Evolutionary recurrent neural network for image captioning
Automatic architecture search is efficient to discover novel neural networks while it is mostly employed for pure vision or natural language tasks. However, cross-modality tasks are highly emphasized on the associative mechanisms between visual and language models rather than merely convolutional ne...
Saved in:
| Published in | Neurocomputing (Amsterdam) Vol. 401; pp. 249 - 256 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
11.08.2020
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Automatic architecture search is efficient to discover novel neural networks while it is mostly employed for pure vision or natural language tasks. However, cross-modality tasks are highly emphasized on the associative mechanisms between visual and language models rather than merely convolutional neural network (CNN) or recurrent neural network (RNN) with the best performance. In this work, the intermediary associative connection is approximated to the topological inner structure of RNN cell, which is further evolved by an evolutionary algorithm on the proxy of image captioning task. On the MSCOCO dataset, the proposed algorithm, starting from scratch, discovers more than 100 RNN variants with the performances all above 100 on CIDEr and 31 on BLEU4, and the top performance achieves 101.4 and 32.6 accordingly. Additionally, several unknown interesting patterns as well as many existing powerful structures are found in the generated RNNs. The patterns of operation and connection in the generated architecture are analyzed to understand the language modeling of cross-modality compared with general RNNs. |
|---|---|
| AbstractList | Automatic architecture search is efficient to discover novel neural networks while it is mostly employed for pure vision or natural language tasks. However, cross-modality tasks are highly emphasized on the associative mechanisms between visual and language models rather than merely convolutional neural network (CNN) or recurrent neural network (RNN) with the best performance. In this work, the intermediary associative connection is approximated to the topological inner structure of RNN cell, which is further evolved by an evolutionary algorithm on the proxy of image captioning task. On the MSCOCO dataset, the proposed algorithm, starting from scratch, discovers more than 100 RNN variants with the performances all above 100 on CIDEr and 31 on BLEU4, and the top performance achieves 101.4 and 32.6 accordingly. Additionally, several unknown interesting patterns as well as many existing powerful structures are found in the generated RNNs. The patterns of operation and connection in the generated architecture are analyzed to understand the language modeling of cross-modality compared with general RNNs. |
| Author | Wang, Hanli Xu, Kaisheng Wang, Hanzhang |
| Author_xml | – sequence: 1 givenname: Hanzhang surname: Wang fullname: Wang, Hanzhang organization: Department of Computer Science & Technology, Tongji University, Shanghai, P. R. China – sequence: 2 givenname: Hanli orcidid: 0000-0002-9999-4871 surname: Wang fullname: Wang, Hanli email: hanliwang@tongji.edu.cn organization: Department of Computer Science & Technology, Tongji University, Shanghai, P. R. China – sequence: 3 givenname: Kaisheng surname: Xu fullname: Xu, Kaisheng organization: Department of Computer Science & Technology, Tongji University, Shanghai, P. R. China |
| BookMark | eNqFkL1OwzAUhS1UJNrCGzDkBRKunR87HZBQVQpSJRaYLce5rlxSu3Lcor49icrEANNZ7nd0vjsjE-cdEnJPIaNAq4dd5vCo_T5jwCCDPAPBr8iUCs5SwUQ1IVOoWZmynLIbMuv7HQDllNVTslidfHeM1jsVzklAfQwBXUyGwqC6IeKXD5-J8SGxe7XFRKvDeG3d9pZcG9X1ePeTc_LxvHpfvqSbt_Xr8mmT6pyzmJqmQlE3taoarERLsc1LxgtErXXTgDAUFS9ZARXwsgABecNEYVpR1nXBTZnPSXHp1cH3fUAjD2HYEs6Sghz95U5e_OXoLyGXg_-ALX5h2kY1bo9B2e4_-PEC4yB2shhkry06ja0dfhRl6-3fBd9XeXxR |
| CitedBy_id | crossref_primary_10_1016_j_neucom_2022_05_098 crossref_primary_10_3390_s21237982 crossref_primary_10_1007_s10661_021_09499_9 crossref_primary_10_1049_ipr2_13287 crossref_primary_10_1007_s11042_023_16687_x crossref_primary_10_1016_j_rineng_2021_100326 crossref_primary_10_1016_j_ymssp_2021_107773 crossref_primary_10_1002_clen_70003 crossref_primary_10_1186_s40537_023_00693_9 crossref_primary_10_1007_s11042_023_15497_5 crossref_primary_10_32604_csse_2023_024553 crossref_primary_10_1016_j_asoc_2023_110412 crossref_primary_10_1002_eng2_12785 crossref_primary_10_3390_electronics11172748 crossref_primary_10_1016_j_neucom_2023_03_020 crossref_primary_10_1109_ACCESS_2022_3144486 crossref_primary_10_1007_s00500_022_06907_1 crossref_primary_10_1109_TNNLS_2021_3080276 crossref_primary_10_1007_s10489_021_02734_3 crossref_primary_10_35377_saucis_04_02_866409 crossref_primary_10_1016_j_engappai_2023_106112 crossref_primary_10_3390_electronics11182935 crossref_primary_10_1039_D2SM00452F crossref_primary_10_31590_ejosat_950924 crossref_primary_10_3390_app122211750 crossref_primary_10_26636_jtit_2022_164222 crossref_primary_10_1016_j_neucom_2020_10_042 crossref_primary_10_1007_s10661_022_10844_9 crossref_primary_10_3390_sym13081347 crossref_primary_10_1007_s11063_024_11527_x crossref_primary_10_1016_j_asoc_2021_108332 crossref_primary_10_1049_cvi2_12087 |
| Cites_doi | 10.1613/jair.3994 10.1162/089976600300015015 10.1162/neco.1997.9.8.1735 10.1207/s15516709cog1402_1 10.1162/106365602320169811 |
| ContentType | Journal Article |
| Copyright | 2020 Elsevier B.V. |
| Copyright_xml | – notice: 2020 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.neucom.2020.03.087 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-8286 |
| EndPage | 256 |
| ExternalDocumentID | 10_1016_j_neucom_2020_03_087 S0925231220304744 |
| GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXLA AAXUO AAYFN ABBOA ABCQJ ABFNM ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SPC SPCBC SSN SSV SSZ T5K ZMT ~G- 29N AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN BNPGV CITATION EJD FEDTE FGOYB HLZ HVGLF HZ~ R2- RIG SBC SEW SSH WUQ XPP |
| ID | FETCH-LOGICAL-c372t-fb6e89b9a6be68d1ed35274eecccbb08f1ea75240607540803b284fd859947f53 |
| IEDL.DBID | .~1 |
| ISSN | 0925-2312 |
| IngestDate | Thu Apr 24 22:51:04 EDT 2025 Tue Jul 01 01:46:48 EDT 2025 Fri Feb 23 02:47:52 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Evolutionary algorithm Image captioning Multimodal learning |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c372t-fb6e89b9a6be68d1ed35274eecccbb08f1ea75240607540803b284fd859947f53 |
| ORCID | 0000-0002-9999-4871 |
| PageCount | 8 |
| ParticipantIDs | crossref_primary_10_1016_j_neucom_2020_03_087 crossref_citationtrail_10_1016_j_neucom_2020_03_087 elsevier_sciencedirect_doi_10_1016_j_neucom_2020_03_087 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2020-08-11 |
| PublicationDateYYYYMMDD | 2020-08-11 |
| PublicationDate_xml | – month: 08 year: 2020 text: 2020-08-11 day: 11 |
| PublicationDecade | 2020 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Jia, Gavves, Fernando, Tuytelaars (bib0031) 2015 Xu, Wang, Tang (bib0033) 2017 Nair, Hinton (bib0018) 2010 Zhou, Xu, Koch, Corso (bib0024) 2017 Hochreiter, Schmidhuber (bib0004) 1997; 9 Papineni, Roukos, Ward, Zhu (bib0017) 2002 Xu, Ba, Kiros, Cho, Courville, Salakhudinov, Zemel, Bengio (bib0026) 2015 You, Jin, Wang, Fang, Luo (bib0027) 2016 Vinyals, Toshev, Bengio, Erhan (bib0009) 2015 Real, Moore, Selle, Saxena, Suematsu, Le, Kurakin (bib0012) 2017 Dauphin, Fan, Auli, Grangier (bib0032) 2017 Banerjee, Lavie (bib0022) 2005; 29 Klambauer, Unterthiner, Mayr (bib0006) 2017 Hodosh, Young, Hockenmaier (bib0021) 2013; 47 Srivastava, Greff, Schmidhuber (bib0003) 2015 Chen, Zhang, Xiao, Nie, Shao, Liu, Chua (bib0028) 2017 Vedantam, Zitnick, Parikh (bib0016) 2015 Mao, Xu, Yang, Wang, Huang, Yuille (bib0025) 2015 Veit, Wilber, Belongie (bib0001) 2016 Elman (bib0007) 1990; 14 Karpathy, Fei-Fei (bib0008) 2015 Stanley, Miikkulainen (bib0011) 2002; 10 Wu, Shen, Liu, Dick, Hengel (bib0023) 2016 Cho, van Merrienboer, Gulcehre, Bougares, Schwenk, Bengio (bib0010) 2014 Pham, Guan, Zoph, Le, Dean (bib0015) 2018 He, Zhang, Ren, Sun (bib0002) 2016 Jozefowicz, Zaremba, Sutskever (bib0013) 2015; 37 Gers, Schmidhuber, Cummins (bib0005) 2000; 12 Zoph, Le (bib0014) 2017 Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (bib0019) 2014; 15 Lin, Maire, Belongie, Hays, Perona, Ramanan, Dollár, Zitnick (bib0020) 2014 Donahue, A. Hendricks, Guadarrama, Rohrbach, Venugopalan, Saenko, Darrell (bib0030) 2015 Kiros, Salakhutdinov, Zemel (bib0029) 2014; 14 Gers (10.1016/j.neucom.2020.03.087_bib0005) 2000; 12 Dauphin (10.1016/j.neucom.2020.03.087_bib0032) 2017 Real (10.1016/j.neucom.2020.03.087_bib0012) 2017 He (10.1016/j.neucom.2020.03.087_bib0002) 2016 Mao (10.1016/j.neucom.2020.03.087_bib0025) 2015 Banerjee (10.1016/j.neucom.2020.03.087_bib0022) 2005; 29 Veit (10.1016/j.neucom.2020.03.087_bib0001) 2016 Wu (10.1016/j.neucom.2020.03.087_bib0023) 2016 Zhou (10.1016/j.neucom.2020.03.087_bib0024) 2017 Vinyals (10.1016/j.neucom.2020.03.087_bib0009) 2015 You (10.1016/j.neucom.2020.03.087_bib0027) 2016 Srivastava (10.1016/j.neucom.2020.03.087_bib0019) 2014; 15 Hochreiter (10.1016/j.neucom.2020.03.087_bib0004) 1997; 9 Cho (10.1016/j.neucom.2020.03.087_bib0010) 2014 Lin (10.1016/j.neucom.2020.03.087_bib0020) 2014 Chen (10.1016/j.neucom.2020.03.087_bib0028) 2017 Karpathy (10.1016/j.neucom.2020.03.087_bib0008) 2015 Jia (10.1016/j.neucom.2020.03.087_bib0031) 2015 Papineni (10.1016/j.neucom.2020.03.087_bib0017) 2002 Stanley (10.1016/j.neucom.2020.03.087_bib0011) 2002; 10 Vedantam (10.1016/j.neucom.2020.03.087_bib0016) 2015 Jozefowicz (10.1016/j.neucom.2020.03.087_bib0013) 2015; 37 Nair (10.1016/j.neucom.2020.03.087_bib0018) 2010 Elman (10.1016/j.neucom.2020.03.087_bib0007) 1990; 14 Xu (10.1016/j.neucom.2020.03.087_bib0026) 2015 Zoph (10.1016/j.neucom.2020.03.087_bib0014) 2017 Pham (10.1016/j.neucom.2020.03.087_bib0015) 2018 Hodosh (10.1016/j.neucom.2020.03.087_bib0021) 2013; 47 Kiros (10.1016/j.neucom.2020.03.087_bib0029) 2014; 14 Srivastava (10.1016/j.neucom.2020.03.087_bib0003) 2015 Xu (10.1016/j.neucom.2020.03.087_bib0033) 2017 Donahue (10.1016/j.neucom.2020.03.087_bib0030) 2015 Klambauer (10.1016/j.neucom.2020.03.087_bib0006) 2017 |
| References_xml | – start-page: 3156 year: 2015 end-page: 3164 ident: bib0009 article-title: Show and tell: A neural image caption generator publication-title: Proc. CVPR’15 – start-page: 4092 year: 2018 end-page: 4101 ident: bib0015 article-title: Efficient neural architecture search via parameter sharing publication-title: Proc. ICML’18 – start-page: 807 year: 2010 end-page: 814 ident: bib0018 article-title: Rectified linear units improve restricted boltzmann machines publication-title: Proc. ICML’10 – volume: 14 start-page: 179 year: 1990 end-page: 211 ident: bib0007 article-title: Finding structure in time publication-title: Cognitive science – start-page: 550 year: 2016 end-page: 558 ident: bib0001 article-title: Residual networks behave like ensembles of relatively shallow networks publication-title: Proc. NIPS’16 – start-page: 311 year: 2002 end-page: 318 ident: bib0017 article-title: BLEU: a method for automatic evaluation of machine translation publication-title: Proc. ACL’02 – start-page: 2048 year: 2015 end-page: 2057 ident: bib0026 article-title: Show, attend and tell: Neural image caption generation with visual attention publication-title: Proc. ICML’15 – volume: 47 start-page: 853 year: 2013 end-page: 899 ident: bib0021 article-title: Framing image description as a ranking task: Data, models and evaluation metrics publication-title: Journal of Artificial Intelligence Research – start-page: 933 year: 2017 end-page: 941 ident: bib0032 article-title: Language modeling with gated convolutional networks publication-title: Proc. ICML’17 – start-page: 2407 year: 2015 end-page: 2415 ident: bib0031 article-title: Guiding the long-short term memory model for image caption generation publication-title: Proc. ICCV’15 – start-page: 1724 year: 2014 end-page: 1734 ident: bib0010 article-title: Learning phrase representations using rnn encoder- decoder for statistical machine translation. publication-title: Proc. EMNLP’14 – year: 2015 ident: bib0003 publication-title: Highway networks – start-page: 3128 year: 2015 end-page: 3137 ident: bib0008 article-title: Deep visual-semantic alignments for generating image descriptions publication-title: Proc. CVPR’15 – start-page: 740 year: 2014 end-page: 755 ident: bib0020 article-title: Microsoft coco: Common objects in context publication-title: Proc. ECCV’14 – start-page: 203 year: 2016 end-page: 212 ident: bib0023 article-title: What value do explicit high level concepts have in vision to language problems? publication-title: Proc. CVPR’16 – start-page: 770 year: 2016 end-page: 778 ident: bib0002 article-title: Deep residual learning for image recognition publication-title: Proc. CVPR’16 – year: 2017 ident: bib0006 publication-title: Self-normalizing neural networks – start-page: 2625 year: 2015 end-page: 2634 ident: bib0030 article-title: Long-term recurrent convolutional networks for visual recognition and description publication-title: Proc. CVPR’15 – volume: 14 start-page: 595 year: 2014 end-page: 603 ident: bib0029 article-title: Multimodal neural language models publication-title: Proc. ICML’14 – volume: 12 start-page: 2451 year: 2000 end-page: 2471 ident: bib0005 article-title: Learning to forget: Continual prediction with LSTM publication-title: Neural Computation – year: 2015 ident: bib0025 article-title: Deep captioning with multimodal recurrent neural networks (m-RNN) publication-title: Proc. ICLR’15 – start-page: 361 year: 2017 end-page: 366 ident: bib0033 article-title: Image captioning with deep LSTM based on sequential residual publication-title: Proc. ICME’17 – start-page: 4566 year: 2015 end-page: 4575 ident: bib0016 article-title: CIDEr: Consensus-based image description evaluation publication-title: Proc. CVPR’15 – volume: 15 start-page: 1929 year: 2014 end-page: 1958 ident: bib0019 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: JMLR – year: 2017 ident: bib0012 publication-title: Large-scale evolution of image classifiers – start-page: 305 year: 2017 end-page: 313 ident: bib0024 article-title: Watch what you just said: Image captioning with text-conditional attention publication-title: Proc. ACM Multimedia Thematic Workshops7 – year: 2017 ident: bib0014 article-title: Neural architecture search with reinforcement learning publication-title: Proc. ICLR’17 – start-page: 4233 year: 2017 end-page: 4239 ident: bib0028 article-title: Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captionin publication-title: Proc. CVPR’17 – start-page: 4651 year: 2016 end-page: 4659 ident: bib0027 article-title: Image captioning with semantic attention publication-title: Proc. CVPR’16 – volume: 37 start-page: 2342 year: 2015 end-page: 2350 ident: bib0013 article-title: An empirical exploration of recurrent network architectures publication-title: Proc. ICML’15 – volume: 29 start-page: 65 year: 2005 end-page: 72 ident: bib0022 article-title: METEOR: An automatic metric for MT evaluation with improved correlation with human judgments publication-title: Proc. ACL Workshop IEEMMTS’05 – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: bib0004 article-title: Long short-term memory publication-title: Neural Computation – volume: 10 start-page: 99 year: 2002 end-page: 127 ident: bib0011 article-title: Evolving neural networks through augmenting topologies publication-title: Evolutionary computation – start-page: 1724 year: 2014 ident: 10.1016/j.neucom.2020.03.087_bib0010 article-title: Learning phrase representations using rnn encoder- decoder for statistical machine translation. – year: 2017 ident: 10.1016/j.neucom.2020.03.087_bib0006 publication-title: Self-normalizing neural networks – start-page: 550 year: 2016 ident: 10.1016/j.neucom.2020.03.087_bib0001 article-title: Residual networks behave like ensembles of relatively shallow networks – year: 2017 ident: 10.1016/j.neucom.2020.03.087_bib0012 publication-title: Large-scale evolution of image classifiers – start-page: 305 year: 2017 ident: 10.1016/j.neucom.2020.03.087_bib0024 article-title: Watch what you just said: Image captioning with text-conditional attention – start-page: 770 year: 2016 ident: 10.1016/j.neucom.2020.03.087_bib0002 article-title: Deep residual learning for image recognition – volume: 14 start-page: 595 year: 2014 ident: 10.1016/j.neucom.2020.03.087_bib0029 article-title: Multimodal neural language models – year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0025 article-title: Deep captioning with multimodal recurrent neural networks (m-RNN) – start-page: 933 year: 2017 ident: 10.1016/j.neucom.2020.03.087_bib0032 article-title: Language modeling with gated convolutional networks – start-page: 740 year: 2014 ident: 10.1016/j.neucom.2020.03.087_bib0020 article-title: Microsoft coco: Common objects in context – volume: 37 start-page: 2342 year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0013 article-title: An empirical exploration of recurrent network architectures – year: 2017 ident: 10.1016/j.neucom.2020.03.087_bib0014 article-title: Neural architecture search with reinforcement learning – start-page: 3156 year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0009 article-title: Show and tell: A neural image caption generator – start-page: 2407 year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0031 article-title: Guiding the long-short term memory model for image caption generation – start-page: 4566 year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0016 article-title: CIDEr: Consensus-based image description evaluation – volume: 29 start-page: 65 year: 2005 ident: 10.1016/j.neucom.2020.03.087_bib0022 article-title: METEOR: An automatic metric for MT evaluation with improved correlation with human judgments – start-page: 4092 year: 2018 ident: 10.1016/j.neucom.2020.03.087_bib0015 article-title: Efficient neural architecture search via parameter sharing – volume: 47 start-page: 853 year: 2013 ident: 10.1016/j.neucom.2020.03.087_bib0021 article-title: Framing image description as a ranking task: Data, models and evaluation metrics publication-title: Journal of Artificial Intelligence Research doi: 10.1613/jair.3994 – start-page: 2625 year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0030 article-title: Long-term recurrent convolutional networks for visual recognition and description – volume: 12 start-page: 2451 year: 2000 ident: 10.1016/j.neucom.2020.03.087_bib0005 article-title: Learning to forget: Continual prediction with LSTM publication-title: Neural Computation doi: 10.1162/089976600300015015 – volume: 9 start-page: 1735 year: 1997 ident: 10.1016/j.neucom.2020.03.087_bib0004 article-title: Long short-term memory publication-title: Neural Computation doi: 10.1162/neco.1997.9.8.1735 – start-page: 2048 year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0026 article-title: Show, attend and tell: Neural image caption generation with visual attention – start-page: 807 year: 2010 ident: 10.1016/j.neucom.2020.03.087_bib0018 article-title: Rectified linear units improve restricted boltzmann machines – year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0003 publication-title: Highway networks – volume: 14 start-page: 179 issue: 2 year: 1990 ident: 10.1016/j.neucom.2020.03.087_bib0007 article-title: Finding structure in time publication-title: Cognitive science doi: 10.1207/s15516709cog1402_1 – volume: 10 start-page: 99 issue: 2 year: 2002 ident: 10.1016/j.neucom.2020.03.087_bib0011 article-title: Evolving neural networks through augmenting topologies publication-title: Evolutionary computation doi: 10.1162/106365602320169811 – start-page: 361 year: 2017 ident: 10.1016/j.neucom.2020.03.087_bib0033 article-title: Image captioning with deep LSTM based on sequential residual – start-page: 4651 year: 2016 ident: 10.1016/j.neucom.2020.03.087_bib0027 article-title: Image captioning with semantic attention – start-page: 4233 year: 2017 ident: 10.1016/j.neucom.2020.03.087_bib0028 article-title: Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captionin – start-page: 203 year: 2016 ident: 10.1016/j.neucom.2020.03.087_bib0023 article-title: What value do explicit high level concepts have in vision to language problems? – volume: 15 start-page: 1929 year: 2014 ident: 10.1016/j.neucom.2020.03.087_bib0019 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: JMLR – start-page: 3128 year: 2015 ident: 10.1016/j.neucom.2020.03.087_bib0008 article-title: Deep visual-semantic alignments for generating image descriptions – start-page: 311 year: 2002 ident: 10.1016/j.neucom.2020.03.087_bib0017 article-title: BLEU: a method for automatic evaluation of machine translation |
| SSID | ssj0017129 |
| Score | 2.4730902 |
| Snippet | Automatic architecture search is efficient to discover novel neural networks while it is mostly employed for pure vision or natural language tasks. However,... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 249 |
| SubjectTerms | Evolutionary algorithm Image captioning Multimodal learning |
| Title | Evolutionary recurrent neural network for image captioning |
| URI | https://dx.doi.org/10.1016/j.neucom.2020.03.087 |
| Volume | 401 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NSwMxEA2lXrz4LX6WHLzGbnazm8RbKS1VoRct9BaSbAIVXUtpBS_-djPdbFEQBY-7ZCBMkpm3sy9vELoKKb7U0thwxF1CWFloolPNCUiR-cz6LMRlYFuMi9GE3U3zaQv1m7swQKuMsb-O6etoHd90oze789ms-5DINHxF0TSFv3ucgSYoYxx2-fXHhuZBOU1rvb00JzC6uT635nhVbgWckTRgprXUKRDrfkpPX1LOcA_tRKyIe_V09lHLVQdot-nDgOOxPEQ3g7e4gfTiHS-ggg6aSxi0KoN9VTO9cYCnePYS4ge2eh7rsEdoMhw89kck9kQgNuPpknhTOCGN1IVxhSipKwOC4syFlbDGJMJTp3kOaTpgARbgYGZCAvKlyKVk3OfZMWpXr5U7Qdg54WRihRWFZ45L4Sg3BsRhEucLTk9R1rhC2SgYDn0rnlXDDHtStQMVOFAlmQoOPEVkYzWvBTP-GM8bL6tvC69CTP_V8uzfludoG56gNEzpBWovFyt3GbDF0nTWm6eDtnq396PxJ-noz7Y |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3PS8MwFA5zHvTib3H-7MFrXZOmTepNxsbUuYsb7BaSNoWJ1jE2wYt_u--16VAQBa9tHoSXvPe-pl--R8gllPhMJyaFELeBz7NY-5pp4aMUWR6meQh5GdkWw7g_5neTaNIgnfouDNIqXe6vcnqZrd2TtvNmezadth-DhMFXFGUM_-4JztfIOofwxTYGVx8rngcVlFWCeyzycXh9f64keRV2iaQRBqCp1DpFZt1P9elLzentkC0HFr2baj67pGGLPbJdN2LwXFzuk-vum9tBev7uzfEIHUWXPBSrBPuionp7gE-96QskEC_VM3cQe0DGve6o0_ddUwQ_DQVb-LmJrUxMomNjY5lRmwGEEtzCUqTGBDKnVosI6zSAAQ54MDRQgfJMRknCRR6Fh6RZvBb2iHjWSpsEqUxlnHMrEmmpMAbVYQKbx4K2SFi7QqVOMRwbVzyrmhr2pCoHKnSgCkIFDmwRf2U1qxQz_hgvai-rbyuvIKn_ann8b8sLstEfPQzU4HZ4f0I28Q2eE1N6SpqL-dKeAdBYmPNyI30C1ofRRA |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Evolutionary+recurrent+neural+network+for+image+captioning&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Wang%2C+Hanzhang&rft.au=Wang%2C+Hanli&rft.au=Xu%2C+Kaisheng&rft.date=2020-08-11&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=401&rft.spage=249&rft.epage=256&rft_id=info:doi/10.1016%2Fj.neucom.2020.03.087&rft.externalDocID=S0925231220304744 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |