Captioning Images with Diverse Objects

Captioning Images with Diverse Objects

Subhashini Venugopalan,  Lisa Anne Hendricks,  Marcus Rohrbach,  Raymond Mooney,  Trevor Darrell,  Kate Saenko

(Submitted on 24 Jun 2016 ( v1), last revised 20 Jul 2017 (this version, v3))

Recent captioning models are limited in their ability to scale and describe concepts unseen in paired image-text corpora. We propose the Novel Object Captioner (NOC), a deep visual semantic captioning model that can describe a large number of object categories not present in existing image-caption datasets. Our model takes advantage of external sources -- labeled images from object recognition datasets, and semantic knowledge extracted from unannotated text. We propose minimizing a joint objective which can learn from these diverse data sources and leverage distributional semantic embeddings, enabling the model to generalize and describe novel objects outside of image-caption datasets. We demonstrate that our model exploits semantic information to generate captions for hundreds of object categories in the ImageNet object recognition dataset that are not observed in MSCOCO image-caption training data, as well as many categories that are observed very rarely. Both automatic evaluations and human judgements show that our model considerably outperforms prior work in being able to describe many more categories of objects.

Comments:	CVPR 2017 Camera ready version. 17 pages (8 + 9 supplement), 12 figures, 8 tables. Includes project page this http URL
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
Cite as:	arXiv:1606.07770 [cs.CV]
	(or arXiv:1606.07770v3 [cs.CV] for this version)

Submission history

From: Subhashini Venugopalan [ view email] 
[v1] Fri, 24 Jun 2016 17:53:45 GMT (1873kb,D)
[v2] Thu, 1 Dec 2016 20:54:17 GMT (8155kb,D)
[v3] Thu, 20 Jul 2017 18:06:27 GMT (9001kb,D)