Show, Tell, and Polish: Ruminant Decoding for Image Captioning
文献类型：期刊论文
| 作者 | Guo, Longteng2,3 ; Liu, Jing2; Lu, Shichen1; Lu, Hanqing2
|
| 刊名 | IEEE TRANSACTIONS ON MULTIMEDIA
 |
| 出版日期 | 2020-08-01 |
| 卷号 | 22期号:8页码:2149-2162 |
| 关键词 | Decoding Visualization Planning Training Semantics Reinforcement learning Task analysis Image captioning multi-pass decoding rumination |
| ISSN号 | 1520-9210 |
| DOI | 10.1109/TMM.2019.2951226 |
| 通讯作者 | Liu, Jing(jliu@nlpr.ia.ac.cn) |
| 英文摘要 | The encoder-decoder framework has been the base of popular image captioning models, which typically predicts the target sentence based on the encoded source image one word at a time in sequence. However, such a single-pass decoding framework encounters two problems. First, mistakes in the predicted words cannot be corrected and may propagate to the entire sentence. Second, because the single-pass decoder cannot access the following un-generated words, it can only perform local planning to choose every single word according to the preceding words, while lacks the global planning ability as for maintaining the semantic consistency and fluency of the whole sentence. In order to address the above two problems, in this work, we design a ruminant captioning framework which contains an image encoder, a base decoder, and a ruminant decoder. Specifically, the outputs of the former/base decoder are utilized as the global information to guide the words prediction of the latter/ruminant decoder, in an attempt to mimic human polishing process. We enable jointly training of the whole framework and overcome the non-differential problem of discrete words by designing a novel reinforcement learning based optimization algorithm. Experiments on two datasets (MS COCO and Flickr30 k) demonstrate that our ruminant decoding method can bring significant improvements over traditional single-pass decoding based models and achieves state-of-the-art performance. |
| 资助项目 | National Natural Science Foundation of China[61922086] ; National Natural Science Foundation of China[61872366] ; Beijing Natural Science Foundation[4192059] |
| WOS研究方向 | Computer Science ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000553424500019 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; Beijing Natural Science Foundation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/40259]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
| 通讯作者 | Liu, Jing |
| 作者单位 | 1.Wuhan Univ, Sch Comp, Wuhan 430072, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Guo, Longteng,Liu, Jing,Lu, Shichen,et al. Show, Tell, and Polish: Ruminant Decoding for Image Captioning[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2020,22(8):2149-2162. |
| APA | Guo, Longteng,Liu, Jing,Lu, Shichen,&Lu, Hanqing.(2020).Show, Tell, and Polish: Ruminant Decoding for Image Captioning.IEEE TRANSACTIONS ON MULTIMEDIA,22(8),2149-2162. |
| MLA | Guo, Longteng,et al."Show, Tell, and Polish: Ruminant Decoding for Image Captioning".IEEE TRANSACTIONS ON MULTIMEDIA 22.8(2020):2149-2162. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。