Zero-shot learning for action recognition using synthesized features
The major disadvantage of supervised methods for action recognition is the need for a large amount of annotated data, where the data is matched to its label accurately. To address this issue, Zero-Shot Learning (ZSL) is introduced. Zero short learning primarily uses data that is synthesized to compe...
Gespeichert in:
| Veröffentlicht in: | Neurocomputing (Amsterdam) Jg. 390; S. 117 - 130 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier B.V
21.05.2020
|
| Schlagworte: | |
| ISSN: | 0925-2312, 1872-8286 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | The major disadvantage of supervised methods for action recognition is the need for a large amount of annotated data, where the data is matched to its label accurately. To address this issue, Zero-Shot Learning (ZSL) is introduced. Zero short learning primarily uses data that is synthesized to compensate for lack of training examples. In this paper, two different approaches are proposed for the synthesis of artificial examples for novel classes; namely, inverse autoregressive flow (IAF) based generative model and bi-directional adversarial GAN(Bi-dir GAN). A consequence of the proposed approach is a transductive setting using a semi-supervised variational autoencoder, where the unlabelled data from unseen classes are used to train the model. This enables the generation of novel class examples from textual descriptions. The proposed models perform well in the following settings, namely, i) Standard setting(ZSL), where the test data comes only from unseen classes, and ii) Generalized setting(GZSL), where the test data comes from both seen and unseen classes. In the case of the generalized setting, examples with pseudo labels are generated for unseen classes. Experiments are performed on three baseline datasets, UCF101, HMDB51, and Olympic. In comparison with state-of-the-art approaches, both the proposed models, IAF based generative model and Bi-dir GAN model outperform in UCF101, and Olympic datasets in all the settings and achieve comparative results in HMDB51. |
|---|---|
| AbstractList | The major disadvantage of supervised methods for action recognition is the need for a large amount of annotated data, where the data is matched to its label accurately. To address this issue, Zero-Shot Learning (ZSL) is introduced. Zero short learning primarily uses data that is synthesized to compensate for lack of training examples. In this paper, two different approaches are proposed for the synthesis of artificial examples for novel classes; namely, inverse autoregressive flow (IAF) based generative model and bi-directional adversarial GAN(Bi-dir GAN). A consequence of the proposed approach is a transductive setting using a semi-supervised variational autoencoder, where the unlabelled data from unseen classes are used to train the model. This enables the generation of novel class examples from textual descriptions. The proposed models perform well in the following settings, namely, i) Standard setting(ZSL), where the test data comes only from unseen classes, and ii) Generalized setting(GZSL), where the test data comes from both seen and unseen classes. In the case of the generalized setting, examples with pseudo labels are generated for unseen classes. Experiments are performed on three baseline datasets, UCF101, HMDB51, and Olympic. In comparison with state-of-the-art approaches, both the proposed models, IAF based generative model and Bi-dir GAN model outperform in UCF101, and Olympic datasets in all the settings and achieve comparative results in HMDB51. |
| Author | Pandey, Anubha Mishra, Ashish Murthy, Hema A. |
| Author_xml | – sequence: 1 givenname: Ashish surname: Mishra fullname: Mishra, Ashish email: mishra@cse.iitm.ac.in – sequence: 2 givenname: Anubha surname: Pandey fullname: Pandey, Anubha – sequence: 3 givenname: Hema A. surname: Murthy fullname: Murthy, Hema A. |
| BookMark | eNqFkE1LAzEQhoNUsFX_gYf9A7tmkm6SehCkfkLBi168hDSZbVPaRJJUqL_erfXkQU_zwvC8zDwjMggxICEXQBugIC5XTcCtjZuGUUYbCg2V6ogMQUlWK6bEgAzphLU148BOyCjnFaUggU2G5PYNU6zzMpZqjSYFHxZVF1NlbPExVAltXAT_nbd5v8y7UJaY_Se6qkNTtgnzGTnuzDrj-c88Ja_3dy_Tx3r2_PA0vZnVlktWajNH6Rw4pcZyzriireAAyIyg2EoFjHedsJJbp4ToqDBAxXzStmqsLHcC-Sm5OvTaFHNO2Gnri9kfV5Lxaw1U733olT740HsfmoLuffTw-Bf8nvzGpN1_2PUBw_6xD49JZ-sxWHS-l1O0i_7vgi91GX9k |
| CitedBy_id | crossref_primary_10_1007_s10489_020_02075_7 crossref_primary_10_1109_LSP_2022_3200605 crossref_primary_10_1007_s11042_024_19711_w crossref_primary_10_1109_TCSVT_2023_3262754 crossref_primary_10_3233_IDT_24027 crossref_primary_10_1016_j_neucom_2021_01_036 crossref_primary_10_1007_s10489_023_04808_w crossref_primary_10_1007_s11263_023_01846_2 crossref_primary_10_1007_s10462_024_10934_9 crossref_primary_10_1016_j_neucom_2020_09_065 crossref_primary_10_1016_j_neucom_2021_04_031 crossref_primary_10_1016_j_knosys_2024_112283 crossref_primary_10_1016_j_eswa_2023_122538 crossref_primary_10_3233_IDT_240297 crossref_primary_10_1016_j_eswa_2024_125150 crossref_primary_10_1016_j_neucom_2024_128385 crossref_primary_10_1007_s10044_021_00992_y crossref_primary_10_1016_j_neucom_2021_03_070 crossref_primary_10_3390_app15073737 crossref_primary_10_1007_s42979_023_01803_3 crossref_primary_10_3390_mca28020061 crossref_primary_10_1155_2022_2142935 |
| Cites_doi | 10.1109/TPAMI.2013.140 10.1007/s11263-017-1027-5 10.1007/s11263-016-0983-5 |
| ContentType | Journal Article |
| Copyright | 2020 |
| Copyright_xml | – notice: 2020 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.neucom.2020.01.078 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-8286 |
| EndPage | 130 |
| ExternalDocumentID | 10_1016_j_neucom_2020_01_078 S0925231220301302 |
| 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 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC SEW WUQ XPP ~HD |
| ID | FETCH-LOGICAL-c372t-abe7dd1d8847b238056311e2a60e578123ff6c73cd866f06a106b955848c3d6e3 |
| ISICitedReferencesCount | 28 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000531729000011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0925-2312 |
| IngestDate | Tue Nov 18 20:38:48 EST 2025 Sat Nov 29 07:11:19 EST 2025 Fri Feb 23 02:47:40 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Transductive ZSL setting Inverse autoregressive flow Generalized zero shot learning Bi-directional generative adversarial network Inductive ZSL setting |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c372t-abe7dd1d8847b238056311e2a60e578123ff6c73cd866f06a106b955848c3d6e3 |
| PageCount | 14 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_neucom_2020_01_078 crossref_primary_10_1016_j_neucom_2020_01_078 elsevier_sciencedirect_doi_10_1016_j_neucom_2020_01_078 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-05-21 |
| PublicationDateYYYYMMDD | 2020-05-21 |
| PublicationDate_xml | – month: 05 year: 2020 text: 2020-05-21 day: 21 |
| PublicationDecade | 2020 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Lampert, Nickisch, Harmeling (bib0014) 2014; 36 Radovanović, Nanopoulos, Ivanović (bib0021) 2010; 11 Zhang, Saligrama (bib0032) 2015 Kodirov, Xiang, Fu, Gong (bib0009) 2015 Gaure, Gupta, Verma, Rai (bib0027) 2017 M. Bishay, G. Zoumpourlis, I. Patras D.P. Kingma, M. Welling, TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition, arXiv preprint arXiv K. Soomro, A.R. Zamir, M. Shah, UCF101: A dataset of 101 human actions classes from videos in the wild, arXiv preprint arXiv Mandal, Narayan, Dwivedi, Gupta, Ahmed, Khan, Shao (bib0040) 2019 Qin, Liu, Shao, Shen, Ni, Chen, Wang (bib0039) 2017 Guo, Ding, Han, Gao (bib0028) 2017 Wang, Ye, Gupta (bib0036) 2018 Zhu, Long, Guan, Newsam, Shao (bib0037) 2018 Changpinyo, Chao, Gong, Sha (bib0029) 2016 Romera-Paredes, Torr (bib0010) 2015 Kodirov, Xiang, Gong (bib0048) 2017 Xu, Hospedales, Gong (bib0016) 2017; 123 He, Zhang, Ren, Sun (bib0025) 2016 Xu, Hospedales, Gong (bib0006) 2015 (2013). Kingma, Mohamed, Rezende, Welling (bib0026) 2014 Bucher, Herbin, Jurie (bib0042) 2017 (2019). Xian, Schiele, Akata (bib0003) 2017 Mikolov, Sutskever, Chen, Corrado, Dean (bib0004) 2013 Kuehne, Jhuang, Garrote, Poggio, Serre (bib0046) 2011 Wang, Kläser, Schmid, Cheng-Lin (bib0053) 2011 Verma, Rai (bib0018) 2017 Tran, Bourdev, Fergus, Torresani, Paluri (bib0047) 2015 D.P. Kingma, M. Welling, Auto-encoding variational bayes, arXiv preprint arXiv Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (bib0023) 2014 Wang, Chen (bib0008) 2017; 124 Mishra, Krishna Reddy, Mittal, Murthy (bib0030) 2018 Kodirov, Xiang, Gong (bib0007) 2017 Simonyan, Zisserman (bib0052) 2014 Xu, Hospedales, Gong (bib0015) 2016 Felix, Kumar, Reid, Carneiro (bib0034) 2018 Roitberg, Martinez, Haurilet, Stiefelhagen (bib0038) 2018 Xian, Lorenz, Schiele, Akata (bib0049) 2018 Palatucci, Pomerleau, Hinton, Mitchell (bib0001) 2009 Pennington, Socher, Manning (bib0005) 2014 Akata, Reed, Walter, Lee, Schiele (bib0013) 2015 Wang, Schmid (bib0054) 2013 M. Norouzi, T. Mikolov, S. Bengio, Y. Singer, J. Shlens, A. Frome, G.S. Corrado, J. Dean, Zero-shot learning by convex combination of semantic embeddings, arXiv preprint arXiv Hu, Yang, Liang, Salakhutdinov, Xing (bib0044) 2017 (2014). Kingma, Salimans, Jozefowicz, Chen, Sutskever, Welling (bib0024) 2016 Xian, Lorenz, Schiele, Akata (bib0033) 2018 (2012). Zhang, Saligrama (bib0031) 2016 Lampert, Nickisch, Harmeling (bib0002) 2009 Kumar Verma, Arora, Mishra, Rai (bib0035) 2018 Germain, Gregor, Murray, Larochelle (bib0043) 2015 G. Dinu, A. Lazaridou, M. Baroni, Improving zero-shot learning by mitigating the hubness problem, arXiv preprint arXiv Liu, Kuipers, Savarese (bib0011) 2011 Wang, Pu, Verma, Fan, Zhang, Chen, Rai, Carin (bib0017) 2018 Felix, Kumar, Reid, Carneiro (bib0050) 2018 Mishra, Verma, Reddy, Arulkumar, Rai, Mittal (bib0019) 2018 Mikolov (10.1016/j.neucom.2020.01.078_bib0004) 2013 Felix (10.1016/j.neucom.2020.01.078_bib0050) 2018 He (10.1016/j.neucom.2020.01.078_bib0025) 2016 Changpinyo (10.1016/j.neucom.2020.01.078_bib0029) 2016 Wang (10.1016/j.neucom.2020.01.078_bib0008) 2017; 124 Felix (10.1016/j.neucom.2020.01.078_bib0034) 2018 Palatucci (10.1016/j.neucom.2020.01.078_bib0001) 2009 Kuehne (10.1016/j.neucom.2020.01.078_bib0046) 2011 Wang (10.1016/j.neucom.2020.01.078_bib0054) 2013 Xu (10.1016/j.neucom.2020.01.078_bib0015) 2016 Verma (10.1016/j.neucom.2020.01.078_bib0018) 2017 Lampert (10.1016/j.neucom.2020.01.078_bib0002) 2009 10.1016/j.neucom.2020.01.078_bib0022 10.1016/j.neucom.2020.01.078_bib0020 Zhu (10.1016/j.neucom.2020.01.078_bib0037) 2018 Xu (10.1016/j.neucom.2020.01.078_bib0016) 2017; 123 Kingma (10.1016/j.neucom.2020.01.078_bib0026) 2014 Gaure (10.1016/j.neucom.2020.01.078_bib0027) 2017 Tran (10.1016/j.neucom.2020.01.078_bib0047) 2015 Mandal (10.1016/j.neucom.2020.01.078_bib0040) 2019 Wang (10.1016/j.neucom.2020.01.078_bib0017) 2018 Goodfellow (10.1016/j.neucom.2020.01.078_bib0023) 2014 Mishra (10.1016/j.neucom.2020.01.078_bib0030) 2018 Wang (10.1016/j.neucom.2020.01.078_bib0053) 2011 10.1016/j.neucom.2020.01.078_bib0012 Liu (10.1016/j.neucom.2020.01.078_bib0011) 2011 Xian (10.1016/j.neucom.2020.01.078_bib0003) 2017 Kodirov (10.1016/j.neucom.2020.01.078_bib0009) 2015 Lampert (10.1016/j.neucom.2020.01.078_bib0014) 2014; 36 Guo (10.1016/j.neucom.2020.01.078_bib0028) 2017 Qin (10.1016/j.neucom.2020.01.078_bib0039) 2017 Xu (10.1016/j.neucom.2020.01.078_bib0006) 2015 Bucher (10.1016/j.neucom.2020.01.078_bib0042) 2017 Zhang (10.1016/j.neucom.2020.01.078_bib0031) 2016 Wang (10.1016/j.neucom.2020.01.078_bib0036) 2018 10.1016/j.neucom.2020.01.078_bib0045 Xian (10.1016/j.neucom.2020.01.078_bib0049) 2018 Kumar Verma (10.1016/j.neucom.2020.01.078_bib0035) 2018 Simonyan (10.1016/j.neucom.2020.01.078_bib0052) 2014 Akata (10.1016/j.neucom.2020.01.078_bib0013) 2015 10.1016/j.neucom.2020.01.078_bib0041 Hu (10.1016/j.neucom.2020.01.078_bib0044) 2017 Pennington (10.1016/j.neucom.2020.01.078_bib0005) 2014 Romera-Paredes (10.1016/j.neucom.2020.01.078_bib0010) 2015 Zhang (10.1016/j.neucom.2020.01.078_bib0032) 2015 Kodirov (10.1016/j.neucom.2020.01.078_bib0048) 2017 Radovanović (10.1016/j.neucom.2020.01.078_bib0021) 2010; 11 Kodirov (10.1016/j.neucom.2020.01.078_bib0007) 2017 Mishra (10.1016/j.neucom.2020.01.078_bib0019) 2018 Kingma (10.1016/j.neucom.2020.01.078_bib0024) 2016 Roitberg (10.1016/j.neucom.2020.01.078_bib0038) 2018 Germain (10.1016/j.neucom.2020.01.078_bib0043) 2015 Xian (10.1016/j.neucom.2020.01.078_bib0033) 2018 |
| References_xml | – start-page: 3337 year: 2011 end-page: 3344 ident: bib0011 article-title: Recognizing human actions by attributes publication-title: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 2556 year: 2011 end-page: 2563 ident: bib0046 article-title: HMDB: a large video database for human motion recognition publication-title: Proceedings of the 2011 IEEE International Conference on Computer Vision (ICCV) – start-page: 2188 year: 2018 end-page: 2196 ident: bib0030 article-title: A generative model for zero shot learning using conditional variational autoencoders publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops – reference: (2012). – start-page: 6034 year: 2016 end-page: 6042 ident: bib0031 article-title: Zero-shot learning via joint latent similarity embedding publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 372 year: 2018 end-page: 380 ident: bib0019 article-title: A generative approach to zero-shot and few-shot action recognition publication-title: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) – start-page: 63 year: 2015 end-page: 67 ident: bib0006 article-title: Semantic embedding space for zero-shot action recognition publication-title: Proceedings of, 2015 IEEE International Conference on the Image Processing (ICIP) – start-page: 951 year: 2009 end-page: 958 ident: bib0002 article-title: Learning to detect unseen object classes by between-class attribute transfer publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009 – start-page: 5542 year: 2018 end-page: 5551 ident: bib0049 article-title: Feature generating networks for zero-shot learning publication-title: Proceedings of the CVPR – start-page: 3174 year: 2017 end-page: 3183 ident: bib0007 article-title: Semantic autoencoder for zero-shot learning publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 11 start-page: 2487 year: 2010 end-page: 2531 ident: bib0021 article-title: Hubs in space: popular nearest neighbors in high-dimensional data publication-title: J. Mach. Learn. Res. – start-page: 4281 year: 2018 end-page: 4289 ident: bib0035 article-title: Generalized zero-shot learning via synthesized examples publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition – start-page: 792 year: 2017 end-page: 808 ident: bib0018 article-title: A simple exponential family framework for zero-shot learning publication-title: Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases – reference: M. Bishay, G. Zoumpourlis, I. Patras D.P. Kingma, M. Welling, TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition, arXiv preprint arXiv: – year: 2017 ident: bib0042 article-title: Generating visual representations for zero-shot classification publication-title: Proceedings of the International Conference on Computer Vision (ICCV) Workshops: TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision – volume: 36 start-page: 453 year: 2014 end-page: 465 ident: bib0014 article-title: Attribute-based classification for zero-shot visual object categorization publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1587 year: 2017 end-page: 1596 ident: bib0044 article-title: Toward controlled generation of text publication-title: Proceedings of the International Conference on Machine Learning – start-page: 1774 year: 2017 end-page: 1780 ident: bib0028 article-title: Synthesizing samples fro zero-shot learning publication-title: IJCAI – start-page: 2672 year: 2014 end-page: 2680 ident: bib0023 article-title: Generative adversarial nets publication-title: Proceedings of the Advances in Neural Information Processing Systems – start-page: 2927 year: 2015 end-page: 2936 ident: bib0013 article-title: Evaluation of output embeddings for fine-grained image classification publication-title: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – reference: G. Dinu, A. Lazaridou, M. Baroni, Improving zero-shot learning by mitigating the hubness problem, arXiv preprint arXiv: – start-page: 6857 year: 2018 end-page: 6866 ident: bib0036 article-title: Zero-shot recognition via semantic embeddings and knowledge graphs publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1532 year: 2014 end-page: 1543 ident: bib0005 article-title: Glove: global vectors for word representation publication-title: Proceedings of the 2014 Conference on Empirical Methods in Natural language processing (EMNLP) – reference: D.P. Kingma, M. Welling, Auto-encoding variational bayes, arXiv preprint arXiv: – start-page: 3581 year: 2014 end-page: 3589 ident: bib0026 article-title: Semi-supervised learning with deep generative models publication-title: Proceedings of the Advances in Neural Information Processing Systems – year: 2018 ident: bib0038 article-title: Towards a fair evaluation of zero-shot action recognition using external data publication-title: Proceedings of the European Conference on Computer Vision (ECCV) – start-page: 2452 year: 2015 end-page: 2460 ident: bib0009 article-title: Unsupervised domain adaptation for zero-shot learning publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 881 year: 2015 end-page: 889 ident: bib0043 article-title: Made: masked autoencoder for distribution estimation publication-title: Proceedings of the International Conference on Machine Learning – start-page: 3 year: 2017 end-page: 12 ident: bib0027 article-title: A probabilistic framework for zero-shot multi-label learning publication-title: Proceedings of the the Conference on Uncertainty in Artificial Intelligence (UAI) – volume: 123 start-page: 309 year: 2017 end-page: 333 ident: bib0016 article-title: Transductive zero-shot action recognition by word-vector embedding publication-title: Int. J. Comput. Vis. – start-page: 5327 year: 2016 end-page: 5336 ident: bib0029 article-title: Synthesized classifiers for zero-shot learning publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2019 ident: bib0040 article-title: Out-of-distribution detection for generalized zero-shot action recognition publication-title: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – reference: (2019). – volume: 124 start-page: 356 year: 2017 end-page: 383 ident: bib0008 article-title: Zero-shot visual recognition via bidirectional latent embedding publication-title: Int. J. Comput. Vis. – start-page: 343 year: 2016 end-page: 359 ident: bib0015 article-title: Multi-task zero-shot action recognition with prioritised data augmentation publication-title: Proceedings of the European Conference on Computer Vision – year: 2018 ident: bib0017 article-title: Zero-shot learning via class-conditioned deep generative models publication-title: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-18), Louisiana, USA. – reference: M. Norouzi, T. Mikolov, S. Bengio, Y. Singer, J. Shlens, A. Frome, G.S. Corrado, J. Dean, Zero-shot learning by convex combination of semantic embeddings, arXiv preprint arXiv: – start-page: 21 year: 2018 end-page: 37 ident: bib0050 article-title: Multi-modal cycle-consistent generalized zero-shot learning publication-title: Proceedings of the ECCV – start-page: 21 year: 2018 end-page: 37 ident: bib0034 article-title: Multi-modal cycle-consistent generalized zero-shot learning publication-title: Proceedings of the European Conference on Computer Vision (ECCV) – start-page: 1410 year: 2009 end-page: 1418 ident: bib0001 article-title: Zero-shot learning with semantic output codes publication-title: Proceedings of the Advances in Neural Information Processing Systems – start-page: 4582 year: 2017 end-page: 4591 ident: bib0003 article-title: Zero-shot learning-the good, the bad and the ugly publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 2833 year: 2017 end-page: 2842 ident: bib0039 article-title: Zero-shot action recognition with error-correcting output codes publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 3111 year: 2013 end-page: 3119 ident: bib0004 article-title: Distributed representations of words and phrases and their compositionality publication-title: Proceedings of the Advances in Neural Information Processing Systems – start-page: 4743 year: 2016 end-page: 4751 ident: bib0024 article-title: Improved variational inference with inverse autoregressive flow publication-title: Proceedings of the Advances in Neural Information Processing Systems – reference: (2014). – start-page: 4489 year: 2015 end-page: 4497 ident: bib0047 article-title: Learning spatiotemporal features with 3D convolutional networks publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 3174 year: 2017 end-page: 3183 ident: bib0048 article-title: Semantic autoencoder for zero-shot learning publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 3169 year: 2011 end-page: 3176 ident: bib0053 article-title: Action recognition by dense trajectories publication-title: Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, CVPR 2011 – start-page: 2152 year: 2015 end-page: 2161 ident: bib0010 article-title: An embarrassingly simple approach to zero-shot learning publication-title: Proceedings of the International Conference on Machine Learning – start-page: 9436 year: 2018 end-page: 9445 ident: bib0037 article-title: Towards universal representation for unseen action recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – reference: K. Soomro, A.R. Zamir, M. Shah, UCF101: A dataset of 101 human actions classes from videos in the wild, arXiv preprint arXiv: – reference: (2013). – start-page: 770 year: 2016 end-page: 778 ident: bib0025 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 4166 year: 2015 end-page: 4174 ident: bib0032 article-title: Zero-shot learning via semantic similarity embedding publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 3551 year: 2013 end-page: 3558 ident: bib0054 article-title: Action recognition with improved trajectories publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 5542 year: 2018 end-page: 5551 ident: bib0033 article-title: Feature generating networks for zero-shot learning publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 568 year: 2014 end-page: 576 ident: bib0052 article-title: Two-stream convolutional networks for action recognition in videos publication-title: Proceedings of the Advances in Neural Information Processing Systems – start-page: 2188 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0030 article-title: A generative model for zero shot learning using conditional variational autoencoders – start-page: 9436 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0037 article-title: Towards universal representation for unseen action recognition – start-page: 2833 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0039 article-title: Zero-shot action recognition with error-correcting output codes – start-page: 4489 year: 2015 ident: 10.1016/j.neucom.2020.01.078_bib0047 article-title: Learning spatiotemporal features with 3D convolutional networks – year: 2019 ident: 10.1016/j.neucom.2020.01.078_bib0040 article-title: Out-of-distribution detection for generalized zero-shot action recognition – start-page: 951 year: 2009 ident: 10.1016/j.neucom.2020.01.078_bib0002 article-title: Learning to detect unseen object classes by between-class attribute transfer – start-page: 21 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0034 article-title: Multi-modal cycle-consistent generalized zero-shot learning – start-page: 1774 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0028 article-title: Synthesizing samples fro zero-shot learning – start-page: 63 year: 2015 ident: 10.1016/j.neucom.2020.01.078_bib0006 article-title: Semantic embedding space for zero-shot action recognition – start-page: 792 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0018 article-title: A simple exponential family framework for zero-shot learning – year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0017 article-title: Zero-shot learning via class-conditioned deep generative models – ident: 10.1016/j.neucom.2020.01.078_bib0022 – start-page: 2672 year: 2014 ident: 10.1016/j.neucom.2020.01.078_bib0023 article-title: Generative adversarial nets – start-page: 5542 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0033 article-title: Feature generating networks for zero-shot learning – start-page: 3174 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0048 article-title: Semantic autoencoder for zero-shot learning – volume: 11 start-page: 2487 issue: Sep year: 2010 ident: 10.1016/j.neucom.2020.01.078_bib0021 article-title: Hubs in space: popular nearest neighbors in high-dimensional data publication-title: J. Mach. Learn. Res. – start-page: 2452 year: 2015 ident: 10.1016/j.neucom.2020.01.078_bib0009 article-title: Unsupervised domain adaptation for zero-shot learning – start-page: 2556 year: 2011 ident: 10.1016/j.neucom.2020.01.078_bib0046 article-title: HMDB: a large video database for human motion recognition – start-page: 881 year: 2015 ident: 10.1016/j.neucom.2020.01.078_bib0043 article-title: Made: masked autoencoder for distribution estimation – start-page: 1410 year: 2009 ident: 10.1016/j.neucom.2020.01.078_bib0001 article-title: Zero-shot learning with semantic output codes – start-page: 4281 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0035 article-title: Generalized zero-shot learning via synthesized examples – start-page: 372 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0019 article-title: A generative approach to zero-shot and few-shot action recognition – start-page: 21 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0050 article-title: Multi-modal cycle-consistent generalized zero-shot learning – start-page: 4743 year: 2016 ident: 10.1016/j.neucom.2020.01.078_bib0024 article-title: Improved variational inference with inverse autoregressive flow – volume: 36 start-page: 453 issue: 3 year: 2014 ident: 10.1016/j.neucom.2020.01.078_bib0014 article-title: Attribute-based classification for zero-shot visual object categorization publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2013.140 – start-page: 4582 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0003 article-title: Zero-shot learning-the good, the bad and the ugly – year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0042 article-title: Generating visual representations for zero-shot classification – start-page: 5327 year: 2016 ident: 10.1016/j.neucom.2020.01.078_bib0029 article-title: Synthesized classifiers for zero-shot learning – start-page: 770 year: 2016 ident: 10.1016/j.neucom.2020.01.078_bib0025 article-title: Deep residual learning for image recognition – start-page: 343 year: 2016 ident: 10.1016/j.neucom.2020.01.078_bib0015 article-title: Multi-task zero-shot action recognition with prioritised data augmentation – start-page: 3581 year: 2014 ident: 10.1016/j.neucom.2020.01.078_bib0026 article-title: Semi-supervised learning with deep generative models – start-page: 3 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0027 article-title: A probabilistic framework for zero-shot multi-label learning – start-page: 3337 year: 2011 ident: 10.1016/j.neucom.2020.01.078_bib0011 article-title: Recognizing human actions by attributes – start-page: 3174 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0007 article-title: Semantic autoencoder for zero-shot learning – start-page: 6857 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0036 article-title: Zero-shot recognition via semantic embeddings and knowledge graphs – start-page: 1587 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0044 article-title: Toward controlled generation of text – volume: 124 start-page: 356 issue: 3 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0008 article-title: Zero-shot visual recognition via bidirectional latent embedding publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-017-1027-5 – start-page: 4166 year: 2015 ident: 10.1016/j.neucom.2020.01.078_bib0032 article-title: Zero-shot learning via semantic similarity embedding – start-page: 3551 year: 2013 ident: 10.1016/j.neucom.2020.01.078_bib0054 article-title: Action recognition with improved trajectories – ident: 10.1016/j.neucom.2020.01.078_bib0012 – start-page: 3169 year: 2011 ident: 10.1016/j.neucom.2020.01.078_bib0053 article-title: Action recognition by dense trajectories – start-page: 1532 year: 2014 ident: 10.1016/j.neucom.2020.01.078_bib0005 article-title: Glove: global vectors for word representation – start-page: 6034 year: 2016 ident: 10.1016/j.neucom.2020.01.078_bib0031 article-title: Zero-shot learning via joint latent similarity embedding – volume: 123 start-page: 309 issue: 3 year: 2017 ident: 10.1016/j.neucom.2020.01.078_bib0016 article-title: Transductive zero-shot action recognition by word-vector embedding publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-016-0983-5 – start-page: 2152 year: 2015 ident: 10.1016/j.neucom.2020.01.078_bib0010 article-title: An embarrassingly simple approach to zero-shot learning – ident: 10.1016/j.neucom.2020.01.078_bib0045 – start-page: 5542 year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0049 article-title: Feature generating networks for zero-shot learning – start-page: 3111 year: 2013 ident: 10.1016/j.neucom.2020.01.078_bib0004 article-title: Distributed representations of words and phrases and their compositionality – start-page: 2927 year: 2015 ident: 10.1016/j.neucom.2020.01.078_bib0013 article-title: Evaluation of output embeddings for fine-grained image classification – ident: 10.1016/j.neucom.2020.01.078_bib0041 – ident: 10.1016/j.neucom.2020.01.078_bib0020 – start-page: 568 year: 2014 ident: 10.1016/j.neucom.2020.01.078_bib0052 article-title: Two-stream convolutional networks for action recognition in videos – year: 2018 ident: 10.1016/j.neucom.2020.01.078_bib0038 article-title: Towards a fair evaluation of zero-shot action recognition using external data |
| SSID | ssj0017129 |
| Score | 2.4971967 |
| Snippet | The major disadvantage of supervised methods for action recognition is the need for a large amount of annotated data, where the data is matched to its label... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 117 |
| SubjectTerms | Bi-directional generative adversarial network Generalized zero shot learning Inductive ZSL setting Inverse autoregressive flow Transductive ZSL setting |
| Title | Zero-shot learning for action recognition using synthesized features |
| URI | https://dx.doi.org/10.1016/j.neucom.2020.01.078 |
| Volume | 390 |
| WOSCitedRecordID | wos000531729000011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELbQlgMXKC9RCsgHbshVYmdj-xiVVgVBLxS04hI5tqPdqs1Wmywq_fUdP5KNWMRL4hJZUbw78nyZfB7PA6HXWiYZB-US19aWZEzXpJoaRWDnkFHlPlC-lt6XD_z0VMxmsj_RbX07Ad404vpaXv1XVcM9ULZLnf0LdQ8_CjdgDEqHK6gdrn-k-K92tSTtfNn1HSFipGToCT4EDMF47f0E7fcGSGC7uAHqWVtf57MdU1ZfvkP75g_RrVBcuuoKxkFpcCN8XLTzVfDRtnMYb46mGhO84kWzruZqpOAuKPjEXqo3xcHY_UD9yTnduB-282KCc5HCUywGSNtgWgWnPml9bHtZ6BUarWca0jjjhzgNBzZbNj64G84PGrt2AT9OKF95NbQC-qF69icnipOEur0fc2VHdyifSjFBO8W7o9n74ciJpzQUZoyi93mWPhhw-79-zmNG3ORsF92PmwpcBDA8RHds8wg96Bt24Gi_H6O3AzZwjw0M2MABG3iEDeyxgUfYwD02nqDPx0dnhyckttEgmnHaEVVZbkxqBBCRChgaUF6WppaqPLFgr4G61HWuOdNG5Hmd5CpN8kpOgZkKzUxu2VM0aZaNfYZAHKmENZzSWmbSZEpQllF4r7mSU5nWe4j1i1LqWGPetTq5KPtgwvMyLGXplrJM0hKWcg-RYdZVqLHym-d5v95l5ImB_5UAkV_OfP7PM_fRvQ36X6BJt1rbl-iu_tYt2tWriKVbMnWNUw |
| linkProvider | Elsevier |
| 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=Zero-shot+learning+for+action+recognition+using+synthesized+features&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Mishra%2C+Ashish&rft.au=Pandey%2C+Anubha&rft.au=Murthy%2C+Hema+A.&rft.date=2020-05-21&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=390&rft.spage=117&rft.epage=130&rft_id=info:doi/10.1016%2Fj.neucom.2020.01.078&rft.externalDocID=S0925231220301302 |
| 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 |