Skip to content

Anh Totti Nguyen

Associate Professor of Computer Science, Auburn University

  • Current Page Parent Research
  • Lab
  • Press
  • Work with me
  • Teaching
    • Courses
    • K-6 AI club
  • About
  • CV
  • Current Page Parent Research
  • Lab
  • Press
  • Work with me
  • Teaching
    • Courses
    • K-6 AI club
  • About
  • CV

change-detection-teaser

May 2025 0

At an optimal confidence threshold, CYWS [25] (top row) sometimes still produces false positives—□ in (a) & (c)—and fails to detect changes (a). Dashed - - - boxes show groundtruth changes. First, we encourage detectors to be more aware of changes via a novel contrastive loss. Second, our Hungarian-based post-processing reduces false positives (a), improves change-detection accuracy (b), and estimates correspondences (c–d), i.e., paired changes such as (□, □) and (□, □). Our work (bottom row) is the first to estimate change correspondences compared to prior works [25, 26, 40] (top row).

Share
  • Previous Improving zero-shot object-level change detection by incorporating visual correspondence
IE z-index bug
CSS

IE z-index bug

  • August 5, 2010
  • 1
A modular wearable 3D input device
Arduino C++ Hardware

A modular wearable 3D input device

  • July 6, 2014
  • 3
It’s time to blog now..
Uncategorized

It’s time to blog now..

  • December 4, 2009
  • 2
The interesting javascript window object
Javascript

The interesting javascript window object

  • February 28, 2010
  • 1

Anh Totti Nguyen © 2026. All Rights Reserved.

Powered by WordPress. Theme by Alx.