![]() |
O-DRUM @ CVPR 2023Workshop on Open-Domain Reasoning Under Multi-Modal Settingscoming soon !!!MontrealODRUM 2022 Archive: [Webpage] YouTube |
In the past decade, there has been a paradigm shift in computer vision research -- the connection between language and vision is now an integral part of various of the philosophy of computer vision. Vision+Language models have not only impacted multimodal tasks but also a wide variety of tasks in fundamental computer vision and computer graphics. The link between vision and language is much more complex than simple image--text alignment -- language is used for reasoning beyond the visible (for example, physical reasoning, spatial reasoning, commonsense reasoning, and embodied reasoning). This is the challenging frontier that the computer vision community is gradually warming up to -- Open-Domain Reasoning in Multi-Modal Settings (ODRUM 2023) is an ideally-suited platform for discussions on multimodal (vision+language) topics with special emphasis on reasoning capabilities.
The aim of ODRUM 2023 is to address the emerging topic of visual reasoning using multiple modalities (such as text, images, videos, audio, etc.). The workshop will feature invited talks by experts at the forefront of research in the realm of reasoning such as: embodied AI and embodied navigation, learning via interaction and collaboration with humans, buildng large V+L that can perform multiple tasks, visual grounding and reasoning, and the use of language to instruct robots. At the end of the workshop, participants and speakers will converge for a panel discussion -- the panel will discuss the importance of reasoning (a core AI topic that has a rich and long history since the 1950s) to computer vision, and relevance to recent progress in visual reasoning. The panel will discuss trends and challenges in open-domain reasoning, from different perspectives of NLP, vision, machine learning, and robotics researchers.
![]() Tejas Gokhale ASU |
![]() Man Luo ASU |
![]() Yezhou Yang ASU |
![]() Chitta Baral ASU |
Kenneth Marino Deepmind |
![]() Pratyay Banerjee Amazon Alexa AI |
![]() Zhiyuan Fang Amazon Alexa AI |
Website maintained by Tejas Gokhale