Follow
Karttikeya Mangalam
Karttikeya Mangalam
Verified email at berkeley.edu - Homepage
Title
Cited by
Cited by
Year
Multiscale vision transformers
H Fan*, B Xiong*, K Mangalam*, Y Li*, Z Yan, J Malik, C Feichtenhofer*
IEEE Conference on Computer Vision and Pattern Recognition, 2021
10482021
Ego4d: Around the world in 3,000 hours of egocentric video
K Grauman, A Westbury, E Byrne, Z Chavis, A Furnari, R Girdhar, ...
IEEE Conference on Computer Vision and Pattern Recognition, 2022
5172022
Mvitv2: Improved multiscale vision transformers for classification and detection
Y Li, CY Wu, H Fan, K Mangalam, B Xiong, J Malik, C Feichtenhofer
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
4892022
It is not the journey but the destination: Endpoint conditioned trajectory prediction
K Mangalam, H Girase, S Agarwal, KH Lee, E Adeli, J Malik, A Gaidon
European Conference on Computer Vision, 2020
3732020
Long-term human motion prediction with scene context
Z Cao, H Gao, K Mangalam, QZ Cai, M Vo, J Malik
European Conference on Computer Vision, 2020
2032020
From goals, waypoints & paths to long term human trajectory forecasting
K Mangalam, Y An, H Girase, J Malik
IEEE International Conference on Computer Vision, 2021
2022021
Future person localization in first-person videos
T Yagi, K Mangalam, R Yonetani, Y Sato
IEEE Conference on Computer Vision and Pattern Recognition, 2018
2022018
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
CY Wu*, Y Li*, K Mangalam, H Fan, B Xiong, J Malik, C Feichtenhofer*
arXiv preprint arXiv:2201.08383, 2022
1352022
Object-region video transformers
R Herzig, E Ben-Avraham, K Mangalam, A Bar, G Chechik, A Rohrbach, ...
IEEE Conference on Computer Vision and Pattern Recognition, 2022
662022
LOKI: Long Term and Key Intentions for Trajectory Prediction
H Girase, H Gang, S Malla, J Li, A Kanehara, K Mangalam, C Choi
IEEE International Conference on Computer Vision, 2021
632021
Disentangling human dynamics for pedestrian locomotion forecasting with noisy supervision
K Mangalam, E Adeli, KH Lee, A Gaidon, JC Niebles
IEEE Winter Conference on Applications of Computer Vision, 2020
622020
Squeezeformer: An efficient transformer for automatic speech recognition
S Kim, A Gholami, A Shaw, N Lee, K Mangalam, J Malik, MW Mahoney, ...
Advances in Neural Information Processing Systems 35, 9361-9373, 2022
562022
Do deep neural networks learn shallow learnable examples first?
K Mangalam, VU Prabhu
Understanding Deep Phenomena, International Conference on Machine Learning, 2019
392019
Reversible vision transformers
K Mangalam, H Fan, Y Li, CY Wu, B Xiong, C Feichtenhofer, J Malik
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
382022
Sequential modeling enables scalable learning for large vision models
Y Bai, X Geng, K Mangalam, A Bar, A Yuille, T Darrell, J Malik, AA Efros
arXiv preprint arXiv:2312.00785, 2023
262023
Learning spontaneity to improve emotion recognition in speech
K Mangalam, T Guha
Interspeech, 2018
202018
Diffusion models as masked autoencoders
C Wei, K Mangalam, PY Huang, Y Li, H Fan, H Xu, H Wang, C Xie, ...
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
192023
Egoschema: A diagnostic benchmark for very long-form video language understanding
K Mangalam, R Akshulakov, J Malik
Advances in Neural Information Processing Systems 36, 2024
182024
On compressing u-net using knowledge distillation
K Mangalam, M Salzamann
arXiv preprint arXiv:1812.00249, 2018
172018
Big little transformer decoder
S Kim, K Mangalam, J Malik, MW Mahoney, A Gholami, K Keutzer
arXiv preprint arXiv:2302.07863, 2023
152023
The system can't perform the operation now. Try again later.
Articles 1–20