• Publications
  • Influence
Attention-based Ensemble for Deep Metric Learning
An attention-based ensemble, which uses multiple attention masks so that each learner can attend to different parts of the object, which outperforms the state-of-the-art methods by a significant margin on image retrieval tasks.
Evolutionary Approaches To Minimizing Network Coding Resources
This work employs evolutionary approaches, based on a genetic algorithm, that avoid the computational complexity that makes the problem NP-hard and develops a novel distributed framework that works also with networks with cycles.
Collaborative Learning in Engineering Students: Gender and Achievement
Background Collaboration is an ABET accreditation required component of the engineering curriculum. Research has shown that collaborative learning positively influences student achievement. The
Genetic Representations for Evolutionary Minimization of Network Coding Resources
This work demonstrates how a genetic algorithm solves the problem of minimizing the resources used for network coding, subject to a throughput constraint, in a multicast scenario and compares two different genotype encodings, which tradeoff search space size with fitness landscape.
Responses of crop yield growth to global temperature and socioeconomic changes
The results revealed that global mean yields of maize and soybean will stagnate with warming even when agronomic adjustments are considered, and this trend is consistent across socioeconomic assumptions.
Examining students' future time perspective: Pathways to knowledge building
The purpose of this study was to provide evidence for the internal structure of the domain-general and context-specific components of future time perspective (FTP) and to provide support for a
A deep learning framework for supporting the classification of breast lesions in ultrasound images.
The proposed method can work in tandem with human radiologists to improve performance, which is a fundamental purpose of computer-aided diagnosis.
Stochastic Class-Based Hard Example Mining for Deep Metric Learning
The key idea is to adopt class signatures that keep track of feature embedding online with minor additional cost during training, and identify hard negative example candidates using the signatures and achieves the state-of-the-art performance on the several standard benchmark datasets.
Abnormal Object Detection by Canonical Scene-Based Contextual Model
A novel generative model is proposed that detects abnormal objects by meeting four proposed criteria of success, and this model generates normal as well as abnormal objects, each following their respective tendencies.
Uncertainties of potentials and recent changes in global yields of major crops resulting from census- and satellite-based yield datasets at multiple resolutions
Comparing the similarities and differences in global yield gaps, trend patterns, growth rates and changes in year-to-year variability shows that estimates of yield gaps and variability changes are more uncertain than those of yield trend patterns and growth rates.