English

Object Counts! Bringing Explicit Detections Back into Image Captioning

Computer Vision and Pattern Recognition 2018-05-02 v1 Artificial Intelligence Computation and Language

Abstract

The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is conditioned directly on a mid-level image embedding. We argue that explicit detections provide rich semantic information, and can thus be used as an interpretable representation to better understand why end-to-end image captioning systems work well. We provide an in-depth analysis of end-to-end image captioning by exploring a variety of cues that can be derived from such object detections. Our study reveals that end-to-end image captioning systems rely on matching image representations to generate captions, and that encoding the frequency, size and position of objects are complementary and all play a role in forming a good image representation. It also reveals that different object categories contribute in different ways towards image captioning.

Keywords

Cite

@article{arxiv.1805.00314,
  title  = {Object Counts! Bringing Explicit Detections Back into Image Captioning},
  author = {Josiah Wang and Pranava Madhyastha and Lucia Specia},
  journal= {arXiv preprint arXiv:1805.00314},
  year   = {2018}
}

Comments

Please cite: In Proceedings of 2018 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2018)

R2 v1 2026-06-23T01:41:30.012Z