ECCV 2024 Tutorial on Emerging Trends in Disentanglement and Compositionality

29 Sep 2024, 9AM-12PM

MiCo Milano


Tutorial lecturers


Participants will learn about advanced techniques and models that allow for the disentanglement of visual factors in images and the compositionality of these factors to produce more meaningful representations. Disentanglement and Composition are believed to be one of the possible ways for AI to fundamentally understand the world, and eventually achieve Artificial General Intelligence (AGI). Specifically, we will cover the following topics:Session #1: Disentangled Representation Learning (DRL); Session #2: Latent Semantics Discovery; Session #3: Disentanglement and Equivariance; Session #4: Composition and Disentanglement for AGI.


09:00 am - 09:10 am Opening remarks, by Xin Jin
09:10 am - 09:50 am Disentanglement Representation Learning (DRL) and Latent Semantics Discovery, by Xin Jin & Tao Yang & Wenjun (Kevin) Zeng [slides-a & video-a, slides-b & video-b]
09:50 am - 10:30 am Disentanglement and Equivariance, by Yue Song & Jingwen Ye & Nicu Sebe [slides]
10:30 am - 10:40 am Coffee break
10:40 am - 11:20 am Disentanglement and Composition for AGI, by Xingyi Yang & Xinchao Wang & Shuicheng Yan [slides]
11:20 am - 12:00 pm TBD, by TBD [slides-a]


Please contact Xin Jin for general inquiries.