Abstract
High-level image understanding includes phases like object detection, predicate classification, and attribute classification. The outputs from each phase are merged to build a scene graph, which arranges the elements in a structured manner. Scene graphs have shown their proficiency in various tasks like image retrieval, visual question answering, and image generation. However, data is an essential aspect for such tasks, especially when the models are too complex. We introduce Compact-VG, a refined subset of the popular dataset visual genome. This subset contains 200 object categories, 10 predicates, and 16 attributes. Studies show that, even when we consider only the most common categories of objects, predicates, and attributes, the extracted dataset is still very rich, with a mean of 14.1 objects, 18.5 attributes, and 19.7 relationships per image. Dataset is available at https://github.com/Aiswarya2021/Scene2Graph.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krishna R et al (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis 123(1):32–73
Luo J, Zhao J, Wen B, Zhang Y (2021) Explaining the semantics capturing capability of scene graph generation models. Pattern Recogn 110:107427
Torralba A, Fergus R, Freeman WT (2008) 80 million tiny images: a large data set for nonparametric object and scene recognition. IEEE Trans Pattern Anal Mach Intell 30(11):1958–1970
Deng J et al (2009) ImageNet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition
Vinyals O et al (2017) Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans Pattern Anal Mach Intell 39(4):652–663
Devnani G et al (2019) Performance evaluation of fine-tuned faster R-CNN on specific MS COCO Objects. Int J Electr Comput Eng (IJECE) 9(4):2548
Kawakura S, Shibasaki R (2020) Suggestions of a deep learning based automatic text annotation system for agricultural sites using GoogLeNet inception and MS-COCO. J Image Graph 8(4):120–125
Fei-Fei L, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell 28(4):594–611
Angelov P, Soares E (2020) Towards explainable deep neural networks (xDNN). Neural Netw 130:185–194
Yang G, Ding F (2020) Associative memory optimized method on deep neural networks for image classification. Inf Sci 533:108–119
Lu C et al (2016) Visual relationship detection with language priors. Lecture Notes in Computer Science, pp 852–869
Sadeghi MA, Farhadi A (2011) Recognition using visual phrases. CVPR 2011
Farhadi A et al (2009) Describing objects by their attributes. In: 2009 IEEE conference on computer vision and pattern recognition
Xiao J et al (2010) SUN database: large-scale scene recognition from abbey to zoo. In: 2010 IEEE computer society conference on computer vision and pattern recognition
Kumar AS, Nair JJ (2021) A novel SPLIT-SIM approach for efficient image retrieval. Multimedia Syst, 1–14
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kumar, A.S., Nair, J.J. (2022). Compact-VG: A Small-scale Dataset for Scene Graph Generation. In: Bhateja, V., Khin Wee, L., Lin, J.CW., Satapathy, S.C., Rajesh, T.M. (eds) Data Engineering and Intelligent Computing. Lecture Notes in Networks and Systems, vol 446. Springer, Singapore. https://doi.org/10.1007/978-981-19-1559-8_18
Download citation
DOI: https://doi.org/10.1007/978-981-19-1559-8_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1558-1
Online ISBN: 978-981-19-1559-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)