Heeseung Kwon
4 papers · 2020–2021 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ICCV (2)
ECCV (1)
NIPS (1)
Top co-authors
Keywords
video understanding
(2)
action recognition
(2)
motion information
(1)
motion representation
(1)
spatio-temporal self-similarity
(1)
neural block
(1)
relational embedding
(1)
cross-correlational attention
(1)
self-correlational representation
(1)
few-shot learning
(1)
relational self-attention
(1)
spatio-temporal relation
(1)
Papers
Relational Self-Attention: What's Missing in Attention for Video Understanding
NIPS 2021
Learning Self-Similarity in Space and Time As Generalized Motion for Video Action Recognition
ICCV 2021
Relational Embedding for Few-Shot Classification
ICCV 2021
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
ECCV 2020