Follow
Manjin Kim
Title
Cited by
Cited by
Year
Motionsqueeze: Neural motion feature learning for video understanding
H Kwon, M Kim, S Kwak, M Cho
Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020
1532020
Future transformer for long-term action anticipation
D Gong, J Lee, M Kim, SJ Ha, M Cho
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
632022
Learning self-similarity in space and time as generalized motion for video action recognition
H Kwon, M Kim, S Kwak, M Cho
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
462021
Relational self-attention: What's missing in attention for video understanding
M Kim, H Kwon, C Wang, S Kwak, M Cho
Advances in Neural Information Processing Systems 34, 8046-8059, 2021
412021
Learning correlation structures for vision transformers
M Kim, PH Seo, C Schmid, M Cho
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
52024
Electronic device and method with spatio-temporal self-similarity consideration
M Cho, K Heeseung, M Kim, K Suha
US Patent App. 17/977,449, 2024
2024
Learning Correlation Structures for Vision Transformers Supplementary Material
M Kim, PH Seo, C Schmid, M Cho
Relational Self-Attention: What’s Missing in Attention for Video Understanding Supplementary Material
M Kim, H Kwon, C Wang, S Kwak, M Cho
StructViT: Learning Correlation Structures for Vision Transformers
M Kim, PH Seo, C Schmid, M Cho
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition Supplementary Material
H Kwon, M Kim, S Kwak, M Cho
The system can't perform the operation now. Try again later.
Articles 1–10