CIDEr: Consensus-based image description evaluation
Ramakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2015
Automatically describing an image with a sentence is a long-standing challenge in computer vision and natural language processing. Due to recent progress in object detection, attribute classification, action recognition, etc., there is renewed interest in this area. However, evaluating the quality of descriptions has proven to be challenging. We propose a novel paradigm for evaluating image descriptions that uses human consensus. This paradigm consists of three main parts: a new triplet-based method of collecting human annotations to measure consensus, a new automated metric that captures consensus, and two new datasets: PASCAL-50S and ABSTRACT-50S that contain 50 sentences describing each image. Our simple metric captures human judgment of consensus better than existing metrics across sentences generated by various sources. We also evaluate five state-of-the-art image description approaches using this new protocol and provide a benchmark for future comparisons. A version of CIDEr named CIDEr-D is available as a part of MS COCO evaluation server to enable systematic evaluation and benchmarking.
Cited by 4,649 works. doi:10.1109/cvpr.2015.7299087
Authors
References
- ImageNet: A large-scale hierarchical image database
- Microsoft COCO: Common Objects in Context
- Object Detection with Discriminatively Trained Part-Based Models
- BLEU
- The Pascal Visual Object Classes Challenge: A Retrospective
- The PASCAL visual object classes challenge 2006 (VOC2006) results
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
- Show and tell: A neural image caption generator
- ROUGE: A Package for Automatic Evaluation of Summaries