Davide Modolo
Davide Modolo
Senior Research Scientist at Amazon Web Services (AWS)
Verified email at amazon.com - Homepage
Title
Cited by
Cited by
Year
Do semantic parts emerge in Convolutional Neural Networks?
A Gonzalez-Garcia, D Modolo, V Ferrari
International Journal of Computer Vision (IJCV), 2017
942017
Action Recognition with Spatial-Temporal Discriminative Filter Banks
B Martinez, D Modolo, Y Xiong, J Tighe
International Conference on Computer Vision (ICCV), 2019
482019
Explorative visualization and analysis of a social network for arts: the case of deviantART
B Buter, N Dijkshoorn, D Modolo, Q Nguyen, S van Noort, B van de Poel, ...
Journal of Convergence Volume 2 (1), 2011
382011
Multi-Scale Attention Network for Crowd Counting
R Rama Varior, B Shuai, J Tighe, D Modolo
arXiv preprint arXiv:1901.06026, 2019
292019
Combining detection and tracking for human pose estimation in videos
M Wang, J Tighe, D Modolo
IEEE Computer Vision and Patter Recognition (CVPR), 2020
212020
DeviantArt in spotlight: A network of artists
AA Salah, AA Salah, B Buter, N Dijkshoorn, D Modolo, Q Nguyen, ...
Leonardo 45 (5), 486-487, 2012
172012
Joint calibration of Ensemble of Exemplar SVMs.
D Modolo, A Vezhnevets, O Russakovsky, V Ferrari
IEEE Computer Vision and Pattern Recognition (CVPR), 2015
142015
Multi-object tracking with siamese track-rcnn
B Shuai, AG Berneshawi, D Modolo, J Tighe
arXiv preprint arXiv:2004.07786, 2020
132020
Context Forest for Object Class Detection
D Modolo, A Vezhnevets, V Ferrari
British Machine Vision Conference (BMVC), 2015
13*2015
Learning Semantic Part-Based Models from Google Images
D Modolo, V Ferrari
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 40 (6, 2018
122018
Objects as Context for detecting their Semantic Parts
A Gonzalez-Garcia, D Modolo, V Ferrari
Computer Vision and Patter Recognition (CVPR), 2018
11*2018
SiamMOT: Siamese Multi-Object Tracking
B Shuai, A Berneshawi, X Li, D Modolo, J Tighe
IEEE Computer Vision and Pattern Recognition (CVPR), 2021
32021
Exploiting weakly supervised visual patterns to learn from partial annotations
K Kundu, E Bas, M Lam, H Chen, D Modolo, J Tighe
Advances in Neural Information Processing Systems (NeurIPS), 2020
32020
Application of Multi-Object Tracking with Siamese Track-RCNN to the Human in Events Dataset
B Shuai, A Berneshawi, M Wang, C Liu, D Modolo, X Li, J Tighe
Proceedings of the 28th ACM International Conference on Multimedia, 4625-4629, 2020
22020
MoDist: Motion Distillation for Self-supervised Video Representation Learning
F Xiao, J Tighe, D Modolo
arXiv preprint arXiv:2106.09703, 2021
12021
Selective Feature Compression for Efficient Activity Recognition Inference
C Liu, X Li, H Chen, D Modolo, J Tighe
arXiv preprint arXiv:2104.00179, 2021
12021
Can object detectors aid Internet video event retrieval?
D Modolo, CGM Snoek
Multimedia Content and Mobile Devices 8667, 866707, 2013
12013
Off-line cursive handwritten word recognition using hidden Markov models
D Modolo, T Kooi
Available at www. ai-project-11. googlecode. com/svn, 0
1
Efficient identification of objects in videos using motion information
A Olgiati, N Singhal, Y Natanzon, V Manohar, D Modolo
US Patent 11,126,854, 2021
2021
Multi-Object Tracking with Hallucinated and Unlabeled Videos
D McKee, B Shuai, A Berneshawi, M Wang, D Modolo, S Lazebnik, ...
arXiv preprint arXiv:2108.08836, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–20