Suman Saha

37 papers A* 5A 5B 1Journal 20Unranked 5
YearRankTypeTitle / Venue / Authors
2025 A conf
Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation.
WACV
Elham Amin Mansour, Ozan Unal, Suman Saha, Benjamín Béjar, Luc Van Gool
2024 — conf
Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding.
ECCV (76)
Ozan Unal, Christos Sakaridis, Suman Saha, Luc Van Gool
2024 J jnl
Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation.
CoRR
Elham Amin Mansour, Ozan Unal, Suman Saha, Benjamín Béjar, Luc Van Gool
2023 A* conf
EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation.
ICCV
Suman Saha, Lukas Hoyer, Anton Obukhov, Dengxin Dai, Luc Van Gool
2023 J jnl
EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation.
CoRR
Suman Saha, Lukas Hoyer, Anton Obukhov, Dengxin Dai, Luc Van Gool
2023 A conf
Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection.
WACV
Yifan Lu, Gurkirt Singh, Suman Saha, Luc Van Gool
2023 J jnl
ROAD: The Road Event Awareness Dataset for Autonomous Driving.
IEEE Trans. Pattern Anal. Mach. Intell.
Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Valentina Fontana, Reza Javanmard Alitappeh, Salman Khan, Suman Saha, Kossar Jeddi Saravi, Farzad Yousefi, Jacob Culley, Tom Nicholson, Jordan Omokeowa, Stanislao Grazioso, Andrew Bradley, Giuseppe Di Gironimo, Fabio Cuzzolin
2023 A conf
Spatio-Temporal Action Detection Under Large Motion.
WACV
Gurkirt Singh, Vasileios Choutas, Suman Saha, Fisher Yu, Luc Van Gool
2023 J jnl
Three Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding.
CoRR
Ozan Unal, Christos Sakaridis, Suman Saha, Fisher Yu, Luc Van Gool
2022 J jnl
Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection.
CoRR
Yifan Lu, Gurkirt Singh, Suman Saha, Luc Van Gool
2022 J jnl
Spatio-Temporal Action Detection Under Large Motion.
CoRR
Gurkirt Singh, Vasileios Choutas, Suman Saha, Fisher Yu, Luc Van Gool
2021 A* conf
Learning To Relate Depth and Semantics for Unsupervised Domain Adaptation.
CVPR
Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, Luc Van Gool
2021 J jnl
Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation.
CoRR
Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, Luc Van Gool
2021 J jnl
ROAD: The ROad event Awareness Dataset for Autonomous Driving.
CoRR
Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Valentina Fontana, Reza Javanmard Alitappeh, Suman Saha, Kossar Jeddi Saravi, Farzad Yousefi, Jacob Culley, Tom Nicholson, Jordan Omokeowa, Salman Khan, Stanislao Grazioso, Andrew Bradley, Giuseppe Di Gironimo, Fabio Cuzzolin
2021 A* conf
Three Ways To Improve Semantic Segmentation With Self-Supervised Depth Estimation.
CVPR
Lukas Hoyer, Dengxin Dai, Yuhua Chen, Adrian Köring, Suman Saha, Luc Van Gool
2021 B conf
Unsupervised Compound Domain Adaptation for Face Anti-Spoofing.
FG
Ankush Panwar, Pratyush Singh, Suman Saha, Danda Pani Paudel, Luc Van Gool
2021 J jnl
Unsupervised Compound Domain Adaptation for Face Anti-Spoofing.
CoRR
Ankush Panwar, Pratyush Singh, Suman Saha, Danda Pani Paudel, Luc Van Gool
2020 — conf
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing.
CVPR Workshops
Suman Saha, Wenhao Xu, Menelaos Kanakis, Stamatios Georgoulis, Yuhua Chen, Danda Pani Paudel, Luc Van Gool
2020 — conf
Reparameterizing Convolutions for Incremental Multi-Task Learning Without Task Interference.
ECCV (20)
Menelaos Kanakis, David Brüggemann, Suman Saha, Stamatios Georgoulis, Anton Obukhov, Luc Van Gool
2020 J jnl
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference.
CoRR
Menelaos Kanakis, David Brüggemann, Suman Saha, Stamatios Georgoulis, Anton Obukhov, Luc Van Gool
2020 J jnl
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation.
CoRR
Lukas Hoyer, Dengxin Dai, Yuhua Chen, Adrian Köring, Suman Saha, Luc Van Gool
2020 J jnl
Two-Stream AMTnet for Action Detection.
CoRR
Suman Saha, Gurkirt Singh, Fabio Cuzzolin
2019 J jnl
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing.
CoRR
Suman Saha, Wenhao Xu, Menelaos Kanakis, Stamatios Georgoulis, Yuhua Chen, Danda Pani Paudel, Luc Van Gool
2018 J jnl
Action Detection from a Robot-Car Perspective.
CoRR
Valentina Fontana, Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Suman Saha, Fabio Cuzzolin
2018 A conf
Incremental Tube Construction for Human Action Detection.
BMVC
Harkirat S. Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip H. S. Torr
2018 — conf
Predicting Action Tubes.
ECCV Workshops (3)
Gurkirt Singh, Suman Saha, Fabio Cuzzolin
2018 J jnl
Predicting Action Tubes.
CoRR
Gurkirt Singh, Suman Saha, Fabio Cuzzolin
2018 — —
Spatio-temporal human action detection and instance segmentation in videos.
Suman Saha
2018 — conf
TraMNet - Transition Matrix Network for Efficient Action Tube Proposals.
ACCV (6)
Gurkirt Singh, Suman Saha, Fabio Cuzzolin
2018 J jnl
TraMNet - Transition Matrix Network for Efficient Action Tube Proposals.
CoRR
Gurkirt Singh, Suman Saha, Fabio Cuzzolin
2017 A* conf
AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture.
ICCV
Suman Saha, Gurkirt Singh, Fabio Cuzzolin
2017 J jnl
AMTnet: Action-Micro-Tube regression by end-to-end trainable deep architecture.
CoRR
Suman Saha, Gurkirt Singh, Fabio Cuzzolin
2017 J jnl
Incremental Tube Construction for Human Action Detection.
CoRR
Harkirat S. Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip H. S. Torr
2017 A* conf
Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction.
ICCV
Gurkirt Singh, Suman Saha, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin
2017 J jnl
Spatio-temporal human action localisation and instance segmentation in temporally untrimmed videos.
CoRR
Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin
2016 A conf
Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos.
BMVC
Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin
2016 J jnl
Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos.
CoRR
Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin