Segui
AJ Piergiovanni
AJ Piergiovanni
Email verificata su google.com - Home page
Titolo
Citata da
Citata da
Anno
Representation flow for action recognition
AJ Piergiovanni, MS Ryoo
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019
1142019
Evolving losses for unsupervised video representation learning
AJ Piergiovanni, A Angelova, MS Ryoo
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
982020
Assemblenet: Searching for multi-stream neural connectivity in video architectures
MS Ryoo, AJ Piergiovanni, M Tan, A Angelova
arXiv preprint arXiv:1905.13209, 2019
802019
Learning latent super-events to detect multiple activities in videos
AJ Piergiovanni, MS Ryoo
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018
752018
Evolving space-time neural architectures for videos
AJ Piergiovanni, A Angelova, A Toshev, MS Ryoo
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
622019
Fine-grained activity recognition in baseball videos
AJ Piergiovanni, MS Ryoo
Proceedings of the ieee conference on computer vision and pattern …, 2018
582018
Temporal gaussian mixture layer for videos
AJ Piergiovanni, M Ryoo
International Conference on Machine learning, 5152-5161, 2019
572019
Learning latent subevents in activity videos using temporal attention filters
A Piergiovanni, C Fan, M Ryoo
Proceedings of the AAAI Conference on Artificial Intelligence 31 (1), 2017
532017
Attentionnas: Spatiotemporal attention cell search for video classification
X Wang, X Xiong, M Neumann, AJ Piergiovanni, MS Ryoo, A Angelova, ...
European Conference on Computer Vision, 449-465, 2020
342020
Tiny video networks
AJ Piergiovanni, A Angelova, MS Ryoo
Applied AI Letters 3 (1), e38, 2022
322022
Learning real-world robot policies by dreaming
AJ Piergiovanni, A Wu, MS Ryoo
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2019
322019
Assemblenet++: Assembling modality representations via attention connections
MS Ryoo, AJ Piergiovanni, J Kangaspunta, A Angelova
European Conference on Computer Vision, 654-671, 2020
232020
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
MS Ryoo, AJ Piergiovanni, A Arnab, M Dehghani, A Angelova
arXiv preprint arXiv:2106.11297, 2021
222021
Avid dataset: Anonymized videos from diverse countries
AJ Piergiovanni, M Ryoo
Advances in Neural Information Processing Systems 33, 16711-16721, 2020
212020
Tokenlearner: Adaptive space-time tokenization for videos
M Ryoo, AJ Piergiovanni, A Arnab, M Dehghani, A Angelova
Advances in Neural Information Processing Systems 34, 12786-12797, 2021
132021
Model-based behavioral cloning with future image similarity learning
A Wu, AJ Piergiovanni, MS Ryoo
Conference on Robot Learning, 1062-1077, 2020
122020
Adversarial generative grammars for human activity prediction
AJ Piergiovanni, A Angelova, A Toshev, MS Ryoo
European Conference on Computer Vision, 507-523, 2020
112020
4d-net for learned multi-modal alignment
AJ Piergiovanni, V Casser, MS Ryoo, A Angelova
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
102021
Learning shared multimodal embeddings with unpaired data
AJ Piergiovanni, MS Ryoo
CoRR, 2018
102018
Temporal attention filters for human activity recognition in videos
A Piergiovanni, C Fan, MS Ryoo
arXiv preprint arXiv:1605.08140, 2016
102016
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–20