Nick Kashani Motlagh

03 Research

Four peer-reviewed first-author papers.

3.1Peer-reviewed

Published papers

Machine Vision and Applications / 2025

First author

Naturally Constrained Reject Option Classification

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

Journal extension evaluating per-class binomial reject thresholds on benchmark image and text datasets and twelve synthetic variants, from 2 to 1,000 classes.

  • vision
  • reject option
  • calibration
  • ImageNet
  • Extends the natural reject-region constraint across controlled synthetic data, benchmark image classification, and text classification.
  • Reports transfer behavior on CINIC10 and long-tailed iNaturalist19 alongside explicit selective-accuracy, reject-accuracy, and coverage tradeoffs.
Paper arXiv Code
Related code and data

Reject-option classification

WMT 2024 / 2024

First author

Assessing the Role of Imagery in Multimodal Machine Translation

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

VGAMT scores 81% ImageCoMMuTE and 63% TextCoMMuTE on contrastive diagnostics, with 13% favorable and 0% unfavorable preference flips versus a mixed-image baseline.

  • multimodal MT
  • vision-language models
  • evaluation
  • WMT
  • Introduced imagery-aware contrastive probes for testing whether model scores change under mismatched visual context.
  • Evaluated three English-to-French multimodal model families, plus gated variants, under matched and mismatched visual context.
Paper

ISVC 2022 / 2022

First author Springer Best Paper Award

Learning When to Say “I Don’t Know”

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

Per-class abstention without preset rejection costs or accuracy/coverage targets: 97.4% selective accuracy at 79.7% coverage on ImageNet validation.

  • vision
  • reject option
  • selective accuracy
  • ImageNet
  • Springer Best Paper Award at ISVC 2022; later extended in the MVA 2025 journal version.
  • At the ImageNet δ=.75 operating point, B-CDF improved select accuracy by 0.4 percentage points and coverage by 1.3 points versus an uncalibrated global 0.5 threshold.
Paper arXiv Code
Related code and data

Reject-option classification

ICCV 2021 Workshop on LUAI / 2021

First author

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 OpenStreetMap extraction, polygon filtering, and temporal imagery download scripts in a public Python workflow.
  • Released the collection code and a sample construction-site satellite-imagery dataset under the repository's GPL license.
Paper Code
Related code and data

Satellite imagery collection

3.2Not yet peer-reviewed

Preprints & manuscripts

arXiv preprint / 2026

First author

Return or Revise? Learning When Revision Helps Retrieval-Augmented QA

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

Paired evaluations distinguish when retrieval-based revision repairs an incorrect answer from when it harms a correct one.

  • LLM evaluation
  • retrieval-augmented generation
  • selective prediction
  • Evaluates direct and revised answers for the same 25,870 held-out questions (NQ-Open, TriviaQA, PopQA).
  • Separates preserved, repaired, harmed, and unrecovered outcomes.
Paper arXiv