Dejene M. Sime

According to our database, Dejene M. Sime authored at least 6 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Saliency-Guided Transformer Attention With Pixel-Level Contrastive Learning for Weakly Supervised Defect Localization.

Dejene M. Sime, Nan Ouyang, Kai Sheng, Getu T. Fellek, Wenkang Wan, Adnan A. Qaseem, Xiaojiang Ren, Shehui Bu

IEEE Trans. Ind. Informatics, April, 2026

DSTIFormer: Vehicle Trajectory Prediction Considering Dynamic Spatial-Temporal Interaction-Aware With Transformer Network.

Adnan A. Qaseem, Lei Ao, Kai Sheng, Dejene M. Sime, Qing Cai, Jianzhao Li, Xiaojiang Ren

IEEE Trans. Veh. Technol., March, 2026

2024

Deep learning-based automated steel surface defect segmentation: a comparative experimental study.

Dejene M. Sime, Guotai Wang, Zhi Zeng, Bei Peng

Multim. Tools Appl., January, 2024

2023

Uncertainty-aware and dynamically-mixed pseudo-labels for semi-supervised defect segmentation.

Dejene M. Sime, Guotai Wang, Zhi Zeng, Bei Peng

Comput. Ind., November, 2023

Semisupervised Defect Segmentation With Pairwise Similarity Map Consistency and Ensemble-Based Cross Pseudolabels.

Dejene M. Sime, Guotai Wang, Zhi Zeng, Wei Wang, Bei Peng

IEEE Trans. Ind. Informatics, 2023

Semi-supervised Defect Segmentation with Uncertainty-aware Pseudo-labels from Multi-branch Network.

Dejene M. Sime, Guotai Wang, Zhi Zeng, Bei Peng

Proceedings of the 5th International Conference on Image Processing and Machine Vision, 2023