no code implementations • 29 May 2024 • Tianrun Chen, Chunan Yu, Jing Li, Jianqi Zhang, Lanyun Zhu, Deyi Ji, Yong Zhang, Ying Zang, Zejian Li, Lingyun Sun
We design a simple baseline method, Reasoning3D, with the capability to understand and execute complex commands for (fine-grained) segmenting specific parts for 3D meshes with contextual awareness and reasoned answers for interactive segmentation.
1 code implementation • 18 Apr 2023 • Tianrun Chen, Lanyun Zhu, Chaotao Ding, Runlong Cao, Yan Wang, Zejian Li, Lingyun Sun, Papa Mao, Ying Zang
We can even outperform task-specific network models and achieve state-of-the-art performance in the task we tested: camouflaged object detection, shadow detection.
no code implementations • CVPR 2022 • Pei Chen, Yangkang Zhang, Zejian Li, Lingyun Sun
When given new training samples annotated with novel semantic classes, the models should be trained from scratch with both learned and new classes.
1 code implementation • ICCV 2021 • Zejian Li, Jingyu Wu, Immanuel Koh, Yongchuan Tang, Lingyun Sun
Object masks are generated separately and mapped to bounding boxes to form a whole semantic segmentation mask (layout-to-mask), with which a new image is generated (mask-to-image).
1 code implementation • 25 Apr 2018 • Zejian Li, Yongchuan Tang, Yongxing He
The analogy is one of the typical cognitive processes, and our proposed strategy is based on the observation that sample pairs in which one is different from the other in one specific generative factor show the same analogical relation.