MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based DecodersSep 29, 2024·Baijiong Lin,Weisen Jiang,Pengguang Chen,Yu Zhang,Shu LiuYing-Cong Chen· 0 min read Cite CodeType1PublicationProceedings of the European conference on computer vision (ECCV)Last updated on Jul 13, 2024 AuthorsYing-Cong ChenAssistant Professor ← Defect Spectrum: A Granular Look of Large-scale Defect Datasets with Rich Semantics Sep 29, 2024Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion Models Sep 29, 2024 →
·
0 min read