2023
Kini, Jyoti; Khan, Fahad Shahbaz; Khan, Salman; Shah, Mubarak
CT-VOS: Cutout Prediction and Tagging for Self-Supervised Video Object Segmentation Journal Article
In: Computer Vision and Image Understanding, 2023.
Tags: CVIU, Video Object Segmentation
@article{Kini2023c,
title = {CT-VOS: Cutout Prediction and Tagging for Self-Supervised Video Object Segmentation},
author = {Jyoti Kini and Fahad Shahbaz Khan and Salman Khan and Mubarak Shah},
year = {2023},
date = {2023-10-09},
journal = {Computer Vision and Image Understanding},
keywords = {CVIU, Video Object Segmentation},
pubstate = {published},
tppubtype = {article}
}
Kini, Jyoti; Khan, Fahad Shahbaz; Khan, Salman; Shah, Mubarak
CT-VOS: Cutout Prediction and Tagging for Self-Supervised Video Object Segmentation Journal Article
In: Computer Vision and Image Understanding, 2023.
Tags: CVIU, Video Object Segmentation
@article{Kini2023cb,
title = {CT-VOS: Cutout Prediction and Tagging for Self-Supervised Video Object Segmentation},
author = {Jyoti Kini and Fahad Shahbaz Khan and Salman Khan and Mubarak Shah},
year = {2023},
date = {2023-10-09},
journal = {Computer Vision and Image Understanding},
keywords = {CVIU, Video Object Segmentation},
pubstate = {published},
tppubtype = {article}
}
2022
Kini, Jyoti; Khan, Fahad Shahbaz; Khan, Salman; Shah, Mubarak
Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging Technical Report
no. arXiv:2204.10846, 2022.
Tags: Self-Supervised Learning, Video Object Segmentation | Links:
@techreport{Kini2022,
title = {Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging},
author = {Jyoti Kini and Fahad Shahbaz Khan and Salman Khan and Mubarak Shah},
url = {https://arxiv.org/pdf/2204.10846.pdf},
year = {2022},
date = {2022-04-24},
urldate = {2022-04-24},
number = {arXiv:2204.10846},
keywords = {Self-Supervised Learning, Video Object Segmentation},
pubstate = {published},
tppubtype = {techreport}
}
Kini, Jyoti; Khan, Fahad Shahbaz; Khan, Salman; Shah, Mubarak
Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging Technical Report
no. arXiv:2204.10846, 2022.
Tags: Self-Supervised Learning, Video Object Segmentation | Links:
@techreport{Kini2022d,
title = {Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging},
author = {Jyoti Kini and Fahad Shahbaz Khan and Salman Khan and Mubarak Shah},
url = {https://arxiv.org/pdf/2204.10846.pdf},
year = {2022},
date = {2022-04-24},
urldate = {2022-04-24},
number = {arXiv:2204.10846},
keywords = {Self-Supervised Learning, Video Object Segmentation},
pubstate = {published},
tppubtype = {techreport}
}
2020
McIntosh, Bruce; Duarte, Kevin; Rawat, Yogesh Singh; Shah, Mubarak
Visual-textual Capsule Routing for Text-based Video Segmentation Conference
IEEE Conference on Computer Vision and Pattern Recognition (Oral), 2020.
Abstract | Tags: Capsule Networks, CVPR, Video Object Segmentation | Links:
@conference{Duarte2020,
title = {Visual-textual Capsule Routing for Text-based Video Segmentation},
author = {Bruce McIntosh and Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/06/Projects_Visual-textual-Capsule-Routing-for-Text-based-Video-Segmentation.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2020/06/Projects_Visual-textual-Capsule-Routing-for-Text-based-Video-Segmentation_Supplementary.zip
https://www.crcv.ucf.edu/research/projects/visual-textual-capsule-routing-for-text-based-video-segmentation/},
year = {2020},
date = {2020-06-14},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition (Oral)},
edition = {(Oral)},
abstract = {Joint understanding of vision and natural language is a challenging problem with a wide range of applications in artificial intelligence. In this work, we focus on integration of video and text for the task of actor and action video segmentation from a sentence. We propose a capsule-based approach which performs pixel-level localization based on a natural language query describing the actor of interest. We encode both the video and textual input in the form of capsules, which provide a more effective representation in comparison with standard convolution based features. Our novel visual-textual routing mechanism allows for the fusion of video and text capsules to successfully localize the actor and action. The existing works on actor-action localization are mainly focused on localization in a single frame instead of the full video. Different from existing works, we propose to perform the localization on all frames of the video. To validate the potential of the proposed network for actor and action video localization, we extend an existing actor-action dataset (A2D) with annotations for all the frames. The experimental evaluation demonstrates the effectiveness of our capsule network for text selective actor and action localization in videos. The proposed method also improves upon the performance of the existing state-of-the art works on single frame-based localization.},
keywords = {Capsule Networks, CVPR, Video Object Segmentation},
pubstate = {published},
tppubtype = {conference}
}
Joint understanding of vision and natural language is a challenging problem with a wide range of applications in artificial intelligence. In this work, we focus on integration of video and text for the task of actor and action video segmentation from a sentence. We propose a capsule-based approach which performs pixel-level localization based on a natural language query describing the actor of interest. We encode both the video and textual input in the form of capsules, which provide a more effective representation in comparison with standard convolution based features. Our novel visual-textual routing mechanism allows for the fusion of video and text capsules to successfully localize the actor and action. The existing works on actor-action localization are mainly focused on localization in a single frame instead of the full video. Different from existing works, we propose to perform the localization on all frames of the video. To validate the potential of the proposed network for actor and action video localization, we extend an existing actor-action dataset (A2D) with annotations for all the frames. The experimental evaluation demonstrates the effectiveness of our capsule network for text selective actor and action localization in videos. The proposed method also improves upon the performance of the existing state-of-the art works on single frame-based localization.
McIntosh, Bruce; Duarte, Kevin; Rawat, Yogesh Singh; Shah, Mubarak
Visual-textual Capsule Routing for Text-based Video Segmentation Conference
IEEE Conference on Computer Vision and Pattern Recognition (Oral), 2020.
Abstract | Tags: Capsule Networks, CVPR, Video Object Segmentation | Links:
@conference{Duarte2020b,
title = {Visual-textual Capsule Routing for Text-based Video Segmentation},
author = {Bruce McIntosh and Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/06/Projects_Visual-textual-Capsule-Routing-for-Text-based-Video-Segmentation.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2020/06/Projects_Visual-textual-Capsule-Routing-for-Text-based-Video-Segmentation_Supplementary.zip
https://www.crcv.ucf.edu/research/projects/visual-textual-capsule-routing-for-text-based-video-segmentation/},
year = {2020},
date = {2020-06-14},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition (Oral)},
edition = {(Oral)},
abstract = {Joint understanding of vision and natural language is a challenging problem with a wide range of applications in artificial intelligence. In this work, we focus on integration of video and text for the task of actor and action video segmentation from a sentence. We propose a capsule-based approach which performs pixel-level localization based on a natural language query describing the actor of interest. We encode both the video and textual input in the form of capsules, which provide a more effective representation in comparison with standard convolution based features. Our novel visual-textual routing mechanism allows for the fusion of video and text capsules to successfully localize the actor and action. The existing works on actor-action localization are mainly focused on localization in a single frame instead of the full video. Different from existing works, we propose to perform the localization on all frames of the video. To validate the potential of the proposed network for actor and action video localization, we extend an existing actor-action dataset (A2D) with annotations for all the frames. The experimental evaluation demonstrates the effectiveness of our capsule network for text selective actor and action localization in videos. The proposed method also improves upon the performance of the existing state-of-the art works on single frame-based localization.},
keywords = {Capsule Networks, CVPR, Video Object Segmentation},
pubstate = {published},
tppubtype = {conference}
}
Joint understanding of vision and natural language is a challenging problem with a wide range of applications in artificial intelligence. In this work, we focus on integration of video and text for the task of actor and action video segmentation from a sentence. We propose a capsule-based approach which performs pixel-level localization based on a natural language query describing the actor of interest. We encode both the video and textual input in the form of capsules, which provide a more effective representation in comparison with standard convolution based features. Our novel visual-textual routing mechanism allows for the fusion of video and text capsules to successfully localize the actor and action. The existing works on actor-action localization are mainly focused on localization in a single frame instead of the full video. Different from existing works, we propose to perform the localization on all frames of the video. To validate the potential of the proposed network for actor and action video localization, we extend an existing actor-action dataset (A2D) with annotations for all the frames. The experimental evaluation demonstrates the effectiveness of our capsule network for text selective actor and action localization in videos. The proposed method also improves upon the performance of the existing state-of-the art works on single frame-based localization.
2019
Duarte, Kevin; Rawat, Yogesh Singh; Shah, Mubarak
CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing Conference
International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2, 2019.
Tags: Video Object Segmentation | Links:
@conference{Duarte2019,
title = {CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing},
author = {Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Projects_CapsuleVOS-Semi-Supervised-Video-Object-Segmentation-Using-Capsule-Routing.pdf
https://www.crcv.ucf.edu/research/projects/capsulevos-semi-supervised-video-object-segmentation-using-capsule-routing/},
year = {2019},
date = {2019-10-30},
publisher = {International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2},
keywords = {Video Object Segmentation},
pubstate = {published},
tppubtype = {conference}
}
Duarte, Kevin; Rawat, Yogesh Singh; Shah, Mubarak
CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing Conference
International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2, 2019.
Tags: Video Object Segmentation | Links:
@conference{Duarte2019b,
title = {CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing},
author = {Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Projects_CapsuleVOS-Semi-Supervised-Video-Object-Segmentation-Using-Capsule-Routing.pdf
https://www.crcv.ucf.edu/research/projects/capsulevos-semi-supervised-video-object-segmentation-using-capsule-routing/},
year = {2019},
date = {2019-10-30},
publisher = {International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct 27-Nov 2},
keywords = {Video Object Segmentation},
pubstate = {published},
tppubtype = {conference}
}
Hou, Rui; Chen, Chen; Sukthankar, Rahul; Shah, Mubarak
An Efficient 3D CNN for Action/Object Segmentation in Video Conference
British Machine Vision Conference (BMVC 2019), UK, Sep 9-10, 2019.
Tags: BMVC, Video Object Segmentation | Links:
@conference{Hou2019,
title = {An Efficient 3D CNN for Action/Object Segmentation in Video},
author = {Rui Hou and Chen Chen and Rahul Sukthankar and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2019/07/Publications_An-Efficient-3D-CNN-for-Action-Object-Segmentation-in-Video.pdf
https://www.crcv.ucf.edu/research/projects/an-efficient-3d-cnn-for-action-object-segmentation-in-video/},
year = {2019},
date = {2019-09-10},
publisher = {British Machine Vision Conference (BMVC 2019), UK, Sep 9-10},
keywords = {BMVC, Video Object Segmentation},
pubstate = {published},
tppubtype = {conference}
}
Hou, Rui; Chen, Chen; Sukthankar, Rahul; Shah, Mubarak
An Efficient 3D CNN for Action/Object Segmentation in Video Conference
British Machine Vision Conference (BMVC 2019), UK, Sep 9-10, 2019.
Tags: BMVC, Video Object Segmentation | Links:
@conference{Hou2019c,
title = {An Efficient 3D CNN for Action/Object Segmentation in Video},
author = {Rui Hou and Chen Chen and Rahul Sukthankar and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2019/07/Publications_An-Efficient-3D-CNN-for-Action-Object-Segmentation-in-Video.pdf
https://www.crcv.ucf.edu/research/projects/an-efficient-3d-cnn-for-action-object-segmentation-in-video/},
year = {2019},
date = {2019-09-10},
publisher = {British Machine Vision Conference (BMVC 2019), UK, Sep 9-10},
keywords = {BMVC, Video Object Segmentation},
pubstate = {published},
tppubtype = {conference}
}