NeurIPS

Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark

DVSOD: RGB-D Video Salient Object Detection

Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection

Training saliency detection models with weak supervisions, e.g., image-level tags or captions, is appealing as it removes the costly demand of per-pixel annotations. Despite the rapid progress of RGB-D saliency detection in fully-supervised setting, …