2021
Kerrigan, Alec; Duarte, Kevin; Rawat, Yogesh Singh; Shah, Mubarak
Reformulating Zero-shot Action Recognition for Multi-label Actions Conference
Thirty-fifth Conference on Neural Information Processing Systems, 2021.
Tags: Action Recognition, NeurIPS, Zero-Shot Learning | Links:
@conference{Kerrigan2021,
title = {Reformulating Zero-shot Action Recognition for Multi-label Actions},
author = {Alec Kerrigan and Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/reformulating_zero_shot_action2.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ZSL-Supp.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Reformulating-Zero-shot-Action-Recognition-forMulti-label-Actions.pptx},
year = {2021},
date = {2021-12-06},
urldate = {2021-12-06},
booktitle = {Thirty-fifth Conference on Neural Information Processing Systems},
keywords = {Action Recognition, NeurIPS, Zero-Shot Learning},
pubstate = {published},
tppubtype = {conference}
}
Kerrigan, Alec; Duarte, Kevin; Rawat, Yogesh Singh; Shah, Mubarak
Reformulating Zero-shot Action Recognition for Multi-label Actions Conference
Thirty-fifth Conference on Neural Information Processing Systems, 2021.
Tags: Action Recognition, NeurIPS, Zero-Shot Learning | Links:
@conference{Kerrigan2021b,
title = {Reformulating Zero-shot Action Recognition for Multi-label Actions},
author = {Alec Kerrigan and Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/reformulating_zero_shot_action2.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ZSL-Supp.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Reformulating-Zero-shot-Action-Recognition-forMulti-label-Actions.pptx},
year = {2021},
date = {2021-12-06},
urldate = {2021-12-06},
booktitle = {Thirty-fifth Conference on Neural Information Processing Systems},
keywords = {Action Recognition, NeurIPS, Zero-Shot Learning},
pubstate = {published},
tppubtype = {conference}
}
Narayan, Sanath; Gupta, Akshita; Khan, Salman; Khan, Fahad Shahbaz; Shao, Ling; Shah, Mubarak
Discriminative Region-based Multi-Label Zero-Shot Learning Conference
International Conference on Computer Vision, 2021.
Abstract | Tags: ICCV, Transformers, Zero-Shot Learning | Links:
@conference{NarayanICCV2021,
title = {Discriminative Region-based Multi-Label Zero-Shot Learning},
author = {Sanath Narayan and Akshita Gupta and Salman Khan and Fahad Shahbaz Khan and Ling Shao and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617-supp.pdf},
year = {2021},
date = {2021-10-11},
urldate = {2021-10-11},
booktitle = {International Conference on Computer Vision},
abstract = {Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and re-quires region-specific processing of visual features to pre-serve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results. Source code is available at <a href="https://github.com/akshitac8/BiAM" target="_blank">https://github.com/akshitac8/BiAM</a>.},
keywords = {ICCV, Transformers, Zero-Shot Learning},
pubstate = {published},
tppubtype = {conference}
}
Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and re-quires region-specific processing of visual features to pre-serve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results. Source code is available at <a href="https://github.com/akshitac8/BiAM" target="_blank">https://github.com/akshitac8/BiAM</a>.
Narayan, Sanath; Gupta, Akshita; Khan, Salman; Khan, Fahad Shahbaz; Shao, Ling; Shah, Mubarak
Discriminative Region-based Multi-Label Zero-Shot Learning Conference
International Conference on Computer Vision, 2021.
Abstract | Tags: ICCV, Transformers, Zero-Shot Learning | Links:
@conference{NarayanICCV2021b,
title = {Discriminative Region-based Multi-Label Zero-Shot Learning},
author = {Sanath Narayan and Akshita Gupta and Salman Khan and Fahad Shahbaz Khan and Ling Shao and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617-supp.pdf},
year = {2021},
date = {2021-10-11},
urldate = {2021-10-11},
booktitle = {International Conference on Computer Vision},
abstract = {Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and re-quires region-specific processing of visual features to pre-serve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results. Source code is available at <a href="https://github.com/akshitac8/BiAM" target="_blank">https://github.com/akshitac8/BiAM</a>.},
keywords = {ICCV, Transformers, Zero-Shot Learning},
pubstate = {published},
tppubtype = {conference}
}
Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and re-quires region-specific processing of visual features to pre-serve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results. Source code is available at <a href="https://github.com/akshitac8/BiAM" target="_blank">https://github.com/akshitac8/BiAM</a>.
2016
Zhang, Yang; Gong, Boqing; Shah, Mubarak
Fast Zero-Shot Image Tagging Conference
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016.
Tags: Deep Learning, Zero-Shot Learning | Links:
@conference{Zhang2016,
title = {Fast Zero-Shot Image Tagging},
author = {Yang Zhang and Boqing Gong and Mubarak Shah},
url = {https://www.crcv.ucf.edu/papers/cvpr2016/Zhang_CVPR2016.pdf
https://youtu.be/Pmv5JHKX2y4},
year = {2016},
date = {2016-02-10},
urldate = {2016-02-10},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016)},
keywords = {Deep Learning, Zero-Shot Learning},
pubstate = {published},
tppubtype = {conference}
}
Zhang, Yang; Gong, Boqing; Shah, Mubarak
Fast Zero-Shot Image Tagging Conference
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016.
Tags: Deep Learning, Zero-Shot Learning | Links:
@conference{Zhang2016c,
title = {Fast Zero-Shot Image Tagging},
author = {Yang Zhang and Boqing Gong and Mubarak Shah},
url = {https://www.crcv.ucf.edu/papers/cvpr2016/Zhang_CVPR2016.pdf
https://youtu.be/Pmv5JHKX2y4},
year = {2016},
date = {2016-02-10},
urldate = {2016-02-10},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016)},
keywords = {Deep Learning, Zero-Shot Learning},
pubstate = {published},
tppubtype = {conference}
}