博士后招聘

可乐实验室招聘博士后,有意者请联系liusi@buaa.edu.cn

NEWS

  • One TPAMI paper <<FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation>> accepted
  • One TPAMI paper <<Multi-Person Pose Regression with Distribution-Aware Single-Stage Models>> accepted
  • 1 paper is accepted by ICRA 2024
  • 2 papers are accepted by ICLR 2024
  • One TPAMI paper <<Teach-DETR: Better Training DETR with Teachers>> accepted
  • Prof. Liu will serve as Reviewer for ICML 2024
  • Prof. Liu serves as Area Chair for ECCV 2024
  • One TPAMI paper <<Delving into the Devils of Bird’s-eye-view Perception: A Review, Evaluation and Recipe>> accepted
  • One TPAMI paper <<Room-Object Entity Prompting and Reasoning for Embodied Referring Expression>> accepted
  • 1 paper is accepted by NeurIPS 2023
  • 3 papers are accepted by ACM MM 2023
  • 4 papers are accepted by ICCV 2023
  • Prof. Liu serves as Area Chair for NeurIPS 2023
  • We release the Person In Contex(PIC) dataset, which contains 17,122 high-resolution images and densely annotated entity segmentation and relations. [Link][pwd:pic]
  • CoLab team and Baidu inc won the CVPR 2023 “Anti-uav” UAV Tracking Challenge. [certificate]
  • 6 papers are accepted by CVPR 2023
  • One TPAMI paper <<Language-Aware Spatial-Temporal Collaboration for Referring Video Segmentation >> accepted
  • Prof. Liu was named 2022 Outstanding Associate Editor of TMM[certificate]
  • Prof. Liu serves as Area Chair for CVPR 2023
  • 2 papers are accepted by ECCV 2022
  • Prof. Liu serves as Area Chair for ACCV 2022
  • 3 papers (including 1 oral paper) are accepted by ACM MM 2022
  • CoLab team and Xiaomi Tech won the CVPR 2022 "SoundSpaces" Audio-visual Navigation Challenge. [certificate]
  • One TIP paper <<Progressive Language-customized Visual Feature Learning for One-stage Visual Grounding>> accepted
  • 5 papers (including 1 oral paper) are accepted by CVPR 2022
  • Prof. Liu serves as Area Chair for ECCV 2022
  • Prof. Liu serves as Area Chair for ACM MM 2022
  • Prof. Liu serves as Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology
  • 我组本科实习生何泽欣、朱乐岩的“关联信息可控的视频背景音乐生成问题”项目荣获教育部首届“提问与猜想”活动一等奖
  • Prof. Liu won the Excellent Instructor Award for Feng Ru Cup--北航冯如杯优秀指导教师[certificate]
  • The paper <<Video Background Music Generation with Controllable Music Transformer>> from Colab Beihang University, Charterhouse School and Sea AI Lab wins ACM MM 2021 Best Paper Award [Image] [Link] [certificate]
  • One NeurIPS paper <<Mining the Benefits of Two-stage and One-stage HOI Detection>> accepted
  • Prof. Liu serves as Associate Editor for IEEE Transactions on Multimedia
  • One ICCV paper <<Language-Guided Global Image Editing via Cross-Modal Cyclic Mechanism>> accepted
  • Prof. Liu and Alibaba group won the CVPR 2021 VizWiz Captioning Challenge [certificate]
  • 2 papers are accepted by ACM MM 2021
  • Shangzhe Di, Zeren Jiang, Zhaokai Wang, Leyan Zhu, Zexin He got the Best Video Award of IJCAI 2021 Video Competition. [certificate]
  • Prof. Liu and Alibaba group won the CVPR 2021 Home Action Genome Scene-graph Generation competition [certificate]
  • Our intern Zhaokai Wang and Sihan Qian win the first price of the 31st Fengru Cup competition--北航冯如杯一等奖 (全校共19个).[certificate]
  • Prof. Liu serves as Area Chair for PRCV 2021 and ICIG 2021
  • One TCSVT paper <<Human-centric Spatio-Temporal Video Grounding With Visual Transformers>>accepted
  • One TPAMI paper <<PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal>> accepted
  • One TPAMI paper <<Cross-Modal Progressive Comprehension for Referring Segmentation>> accepted
  • One TPAMI paper <<Human-centric Relation Segmentation: Dataset and Solution >> accepted
  • Prof. Liu will serve as Reviewer for NeurIPS 2021, Area Chair for ACM MM 2021 and TPC member for UAI 2021
  • 5 papers(including 2 oral papers) are accepted by CVPR 2021
  • One TPAMI paper <<Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding >> accepted
  • About Us

    Contact Email: liusi@buaa.edu.cn
    CoLab (Cola Laboratory,可乐实验室) is founded on June 12th 2016.We focus on developing human-centric image/video understanding techniques, including human parsing,human pose estimation, human attribute prediction, people re-id etc.
    CoLab is interested in applying the CV techniques to real applications, such as intelligent makeup system and surveillance video analysis.
    京ICP备2022014557号-1