Skip to Main Content (Press Enter)

Logo UNIMORE
  • ×
  • Home
  • Corsi
  • Insegnamenti
  • Professioni
  • Persone
  • Pubblicazioni
  • Strutture
  • Terza Missione
  • Attività
  • Competenze

UNI-FIND
Logo UNIMORE

|

UNI-FIND

unimore.it
  • ×
  • Home
  • Corsi
  • Insegnamenti
  • Professioni
  • Persone
  • Pubblicazioni
  • Strutture
  • Terza Missione
  • Attività
  • Competenze
  1. Pubblicazioni

Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions

Contributo in Atti di convegno
Data di Pubblicazione:
2019
Citazione:
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions / Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita. - 2019-:(2019), pp. 8299-8308. ( 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 Long Beach, CA, USA June 16-20 2019) [10.1109/CVPR.2019.00850].
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.
Tipologia CRIS:
Relazione in Atti di Convegno
Keywords:
Deep Learning; Vision + Language; Visual Reasoning;
Elenco autori:
Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Autori di Ateneo:
BARALDI LORENZO
CORNIA MARCELLA
CUCCHIARA Rita
Link alla scheda completa:
https://iris.unimore.it/handle/11380/1171698
Link al Full Text:
https://iris.unimore.it//retrieve/handle/11380/1171698/220677/2019-cvpr-captioning.pdf
Titolo del libro:
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Pubblicato in:
IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
Series
  • Utilizzo dei cookie

Realizzato con VIVO | Designed by Cineca | 26.4.4.0