AI, in the insurance sector. We consi…
Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception
Moseli Mots'oehli, Feimei Chen, Hok Wai Chan +4
The scarcity of autonomous vehicle datasets from developing regions, particularly across Africa's diverse urban, rural, and unpaved roads, remains a key obstacle to robust percepti…
Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise
Moseli Mots'oehli, Hope Mogale, Kyungim Baek
Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformer…
GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise
Moseli Mots'oehli, kyungim Baek
Active learning aims to train accurate classifiers while minimizing labeling costs by strategically selecting informative samples for annotation. This study focuses on image classi…
Assistive Image Annotation Systems with Deep Learning and Natural Language Capabilities: A Review
Moseli Mots'oehli
While supervised learning has achieved significant success in computer vision tasks, acquiring high-quality annotated data remains a bottleneck. This paper explores both scholarly…
FishNet: Deep Neural Networks for Low-Cost Fish Stock Estimation
Moseli Mots'oehli, Anton Nikolaev, Wawan B. IGede +3
Fish stock assessment often involves manual fish counting by taxonomy specialists, which is both time-consuming and costly. We propose FishNet, an automated computer vision system…
PuoBERTa: Training and evaluation of a curated language model for Setswana
Vukosi Marivate, Moseli Mots'Oehli, Valencia Wagner +2
Natural language processing (NLP) has made significant progress for well-resourced languages such as English but lagged behind for low-resource languages like Setswana. This paper…
Deep Active Learning in the Presence of Label Noise: A Survey
Moseli Mots'oehli, Kyungim Baek
Deep active learning has emerged as a powerful tool for training deep learning models within a predefined labeling budget. These models have achieved performances comparable to tho…
Comparision Of Adversarial And Non-Adversarial LSTM Music Generative Models
Moseli Mots'oehli, Anna Sergeevna Bosman, Johan Pieter De Villiers
Algorithmic music composition is a way of composing musical pieces with minimal to no human intervention. While recurrent neural networks are traditionally applied to many sequence…
Public Parking Spot Detection And Geo-localization Using Transfer Learning
Moseli Mots'oehli, Yao Chao Yang
In cities around the world, locating public parking lots with vacant parking spots is a major problem, costing commuters time and adding to traffic congestion. This work illustrate…