← Search

Duowang Zhu

2 accepted papers

2025

Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective

CVPR 2025highlight

In this paper, we present Change3D, a framework that reconceptualizes the change detection and captioning tasks through video modeling. Recent methods have achieved remarkable success by regarding each pair of bi-temporal images as separate frames. They employ a shared-weight image encoder to extrac…

2021

Context-Sensitive Temporal Feature Learning for Gait Recognition

ICCV 2021poster

Although gait recognition has drawn increasing research attention recently, it remains challenging to learn discriminative temporal representation since the silhouette differences are quite subtle in spatial domain. Inspired by the observation that humans can distinguish gaits of different subjects…

Cited by 169PDFcodeScholar