Learning Spatiotemporal Features with 3D Convolutional Networks
2015 · 9,488 citations
https://doi.org/10.1109/iccv.2015.510
L
Lorenzo Torresani
Claim or correct this author profile
Claim this profile or suggest corrections to the name, affiliation, bio, photo, or paper titles. Approved changes appear as verified CitedEvidence overlays.
198
Papers
25.3K
Citations
52
h-index
106
i10-index
Lorenzo Torresani is an academic researcher from University of Stuttgart. The author has contributed to research in topics: Human Pose and Action Recognition & Multimodal Machine Learning Applications & Domain Adaptation and Few-Shot Learning. The author has an h-index of 52, co-authored 169 publications.
Papers by this author
worksA Closer Look at Spatiotemporal Convolutions for Action Recognition
2018 · 3,423 citations
https://doi.org/10.1109/cvpr.2018.00675
Is Space-Time Attention All You Need for Video Understanding?
2021 · arXiv (Cornell University) · 1,287 citations
https://doi.org/10.48550/arxiv.2102.05095
Video Classification With Channel-Separated Convolutional Networks
2019 · 620 citations
https://doi.org/10.1109/iccv.2019.00565
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection
2015 · 525 citations
https://doi.org/10.1109/cvpr.2015.7299067
Ego4D: Around the World in 3,000 Hours of Egocentric Video
2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 480 citations
https://doi.org/10.1109/cvpr52688.2022.01842
Research topics
topicsChat about Author
Papers
Chat
Click to start Chat