Toggle navigation
Karttikeya Mangalam
Home
Publications
Projects
1
Reversible Vision Transformers
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
Improved Multiscale Vision Transformers for Classification and Detection
Multiscale Vision Transformers
LOKI: Long Term and Key Intentions for Trajectory Prediction
Overcoming Mode Collapse with Adaptive Multi Adversarial Training
Object-Region Video Transformers
Long-term Human Motion Prediction with Scene Context
Future Person Localization in First-Person Videos
Learning Spontaneity to Improve Emotion Recognition in Speech
Next »