Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the corresponding caption through a recurrent architecture which predicts textual chunks explicitly grounded on regions, following the constraints of the given control. Experiments are conducted on Flickr30k Entities and on COCO Entities, an extended version of COCO in which we add grounding annotations collected in a semi-automatic manner. Results demonstrate that our method achieves state of the art performances on controllable image captioning, in terms of caption quality and diversity. Code and annotations are publicly available at: https://github.com/aimagelab/show-control-and-tell.
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions / Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita. - 2019-:(2019), pp. 8299-8308. (Intervento presentato al convegno 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 tenutosi a Long Beach, CA, USA nel June 16-20 2019) [10.1109/CVPR.2019.00850].
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
Cornia, Marcella;Baraldi, Lorenzo;Cucchiara, Rita
2019
Abstract
Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the corresponding caption through a recurrent architecture which predicts textual chunks explicitly grounded on regions, following the constraints of the given control. Experiments are conducted on Flickr30k Entities and on COCO Entities, an extended version of COCO in which we add grounding annotations collected in a semi-automatic manner. Results demonstrate that our method achieves state of the art performances on controllable image captioning, in terms of caption quality and diversity. Code and annotations are publicly available at: https://github.com/aimagelab/show-control-and-tell.File | Dimensione | Formato | |
---|---|---|---|
2019-cvpr-captioning.pdf
Open access
Tipologia:
AAM - Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
9.1 MB
Formato
Adobe PDF
|
9.1 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris