Leveraging Visual Question Answering for Image-Caption Ranking
Visual Question Answering (VQA) is the task of taking as input an image and a free-form natural language question about the image, and producing an accurate answer. In this work we view VQA as a “feature extraction” module to extract image and caption rep
- PDF / 3,569,102 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 98 Downloads / 220 Views
Abstract. Visual Question Answering (VQA) is the task of taking as input an image and a free-form natural language question about the image, and producing an accurate answer. In this work we view VQA as a “feature extraction” module to extract image and caption representations. We employ these representations for the task of image-caption ranking. Each feature dimension captures (imagines) whether a fact (question-answer pair) could plausibly be true for the image and caption. This allows the model to interpret images and captions from a wide variety of perspectives. We propose score-level and representation-level fusion models to incorporate VQA knowledge in an existing state-of-theart VQA-agnostic image-caption ranking model. We find that incorporating and reasoning about consistency between images and captions significantly improves performance. Concretely, our model improves stateof-the-art on caption retrieval by 7.1 % and on image retrieval by 4.4 % on the MSCOCO dataset.
Keywords: Visual question answering Mid-level concepts
1
·
Image-caption ranking
·
Introduction
Visual Question Answering (VQA) is an “AI-complete” problem that requires knowledge from multiple disciplines such as computer vision, natural language processing and knowledge base reasoning. A VQA system takes as input an image and a free-form open-ended question about the image and outputs the natural language answer to the question. A VQA system needs to not only recognize objects and scenes but also reason beyond low-level recognition about aspects such as intention, future, physics, material and commonsense knowledge. For example (Q: Who is the person in charge in this picture? A: Chef) reveals the most important person and occupation in the image. Moreover, answers to multiple questions about the same image can be correlated and may reveal Electronic supplementary material The online version of this chapter (doi:10. 1007/978-3-319-46475-6 17) contains supplementary material, which is available to authorized users. c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part II, LNCS 9906, pp. 261–277, 2016. DOI: 10.1007/978-3-319-46475-6 17
262
X. Lin and D. Parikh
more complex interactions. For example (Q: What is this person riding? A: Motorcycle) and (Q: What is the man wearing on his head? A: Helmet) might reveal correlations observable in the visual world due to safety regulations. Today’s VQA models, while far from perfect, may already be picking up on these semantic correlations of the world. If so, they may serve as an implicit knowledge resource to help other tasks. Just like we do not need to fully understand the theory behind an equation to use it, can we already use VQA knowledge captured by existing VQA models to improve other tasks? In this work we study the problem of using VQA knowledge to improve imagecaption ranking. Consider the image and its caption in Fig. 1. Aligning them not only requires recognizing the batter and that it is a baseball game (mentioned in the caption), but also realiz
Data Loading...
