Tutorials

Half-day

Oct. 2nd am

• End-to-End Learned Image and Video Compression: Design, Implementation, and Computer Vision Applications
  @room W08

  Wen-Hsiao Peng (National Yang Ming Chiao Tung University), Heming Sun (Yokohama National University)

• OpenMMLab: Open-source Platform for Vision, Language and Generative AI
  @room P02

  Kai Chen (Shanghai AI Laboratory), Wenwei Zhang (Nanyang Technological University), Songyang Zhang (Shanghai AI Laboratory), Yanhong Zeng (Shanghai AI Laboratory), Conghui He (Shanghai AI Laboratory)

• Visual Recognition Beyond the Comfort Zone: Adapting to Unseen Concepts on the Fly
  @room S04

  Aishwarya Agrawal (University of Montreal, Mila), Tyler L Hayes (NAVER LABS Europe), Zsolt Kira (Georgia Tech), Massimiliano Mancini (University of Trento), Riccardo Volpi (NAVER LABS Europe)

Oct. 2nd pm

• Camera Geometry Problems in Computer Vision
  @room W07

  Zuzana Kukelova (Czech Technical University), Daniel Barath (ETH Zurich), Viktor Larsson (Lund University), Tomas Pajdla (CTU), Torsten Sattler (CTU)

• Mixed-Reality for Biomedical Image Analysis and Clinical Neurosciences
  @room W08

  Johannes C. Paetzold (Imperial College London), Kaiyuan Yang (University of Zurich), Bjoern Menze (University of Zurich), Daniel Rueckert (Imperial College London), Ali Erturk (University of Munich), Rami Al-Maskari (University of Munich), Fabio Musio (University of Zurich), Izabela Horvath (University of Munich), Luciano Hoeher (University of Munich), Martin Menten (Imperial College London)

• Self-Supervised Learning of Visual Representations
  @room P02

  Christoph Feichtenhofer (Meta AI), Xinlei Chen (Meta AI), Piotr Dollár (Meta AI), Ross Girshick (Meta AI), Kaiming He (Meta AI)

Oct. 3rd am

• The Many Faces of Reliability of Deep Learning for Real-World Deployment
  @room S05

  Andrei Bursuc (valeo.ai), Tuan-Hung Vu (valeo.ai), Sharon Yixuan Li (UW-Madison), Dengxin Dai (MPI), Puneet K. Dokania (University of Oxford), Patrick Perez (valeo.ai)

Oct. 3rd pm

• Backdoor Learning: Recent Advances and Future Trends
  @room W08

  Baoyuan Wu (CUHK-Shenzhen), Bernard Ghanem (KAUST), Hasan Hammoud (KAUST)

• Understanding the In-Camera Rendering Pipeline and the role of AI/Deep Learning
  @room S06

  Michael S. Brown (York University)

Full-day

Oct. 3rd

• Learning with Noisy and Unlabeled Data for Large Models beyond Categorization
  @room P02

  Sifei Liu (NVIDIA), Hongxu Yin (NVIDIA), Shalini De Mello (NVIDIA), Pavlo Molchanov (NVIDIA), Jose M. Alvarez (NVIDIA), Jan Kautz (NVIDIA), Xiaolong Wang (UC San Diego), Anima Anandkumar (NVIDIA), Ming-Hsuan Yang (UC Merced), Trevor Darrell (UC Berkeley)