Selected Publications

Selected Publications

• CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
  Jiachen Li, Xinyao Wang, Sijie Zhu, Chia-wen Kuo, Lu Xu, Fan Chen, Jitesh Jain, Humphrey Shi, Longyin Wen
  NeurIPS 2024
  [Paper] [Project Page] [Code]

• Matting Anything
  Jiachen Li, Jitesh Jain, Humphrey Shi
  CVPRW 2024
  [Paper] [Demo] [Code]

• Video Instance Matting
  Jiachen Li, Roberto Henschel, Vidit Goel, Marianna Ohanyan, Shant Navasardyan, Humphrey Shi
  WACV 2024
  [Paper] [Code]

• VMFormer: End-to-End Video Matting with Transformer
  Jiachen Li, Vidit Goel, Marianna Ohanyan, Shant Navasardyan, Yunchao Wei, Humphrey Shi
  WACV 2024
  [Paper] [Project] [Code]

• Neighborhood Attention Transformer
  Ali Hassani, Steven Walton, Jiachen Li, Shen Li, Humphrey Shi
  CVPR 2023
  [Paper] [Code]

• OneFormer: One Transformer to Rule Universal Image Segmentation
  Jitesh Jain, Jiachen Li, MangTik Chiu, Ali Hassani, Nikita Orlov, Humphrey Shi
  CVPR 2023
  [Paper] [Project] [Code]

• VideoMatt: A Simple Baseline for Accessible Real-Time Video Matting
  Jiachen Li, Marianna Ohanyan, Vidit Goel, Shant Navasardyan, Yunchao Wei, Humphrey Shi
  CVPRW 2023
  [Paper]

• ConvMLP: Hierarchical Convolutional MLPs for Vision
  Jiachen Li, Ali Hassani, Steven Walton, Humphrey Shi
  CVPRW 2023
  [Paper] [Code]

• Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
  Jiachen Li , Bowen Cheng, Rogerio Feris, Jinjun Xiong, Thomas S.Huang, Wen-Mei Hwu, Humphrey Shi
  CVPRW 2021
  [Paper] [Code]

• RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection
  Jiachen Li , Yuan Lin, Rongrong Liu, Chiuman Ho and Humphrey Shi
  CVPRW 2021
  [Paper]

Competitions

• 3rd Place in CVPR 2021 Video-Instacne-Segmentation Challenge @ PAIR Team
  [Tech Report]

• 1st Place in DAC-SDC 2019 Low Power Object Detection Challenge @ IBM C3SR Team
  [Tech Report]

• 1st Place in all tasks of ICDAR 2019 RRC on Multi-lingual Scene Text Detection and Recognition @ Tencent-DPPR Team
  [Tech Report]

• 1st Place in all tasks of ICDAR 2019 RRC on Large-scale Street View Text with Partial Labeling @ Tencent-DPPR Team
  [Tech Report]