Huang, Yu YaoYu YaoHuangJIAN-JIUN DINGHua, Shiang ChihShiang ChihHua2024-03-072024-03-072023-01-019798350359855https://scholars.lib.ntu.edu.tw/handle/123456789/640569Salient object detection (SOD) is a preprocessing step for several computer vision techniques, including visual tracking, image captioning, image segmentation, and so on. In this work, several techniques are adopted to improve the accuracy of SOD. Instead of directly using edge maps as guidance, we improve the adaptive two-stream encoder by employing a clever technique to generate body maps and detail maps, which can provide much information for the final predictions. Regarding body maps and detail maps, different parameter contrasts are provided for users to choose the desired results. Compared to state-of-The-Art SOD algorithms, our method outperforms almost all other methods on twelve datasets under two evaluation metrics.body map | detail map | edge map | salient object detection[SDGs]SDG13conference paper10.1109/VCIP59821.2023.104026942-s2.0-85184856390https://api.elsevier.com/content/abstract/scopus_id/85184856390