Follow
Swathikiran Sudhakaran
Swathikiran Sudhakaran
Samsung AI Center Cambridge
Verified email at samsung.com
Title
Cited by
Cited by
Year
Learning to detect violent videos using convolutional long short-term memory
S Sudhakaran, O Lanz
2017 14th IEEE International Conference on Advanced Video and Signal Based …, 2017
1672017
Lsta: Long short-term attention for egocentric action recognition
S Sudhakaran, S Escalera, O Lanz
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
1192019
Gate-Shift Networks for Video Action Recognition
S Sudhakaran, S Escalera, O Lanz
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
1052020
Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition
S Sudhakaran, O Lanz
Proceedings of British Machine Vision Conference, 2018, 2018
792018
Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactions
S Sudhakaran, O Lanz
Computer Vision Workshop (ICCVW), 2017 IEEE International Conference on …, 2017
372017
Space-time mixing attention for video transformer
A Bulat, JM Perez Rua, S Sudhakaran, B Martinez, G Tzimiropoulos
Advances in Neural Information Processing Systems 34, 19594-19607, 2021
242021
Semantic Guided Deep Unsupervised Image Segmentation
S Saha, S Sudhakaran, B Banerjee, S Pendurkar
International Conference on Image Analysis and Processing, 499-510, 2019
102019
Sparse distributed localized gradient fused features of objects
S Sudhakaran, AP James
Pattern Recognition 48 (4), 1538-1546, 2015
92015
Ancient indian document analysis using cognitive memory network
NS Kumar, DS Kumar, S Swathikiran, AP James
Advances in Computing, Communications and Informatics (ICACCI, 2014 …, 2014
82014
Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries.
S Sudhakaran, S Escalera, O Lanz
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
72021
FBK-HUPBA Submission to the EPIC-Kitchens 2019 Action Recognition Challenge
S Sudhakaran, S Escalera, O Lanz
arXiv preprint arXiv:1906.08960, 2019
72019
Top-down attention recurrent vlad encoding for action recognition in videos
S Sudhakaran, O Lanz
Intelligenza Artificiale 13 (1), 107-118, 2019
72019
Top-Down Attention Recurrent VLAD Encoding for Action Recognition in Videos
S Sudhakaran, O Lanz
International Conference of the Italian Association for Artificial …, 2018
72018
Relevance-based Margin for Contrastively-trained Video Retrieval Models
A Falcon, S Sudhakaran, G Serra, S Escalera, O Lanz
arXiv preprint arXiv:2204.13001, 2022
12022
FBK-HUPBA Submission to the EPIC-Kitchens Action Recognition 2020 Challenge
S Sudhakaran, S Escalera, O Lanz
arXiv preprint arXiv:2006.13725, 2020
12020
Object-centric attention for egocentric activity recognition
S Sudhakaran, O Lanz
Proc. ECCVW, 1-3, 2018
12018
Gate-Shift-Fuse for Video Action Recognition
S Sudhakaran, S Escalera, O Lanz
arXiv preprint arXiv:2203.08897, 2022
2022
SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021
S Sudhakaran, A Bulat, JM Perez-Rua, A Falcon, S Escalera, O Lanz, ...
arXiv preprint arXiv:2110.02902, 2021
2021
Deep Neural Architectures for Video Representation Learning
S Sudhakaran
University of Trento, 2019
2019
Hierarchical Feature Aggregation Networks for Video Action Recognition
S Sudhakaran, S Escalera, O Lanz
arXiv preprint arXiv:1905.12462, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–20