The Flickr30K dataset has become a standard benchmark for sentence-based image description. This paper presents Flickr30K Entities, which augments the 158k captions from Flickr30k with 244k coreference chains, linking mentions of the same entities across different captions for the same image, and associating them with 276k manually annotated bounding boxes. Such annotations are essential for continued progress in automatic image description and grounded language understanding. They enable us to define a new benchmark for localization of textual entity mentions in an image. We present a strong baseline for this task that combines an image-text embedding, detectors for common objects, a color classifier, and a bias towards selecting larger objects. While our baseline rivals in accuracy more complex state-of-the-art models, we show that its gains cannot be easily parlayed into improvements on such tasks as image-sentence retrieval, thus underlining the limitations of current methods and the need for further research.
Keywords for this software
References in zbMATH (referenced in 6 articles , 1 standard article )
Showing results 1 to 6 of 6.
- Paul Pu Liang, Yiwei Lyu, Gunjan Chhablani, Nihal Jain, Zihao Deng, Xingbo Wang, Louis-Philippe Morency, Ruslan Salakhutdinov: MultiViz: An Analysis Benchmark for Visualizing and Understanding Multimodal Models (2022) arXiv
- Arachie, Chidubem; Huang, Bert: A general framework for adversarial label learning (2021)
- Huang, Feicheng; Li, Zhixin; Wei, Haiyang; Zhang, Canlong; Ma, Huifang: Boost image captioning with knowledge reasoning (2020)
- Mondal, Ranjan; Dey, Moni Shankar; Chanda, Bhabatosh: Image restoration by learning morphological opening-closing network (2020)
- Yu, Yong; Si, Xiaosheng; Hu, Changhua; Zhang, Jianxun: A review of recurrent neural networks: LSTM cells and network architectures (2019)
- Bryan A. Plummer, Liwei Wang, Chris M. Cervantes, Juan C. Caicedo, Julia Hockenmaier, Svetlana Lazebnik: Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models (2015) arXiv