IEEE/CVF ICCV 2023
2nd – 6th October 2023 - Paris, France
We are presenting 3 main conference papers and 1 workshop's challenge winning technical report.| Wednesday, October 4, 2023 10:30AM–12:30PM CET - Posters (Room Foyer Sud)
• We present a method to generate a temporally-coherent sequence of images corresponding to sentences.

Story Visualization by Online Text Augmentation with Context Memory
Daechul Ahn, Daneul Kim, Gwangmo Song, Seung Hwan Kim, Honglak Lee, Dongyeop Kang, Jonghyun Choi
ICCV 2023
PDF (arXiv) · Project Page · Code| Thursday, October 5, 2023 10:30AM–12:30PM CET - Posters (Room Foyer Sud)
• We present a new embodied agent that remembers the consequences of previous actions and use them for better planning next actions.
(CVPR'23 Embodied AI workshop - 'Generalist Language Grounding Agents Challenge' Winner)

Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents
Byeonghwi Kim, Jinyeon Kim, Yuyeong Kim, Cheolhong Min, Jonghyun Choi
ICCV 2023
(CVPR 2023 Embodied AI Workshop - 1st Place Winner)
PDF (arXiv) ·
Project Page ·
CVPR 2023 Workshop Challenge Page
• We present a new continual learning setup that assumes to know hierarchies of classes in the previous and the currently given tasks.
(Collaborated with SNU ICL.)

Online Continual Learning on Hierarchical Label Expansion
Byung Hyun Lee, Okchul Jung, Jonghyun Choi, Se Young Chun
ICCV 2023
PDF (arXiv) · Project Page · Code| Monday, October 2, 2023 11:30AM-12:00PM CET - Room E04
Visual Continual Learning Workshop
• We present a new method for Challenge B - Continual Test-time Adaptation for Object Detection. (challenge winner)

TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions
Dongjae Jeon, Taeheon Kim, Seongwon Jo, Minhyuk Seo, Jonghyun Choi
Technical Report - ICCV Workshop on Visual Continual Learning 2023
PDFACM MobiCom 2023
2nd – 6th October 2023 - Madrid, Spain
We are presenting 1 main conference paper.| Thursday, October 5, 2023 17:30–18:30 CET - Poster 3.1 (Halls B2-C)
• We present a continual learning system that is computationally efficient.

Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
Xinyue Ma, Suyeon Jeong, Minjia Zhang, Di Wang, Jonghyun Choi, Myeongjae Jeon