no code implementations • 22 Feb 2024 • Vuong D. Nguyen, Shishir K. Shah
Long-term Person Re-Identification (LRe-ID) aims at matching an individual across cameras after a long period of time, presenting variations in clothing, pose, and viewpoint.
no code implementations • 11 Feb 2024 • Samiha Mirza, Vuong D. Nguyen, Pranav Mantini, Shishir K. Shah
In the midst of the rapid integration of artificial intelligence (AI) into real world applications, one pressing challenge we confront is the phenomenon of model drift, wherein the performance of AI models gradually degrades over time, compromising their effectiveness in real-world, dynamic environments.
no code implementations • 6 Feb 2024 • Vuong D. Nguyen, Samiha Mirza, Pranav Mantini, Shishir K. Shah
Our ASGL framework improves Re-ID performance under clothing variations by learning clothing-invariant gait cues using a Spatial-Temporal Graph Attention Network (ST-GAT).
2 code implementations • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops 2024 • Vuong D. Nguyen, Pranav Mantini, Shishir K. Shah
In this work, we propose "Temporal 3D ShapE Modeling for VCCRe-ID" (SEMI), a lightweight end-to-end framework that addresses these issues by learning human 3D shape representations.
no code implementations • 11 Oct 2023 • Pranav Mantini, Shishir K. Shah
We formulate tampering detection as a time series analysis problem, and design experiments to study the robustness and capability of various feature types.
no code implementations • ICCV 2017 • Arko Barman, Shishir K. Shah
In this paper, we formulate an algorithm that maps the ranking process in a person re-identification algorithm to a problem in graph theory.
no code implementations • CVPR 2017 • Pengfei Dou, Shishir K. Shah, Ioannis A. Kakadiaris
Inspired by the success of deep neural networks (DNN), we propose a DNN-based approach for End-to-End 3D FAce Reconstruction (UH-E2FAR) from a single 2D image.
no code implementations • 7 Apr 2017 • Yuhang Wu, Shishir K. Shah, Ioannis A. Kakadiaris
Facial landmark localization is a fundamental module for pose-invariant face recognition.