Picture for Manjin Kim

Manjin Kim

Learning Correlation Structures for Vision Transformers

Add code
Apr 05, 2024
Viaarxiv icon

Future Transformer for Long-term Action Anticipation

Add code
May 27, 2022
Figure 1 for Future Transformer for Long-term Action Anticipation
Figure 2 for Future Transformer for Long-term Action Anticipation
Figure 3 for Future Transformer for Long-term Action Anticipation
Figure 4 for Future Transformer for Long-term Action Anticipation
Viaarxiv icon

Relational Self-Attention: What's Missing in Attention for Video Understanding

Add code
Nov 02, 2021
Figure 1 for Relational Self-Attention: What's Missing in Attention for Video Understanding
Figure 2 for Relational Self-Attention: What's Missing in Attention for Video Understanding
Figure 3 for Relational Self-Attention: What's Missing in Attention for Video Understanding
Figure 4 for Relational Self-Attention: What's Missing in Attention for Video Understanding
Viaarxiv icon

Learning Self-Similarity in Space and Time as Generalized Motion for Action Recognition

Add code
Feb 14, 2021
Figure 1 for Learning Self-Similarity in Space and Time as Generalized Motion for Action Recognition
Figure 2 for Learning Self-Similarity in Space and Time as Generalized Motion for Action Recognition
Figure 3 for Learning Self-Similarity in Space and Time as Generalized Motion for Action Recognition
Figure 4 for Learning Self-Similarity in Space and Time as Generalized Motion for Action Recognition
Viaarxiv icon

MotionSqueeze: Neural Motion Feature Learning for Video Understanding

Add code
Jul 20, 2020
Figure 1 for MotionSqueeze: Neural Motion Feature Learning for Video Understanding
Figure 2 for MotionSqueeze: Neural Motion Feature Learning for Video Understanding
Figure 3 for MotionSqueeze: Neural Motion Feature Learning for Video Understanding
Figure 4 for MotionSqueeze: Neural Motion Feature Learning for Video Understanding
Viaarxiv icon