nsamagic.blogg.se

HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling Junfeng Wu (Huazhong University of Science and Technology) Qihao Liu (Johns Hopkins University) Yi Jiang (Bytedance) Song Bai (University of Oxford) Alan Yuille (Johns Hopkins University) Xiang Bai (Huazhong University of Science and Technology)*

In Defense of Online Models for Video Instance Segmentation Jiajun Tang (Peking University) Yongjie Zhu (Beijing University of Posts and Telecommunications) Haoyu Wang (Peking University) Jun Hoong Chan (Peking University) Si Li (Beijing University of Posts and Telecommunications) Boxin Shi (Peking University)* Junfeng Wu (Huazhong University of Science and Technology) Yi Jiang (Bytedance) Song Bai (University of Oxford) Wenqing Zhang (Huazhong University of Science and Technology) Xiang Bai (Huazhong University of Science and Technology)*Įstimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation SeqFormer: Sequential Transformer for Video Instance Segmentation Towards Grand Unification of Object Trackingīin Yan (Dalian University of Technology)* Yi Jiang (Bytedance) Peize Sun (The University of Hong Kong) Dong Wang (Dalian University of Technology) Zehuan Yuan (Bytedance.Inc) Ping Luo (The University of Hong Kong) Huchuan Lu (Dalian University of Technology) Linfeng Zhang (Tsinghua University )* Xin Chen (Intel Corp.) Junbo Zhang (Tsinghua University) Runpei Dong (Xi’an Jiaotong University) Kaisheng Ma (Tsinghua University )