LIU, Lihao; PROST, Jean; ZHU, Lei; PAPADAKIS, Nicolas; LIÒ, Pietro; SCHÖNLIEB, Carola-Bibiane; AVILES-RIVERO, Angelica I

Metadatos

Mostrar el registro completo del ítem

Licencia de uso del documento

LIU, Lihao
Department of Applied Mathematics and Theoretical Physics [Cambridge] [DAMTP]

PROST, Jean
Institut de Mathématiques de Bordeaux [IMB]

ZHU, Lei
Electronic and Computer Engineering Department [Hong Kong] [ECE]

Idioma

Communication dans un congrès

Este ítem está publicado en

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR'23), 2023-06-18, Vancouver. 2022-11-13

Resumen en inglés

Shadows in videos are difficult to detect because of the large shadow deformation between frames. In this work, we argue that accounting for the shadow deformation is essential when designing a video shadow detection method. To this end, we introduce the shadow deformation attention trajectory (SODA), a new type of video self-attention module, specially designed to handle the large shadow deformations in videos. Moreover, we present a shadow contrastive learning mechanism (SCOTCH) which aims at guiding the network to learn a high-level representation of shadows, unified across different videos. We demonstrate empirically the effectiveness of our two contributions in an ablation study. Furthermore, we show that SCOTCH and SODA significantly outperforms existing techniques for video shadow detection. Code will be available upon the acceptance of this work.< Leer menos

URI

https://oskar-bordeaux.fr/handle/20.500.12278/190684

Proyecto europeo

Nonlocal Methods for Arbitrary Data Sources

Orígen

Importado de Hal

Centros de investigación

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251