ECCV 2024 Tutorial on Emerging Trends in Disentanglement and Compositionality

30 Sep 2024, 9AM-12PM

MiCo Milano

ECCV2024

Tutorial lecturers

Overview

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.

Schedule

09:00 am - 09:10 am Opening remarks, by Nicu Sebe
09:10 am - 09:40 am Equivariant and Disentangled Representation Learning, by Yue Song & Nicu Sebe [slides]
09:40 am - 10:30 am Emerging Trends in Disentanglement and Compositionality, by Xin Jin [slides]
10:30 am - 10:40 am Coffee break
10:40 am - 11:20 am Disentangled Model-Based Visual Concept Learning, by Tao Yang & Wenjun (Kevin) Zeng [slides]
11:20 am - 12:00 am Disentanglement and Composition for AGI, by Xingyi Yang & Jingwen Ye & Xinchao Wang & Shuicheng Yan [slides]

Contact

Please contact Xin Jin for general inquiries.

-->