Nick Kashani Motlagh
Research archive

Publications and scholarly articles

A reading-friendly archive of papers on selective prediction, multimodal evidence, calibration, and typed abstention for ML systems.

Each card summarizes the task, method, reported signal, and available artifacts so the archive can be scanned without opening every PDF.

Machine Vision and Applications / 2025

Naturally Constrained Reject Option Classification

N. Kashani Motlagh, J. Davis, T. Anderson, J. Gwinnup

Journal extension of ISVC 2022 Best Paper, evaluating per-class binomial reject thresholds on ImageNet and remote-sensing datasets.

  • vision
  • reject option
  • calibration
  • ImageNet
  • remote sensing
  • Invited journal extension of the ISVC Best Paper with additional datasets, analysis, and calibration experiments.
  • Per-class binomial thresholds outperform global thresholding on ImageNet and remote-sensing splits.
Paper Code
Artifacts

learning-idk

WMT 2024 / 2024

Assessing the Role of Imagery in Multimodal Machine Translation

N. Kashani Motlagh, J. Davis, T. Anderson, J. Gwinnup, G. Erdmann

Contrastive evaluation of WMT 2024 multimodal MT systems shows measurable dependence on paired visual context.

  • multimodal MT
  • vision-language models
  • evaluation
  • WMT
  • Introduced imagery-aware contrastive probes for testing whether translations change under mismatched visual context.
  • Benchmarked nine multimodal MT systems across evaluation splits with high image-sensitivity variance.
Paper Code Data
Artifacts

calibration

ISVC 2022 / 2022

Best Paper

Learning When to Say "I Don't Know"

N. Kashani Motlagh, J. Davis, T. Anderson, J. Gwinnup

Per-class reject thresholds estimated from validation statistics, improving selective accuracy and coverage over global thresholding.

  • vision
  • reject option
  • selective accuracy
  • ImageNet
  • Best Paper at ISVC 2022; later extended in the MVA 2025 journal version.
  • Reported +0.4% selective-accuracy and +1.3% coverage gains on ImageNet over global thresholding.
Paper arXiv Code
Artifacts

learning-idk

ICCV 2021 Workshop on LUAI / 2021

A Framework for Semi-automatic Collection of Temporal Satellite Imagery for Analysis of Dynamic Regions

N. Kashani Motlagh, A. Radhakrishnan, J. Davis, R. Ilin

OpenStreetMap-guided imagery collection and labeling tools for building temporal satellite datasets for dynamic-region analysis.

  • remote sensing
  • data collection
  • labeling pipelines
  • change detection
  • Combined imagery download, polygon filtering, temporal organization, and annotation UI in a reproducible Python pipeline.
  • Reduced manual setup for construction-site monitoring datasets and downstream change-detection experiments.
Paper Code
Artifacts

construction-site-satellite-imagery-collection