6 papers · 1 filter
SoccerNet 2026 Challenges Results
Anthony Cioppa, Silvio Giancola, Håkan Ardö +102
The SoccerNet 2026 Challenges constitute the sixth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in sports video underst…
GUNNEL: Guided Mixup Augmentation and Multi-Model Fusion for Aquatic Animal Segmentation
Minh-Quan Le, Trung-Nghia Le, Tam V. Nguyen +2
Recent years have witnessed great advances in object segmentation research. In addition to generic objects, aquatic animals have attracted research attention. Deep learning-based m…
NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
Shuhao Han, Haotian Fan, Fangyuan Kong +112
This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoratio…
CamoFA: A Learnable Fourier-based Augmentation for Camouflage Segmentation
Minh-Quan Le, Minh-Triet Tran, Trung-Nghia Le +2
Camouflaged object detection (COD) and camouflaged instance segmentation (CIS) aim to recognize and segment objects that are blended into their surroundings, respectively. While se…
SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation
Quoc-Huy Trinh, Hai-Dang Nguyen, Bao-Tram Nguyen Ngoc +3
Polyp segmentation, a critical concern in medical imaging, has prompted numerous proposed methods aimed at enhancing the quality of segmented masks. While current state-of-the-art…
PGDS: Pose-Guidance Deep Supervision for Mitigating Clothes-Changing in Person Re-Identification
Quoc-Huy Trinh, Nhat-Tan Bui, Dinh-Hieu Hoang +6
Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retri…