TSRN: two-stage refinement network for temporal action segmentation
In high-level video semantic understanding, continuous action segmentation is a challenging task aimed at segmenting an untrimmed video and labeling each segment with predefined labels over time. However, the accuracy of segment predictions is limited by confusing information in video sequences, suc...
Saved in:
| Published in | Pattern analysis and applications : PAA Vol. 26; no. 3; pp. 1375 - 1393 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
London
Springer London
01.08.2023
Springer Nature B.V |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | In high-level video semantic understanding, continuous action segmentation is a challenging task aimed at segmenting an untrimmed video and labeling each segment with predefined labels over time. However, the accuracy of segment predictions is limited by confusing information in video sequences, such as ambiguous frames during action boundaries or over-segmentation errors due to the lack of semantic relations. In this work, we present a two-stage refinement network (TSRN) to improve temporal action segmentation. We first capture global relations over an entire video sequence using a multi-head self-attention mechanism in the novel transformer temporal convolutional network and model temporal relations in each action segment. Then, we introduce a dual-attention spatial pyramid pooling network to fuse features from macroscale and microscale perspectives, providing more accurate classification results from the initial prediction. In addition, a joint loss function mitigates over-segmentation. Compared with state-of-the-art methods, the proposed TSRN substantially improves temporal action segmentation on three challenging datasets (i.e., 50Salads, Georgia Tech Egocentric Activities, and Breakfast). |
|---|---|
| AbstractList | In high-level video semantic understanding, continuous action segmentation is a challenging task aimed at segmenting an untrimmed video and labeling each segment with predefined labels over time. However, the accuracy of segment predictions is limited by confusing information in video sequences, such as ambiguous frames during action boundaries or over-segmentation errors due to the lack of semantic relations. In this work, we present a two-stage refinement network (TSRN) to improve temporal action segmentation. We first capture global relations over an entire video sequence using a multi-head self-attention mechanism in the novel transformer temporal convolutional network and model temporal relations in each action segment. Then, we introduce a dual-attention spatial pyramid pooling network to fuse features from macroscale and microscale perspectives, providing more accurate classification results from the initial prediction. In addition, a joint loss function mitigates over-segmentation. Compared with state-of-the-art methods, the proposed TSRN substantially improves temporal action segmentation on three challenging datasets (i.e., 50Salads, Georgia Tech Egocentric Activities, and Breakfast). |
| Author | Jin, Ye Tian, Xiaoyan Tang, Xianglong |
| Author_xml | – sequence: 1 givenname: Xiaoyan surname: Tian fullname: Tian, Xiaoyan organization: Harbin Institute of Technology – sequence: 2 givenname: Ye surname: Jin fullname: Jin, Ye email: jinye@hit.edu.cn organization: Harbin Institute of Technology – sequence: 3 givenname: Xianglong surname: Tang fullname: Tang, Xianglong organization: Harbin Institute of Technology |
| BookMark | eNp9kE1LAzEQhoNUsK3-AU8LnqOZze4m602KX1AUtIK3kKRJ2dpNapIi_nt3XVHw0EsmM7zPfLwTNHLeGYROgZwDIewidm9RYJJTTACqCvMDNIaCUszK8nX0-y_gCE1iXBNCKc35GM0Wz08Pl1n68DgmuTJZMLZxpjUuZc505fCWWR-yZNqtD3KTSZ0a77JoVr1G9skxOrRyE83JT5yil5vrxewOzx9v72dXc6wp1AnntpSs5qCMUTVIu9SKVkQxrkrFQC8NqeoagFa0Kq0FyZRmtLKcEqqJ5opO0dnQdxv8-87EJNZ-F1w3UuS8IIyzHHin4oNKBx9jd47QzbBnCrLZCCCit0wMlonOMvFtmejR_B-6DU0rw-d-iA5Q7MRuZcLfVnuoL3nsgFk |
| CitedBy_id | crossref_primary_10_1007_s11042_024_18684_0 crossref_primary_10_1016_j_engappai_2025_110334 crossref_primary_10_3390_math12010057 crossref_primary_10_1007_s00371_024_03598_7 crossref_primary_10_1007_s11042_023_17276_8 crossref_primary_10_1007_s00530_024_01451_4 crossref_primary_10_1007_s11760_024_03199_w crossref_primary_10_1109_TPAMI_2024_3509434 crossref_primary_10_1109_JSEN_2024_3381928 |
| Cites_doi | 10.1007/s10489-020-01933-8 10.1109/TPAMI.2015.2389824 10.1016/j.neucom.2020.03.066 10.1109/TPAMI.2021.3132068 10.1109/TPAMI.2020.3021756 10.1007/s10044-021-00989-7 10.1007/s10489-019-01587-1 10.1016/j.jpdc.2018.06.012 10.1371/journal.pcbi.1008935 10.1007/s10044-019-00821-3 10.18653/v1/P19-1340 10.1109/CVPR.2019.00369 10.1109/CVPR46437.2021.01653 10.1109/CVPR.2016.216 10.1109/WACV45572.2020.9093535 10.1109/CVPR.2018.00705 10.1109/ICCV48922.2021.00676 10.1109/CVPR.2015.7298935 10.1109/ICCV.2017.324 10.1109/ICCVW.2017.95 10.1007/978-3-030-58595-2_3 10.1109/CVPR.2017.502 10.1109/CVPR.2014.105 10.1109/CVPR.2019.01228 10.1109/CVPR42600.2020.00947 10.1109/CVPR.2015.7298878 10.1109/CVPR.2011.5995444 10.1109/CVPR.2012.6247808 10.1109/CVPR46437.2021.00681 10.1109/CVPR.2017.140 10.1109/ICCV.2015.510 10.1109/CVPR42600.2020.01404 10.1109/CVPR.2018.00745 10.1109/WACV.2016.7477701 10.1109/CVPR.2017.113 10.1109/ICCV.2019.00718 10.1109/CVPR.2014.286 10.1109/WACV48630.2021.00237 10.1109/CVPR.2017.787 10.1007/978-3-030-01234-2_1 10.1109/CVPR.2012.6247801 10.1609/aaai.v35i4.16377 10.1007/978-3-319-46487-9_3 10.1145/2493432.2493482 10.1007/978-3-642-40760-4_43 10.1109/CVPR.2017.106 10.1109/ICCV.2019.00638 |
| ContentType | Journal Article |
| Copyright | The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| Copyright_xml | – notice: The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| DBID | AAYXX CITATION |
| DOI | 10.1007/s10044-023-01166-8 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Computer Science |
| EISSN | 1433-755X |
| EndPage | 1393 |
| ExternalDocumentID | 10_1007_s10044_023_01166_8 |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 51935005 funderid: http://dx.doi.org/10.13039/501100001809 – fundername: Natural Science Foundation of Heilongjiang Province of China grantid: LH2021F023 – fundername: Science & Technology Planned Project of Heilongjiang Province of China grantid: GA21C031 – fundername: Basic Research Key Project grantid: JCKY20200603C010 |
| GroupedDBID | -59 -5G -BR -EM -Y2 -~C .86 .DC .VR 06D 0R~ 0VY 123 1N0 1SB 203 29O 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5VS 67Z 6NX 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFO ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACREN ACSNA ACZOJ ADHHG ADHIR ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADYOE ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFGCZ AFLOW AFQWF AFWTZ AFYQB AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMTXH AMXSW AMYLF AMYQR AOCGG ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN B-. BA0 BDATZ BGNMA BSONS CAG COF CSCUP DDRTE DL5 DNIVK DPUIP DU5 EBLON EBS EIOEI EJD ESBYG F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS H13 HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I09 IHE IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z J9A JBSCW JCJTX JZLTJ KDC KOV LAS LLZTM M4Y MA- N2Q N9A NB0 NPVJJ NQJWS NU0 O9- O93 O9J OAM P2P P9O PF0 PT4 PT5 QOS R89 R9I RIG RNI ROL RPX RSV RZK S16 S1Z S27 S3B SAP SCO SDH SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z7R Z7X Z81 Z83 Z88 ZMTXR ~A9 AAPKM AAYXX ABBRH ABDBE ABFSG ACSTC ADHKG ADKFA AEZWR AFDZB AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION ABRTQ |
| ID | FETCH-LOGICAL-c319t-2f5a7981beeb91afdcb360b78b5b71cde06991136365ff1a7bc736f8303c0c8b3 |
| IEDL.DBID | U2A |
| ISSN | 1433-7541 |
| IngestDate | Fri Jul 25 03:47:48 EDT 2025 Tue Jul 01 01:15:18 EDT 2025 Thu Apr 24 23:04:18 EDT 2025 Fri Feb 21 02:42:52 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | Temporal action segmentation Refinement network Over-segmentation Video semantic understanding Self-attention |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c319t-2f5a7981beeb91afdcb360b78b5b71cde06991136365ff1a7bc736f8303c0c8b3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| PQID | 2840787218 |
| PQPubID | 2043691 |
| PageCount | 19 |
| ParticipantIDs | proquest_journals_2840787218 crossref_citationtrail_10_1007_s10044_023_01166_8 crossref_primary_10_1007_s10044_023_01166_8 springer_journals_10_1007_s10044_023_01166_8 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2023-08-01 |
| PublicationDateYYYYMMDD | 2023-08-01 |
| PublicationDate_xml | – month: 08 year: 2023 text: 2023-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London – name: Heidelberg |
| PublicationTitle | Pattern analysis and applications : PAA |
| PublicationTitleAbbrev | Pattern Anal Applic |
| PublicationYear | 2023 |
| Publisher | Springer London Springer Nature B.V |
| Publisher_xml | – name: Springer London – name: Springer Nature B.V |
| References | Li, Abufarha, Liu, Cheng, Gall (CR14) 2020 Levenshtein (CR41) 1966; 10 CR38 CR37 CR36 CR35 CR31 CR30 Li, Sun, Zhang (CR52) 2021; 44 CR4 Pan, Liu, Sangaiah, Muhammad (CR2) 2018; 120 CR6 Cheng, Qiu, Jiang, Zhu (CR28) 2021; 24 CR5 CR8 CR7 CR9 CR49 CR48 CR47 CR46 Febin, Jayasree, Joy (CR1) 2020; 23 CR45 CR44 CR43 CR42 CR40 Stenum, Rossi, Roemmich (CR3) 2021; 17 He, Zhang, Ren, Sun (CR39) 2015; 37 CR19 CR18 CR17 CR16 CR15 CR13 CR12 CR11 CR10 CR53 CR51 CR50 Wang, Yuan, Wang (CR23) 2020; 407 Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (CR32) 2017; 30 He, Wen, Wang, Li (CR33) 2021; 51 CR29 CR27 CR26 CR25 CR24 Wang, Xiong, Wang, Nian (CR34) 2020; 50 CR22 CR21 CR20 1166_CR51 1166_CR50 1166_CR12 1166_CR11 1166_CR10 1166_CR53 1166_CR16 1166_CR15 1166_CR13 1166_CR19 1166_CR18 1166_CR17 Z Pan (1166_CR2) 2018; 120 Z Li (1166_CR52) 2021; 44 SJ Li (1166_CR14) 2020 1166_CR22 1166_CR21 L He (1166_CR33) 2021; 51 1166_CR20 1166_CR27 1166_CR26 1166_CR5 1166_CR25 1166_CR4 1166_CR24 1166_CR29 1166_CR7 1166_CR6 1166_CR9 1166_CR8 1166_CR30 VI Levenshtein (1166_CR41) 1966; 10 1166_CR31 1166_CR38 IP Febin (1166_CR1) 2020; 23 1166_CR37 1166_CR36 1166_CR35 1166_CR40 1166_CR45 A Vaswani (1166_CR32) 2017; 30 1166_CR44 1166_CR43 K He (1166_CR39) 2015; 37 1166_CR42 1166_CR49 1166_CR48 1166_CR47 1166_CR46 J Stenum (1166_CR3) 2021; 17 X Cheng (1166_CR28) 2021; 24 J Wang (1166_CR34) 2020; 50 D Wang (1166_CR23) 2020; 407 |
| References_xml | – ident: CR45 – ident: CR22 – volume: 51 start-page: 2128 issue: 4 year: 2021 end-page: 2143 ident: CR33 article-title: Vehicle theft recognition from surveillance video based on spatiotemporal attention publication-title: Appl Intell doi: 10.1007/s10489-020-01933-8 – ident: CR49 – volume: 37 start-page: 1904 issue: 9 year: 2015 end-page: 1916 ident: CR39 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2015.2389824 – ident: CR4 – ident: CR16 – ident: CR51 – ident: CR12 – ident: CR35 – ident: CR29 – ident: CR8 – ident: CR25 – ident: CR42 – ident: CR21 – ident: CR46 – ident: CR19 – volume: 407 start-page: 63 year: 2020 end-page: 71 ident: CR23 article-title: Gated forward refinement network for action segmentation publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.03.066 – ident: CR15 – ident: CR50 – ident: CR11 – ident: CR9 – volume: 44 start-page: 9904 issue: 12 year: 2021 end-page: 9917 ident: CR52 article-title: CTNet: context-based tandem network for semantic segmentation publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2021.3132068 – year: 2020 ident: CR14 article-title: Ms-tcn++: Multi-stage temporal convolutional network for action segmentation publication-title: IEEE Trans Pattern Anal doi: 10.1109/TPAMI.2020.3021756 – ident: CR36 – ident: CR5 – ident: CR26 – volume: 24 start-page: 1347 issue: 3 year: 2021 end-page: 1355 ident: CR28 article-title: An improved small object detection method based on Yolo V3 publication-title: Pattern Anal Appl doi: 10.1007/s10044-021-00989-7 – volume: 50 start-page: 1045 issue: 4 year: 2020 end-page: 1056 ident: CR34 article-title: ADSCNet: asymmetric depthwise separable convolution for semantic segmentation in real-time publication-title: Appl Intell doi: 10.1007/s10489-019-01587-1 – ident: CR18 – ident: CR43 – volume: 120 start-page: 182 year: 2018 end-page: 194 ident: CR2 article-title: Visual attention feature (VAF): a novel strategy for visual tracking based on cloud platform in intelligent surveillance systems publication-title: J Parallel Distr Com doi: 10.1016/j.jpdc.2018.06.012 – ident: CR47 – volume: 10 start-page: 707 issue: 8 year: 1966 end-page: 710 ident: CR41 article-title: Binary codes capable of correcting deletions, insertions, and reversals publication-title: Soviet physics doklady – ident: CR37 – ident: CR53 – ident: CR30 – volume: 17 issue: 4 year: 2021 ident: CR3 article-title: Two-dimensional video-based analysis of human gait using pose estimation publication-title: Plos Comput Biol doi: 10.1371/journal.pcbi.1008935 – ident: CR10 – ident: CR6 – ident: CR40 – ident: CR27 – ident: CR44 – ident: CR48 – ident: CR38 – ident: CR17 – ident: CR31 – ident: CR13 – volume: 23 start-page: 611 issue: 2 year: 2020 end-page: 623 ident: CR1 article-title: Violence detection in videos for an intelligent surveillance system using MoBSIFT and movement filtering algorithm publication-title: Pattern Anal Appl doi: 10.1007/s10044-019-00821-3 – ident: CR7 – volume: 30 start-page: 5998 year: 2017 end-page: 6008 ident: CR32 article-title: Attention is all you need publication-title: Adv Neural Inf Process Syst – ident: CR24 – ident: CR20 – ident: 1166_CR27 doi: 10.18653/v1/P19-1340 – volume: 120 start-page: 182 year: 2018 ident: 1166_CR2 publication-title: J Parallel Distr Com doi: 10.1016/j.jpdc.2018.06.012 – ident: 1166_CR11 doi: 10.1109/CVPR.2019.00369 – ident: 1166_CR26 doi: 10.1109/CVPR46437.2021.01653 – volume: 44 start-page: 9904 issue: 12 year: 2021 ident: 1166_CR52 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2021.3132068 – ident: 1166_CR9 doi: 10.1109/CVPR.2016.216 – volume: 10 start-page: 707 issue: 8 year: 1966 ident: 1166_CR41 publication-title: Soviet physics doklady – volume: 30 start-page: 5998 year: 2017 ident: 1166_CR32 publication-title: Adv Neural Inf Process Syst – ident: 1166_CR49 – ident: 1166_CR25 doi: 10.1109/WACV45572.2020.9093535 – ident: 1166_CR21 doi: 10.1109/CVPR.2018.00705 – ident: 1166_CR30 doi: 10.1109/ICCV48922.2021.00676 – ident: 1166_CR44 doi: 10.1109/CVPR.2015.7298935 – ident: 1166_CR38 doi: 10.1109/ICCV.2017.324 – ident: 1166_CR53 doi: 10.1109/ICCVW.2017.95 – ident: 1166_CR12 doi: 10.1007/978-3-030-58595-2_3 – ident: 1166_CR42 doi: 10.1109/CVPR.2017.502 – year: 2020 ident: 1166_CR14 publication-title: IEEE Trans Pattern Anal doi: 10.1109/TPAMI.2020.3021756 – volume: 50 start-page: 1045 issue: 4 year: 2020 ident: 1166_CR34 publication-title: Appl Intell doi: 10.1007/s10489-019-01587-1 – ident: 1166_CR7 – ident: 1166_CR19 doi: 10.1109/CVPR.2014.105 – volume: 24 start-page: 1347 issue: 3 year: 2021 ident: 1166_CR28 publication-title: Pattern Anal Appl doi: 10.1007/s10044-021-00989-7 – volume: 23 start-page: 611 issue: 2 year: 2020 ident: 1166_CR1 publication-title: Pattern Anal Appl doi: 10.1007/s10044-019-00821-3 – ident: 1166_CR22 doi: 10.1109/CVPR.2019.01228 – ident: 1166_CR15 doi: 10.1109/CVPR42600.2020.00947 – ident: 1166_CR43 doi: 10.1109/CVPR.2015.7298878 – ident: 1166_CR18 doi: 10.1109/CVPR.2011.5995444 – ident: 1166_CR40 doi: 10.1109/CVPR.2012.6247808 – ident: 1166_CR31 doi: 10.1109/CVPR46437.2021.00681 – ident: 1166_CR51 doi: 10.1109/CVPR.2017.140 – ident: 1166_CR8 doi: 10.1109/ICCV.2015.510 – ident: 1166_CR24 doi: 10.1109/CVPR42600.2020.01404 – ident: 1166_CR35 doi: 10.1109/CVPR.2018.00745 – ident: 1166_CR20 – ident: 1166_CR29 doi: 10.1109/WACV.2016.7477701 – volume: 51 start-page: 2128 issue: 4 year: 2021 ident: 1166_CR33 publication-title: Appl Intell doi: 10.1007/s10489-020-01933-8 – ident: 1166_CR10 doi: 10.1109/CVPR.2017.113 – ident: 1166_CR6 doi: 10.1109/ICCV.2019.00718 – volume: 37 start-page: 1904 issue: 9 year: 2015 ident: 1166_CR39 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2015.2389824 – ident: 1166_CR47 doi: 10.1109/CVPR.2014.286 – volume: 17 issue: 4 year: 2021 ident: 1166_CR3 publication-title: Plos Comput Biol doi: 10.1371/journal.pcbi.1008935 – ident: 1166_CR13 doi: 10.1109/WACV48630.2021.00237 – ident: 1166_CR4 doi: 10.1109/CVPR.2017.787 – ident: 1166_CR5 – ident: 1166_CR36 doi: 10.1007/978-3-030-01234-2_1 – ident: 1166_CR46 doi: 10.1109/CVPR.2012.6247801 – ident: 1166_CR16 doi: 10.1609/aaai.v35i4.16377 – ident: 1166_CR48 doi: 10.1007/978-3-319-46487-9_3 – ident: 1166_CR17 doi: 10.1145/2493432.2493482 – ident: 1166_CR45 doi: 10.1007/978-3-642-40760-4_43 – volume: 407 start-page: 63 year: 2020 ident: 1166_CR23 publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.03.066 – ident: 1166_CR37 doi: 10.1109/CVPR.2017.106 – ident: 1166_CR50 doi: 10.1109/ICCV.2019.00638 |
| SSID | ssj0033328 |
| Score | 2.3805392 |
| Snippet | In high-level video semantic understanding, continuous action segmentation is a challenging task aimed at segmenting an untrimmed video and labeling each... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1375 |
| SubjectTerms | Computer Science Labels Pattern Recognition Segmentation Segments Semantics Theoretical Advances |
| Title | TSRN: two-stage refinement network for temporal action segmentation |
| URI | https://link.springer.com/article/10.1007/s10044-023-01166-8 https://www.proquest.com/docview/2840787218 |
| Volume | 26 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4ULl58G1EkPXjTJnS7bXe9EQISjRwUEjxtaLflgouRNf59p0sratTEa5_J9DFfO_PNIHTOeaKmxlBiDTUkzjknKnd_8DbSgOVYLqwjON8NxWAc30z4xJPClsHbPZgkq5v6E9mtHccEdAxxxgNBkk1U5_B2d45c46gT7l_GWJVRFYAAI5LH1FNlfh7jqzpaY8xvZtFK2_R30baHibizWtc9tGGKfbTjISP2B3IJRSErQyg7QN3Rw_3wCpdvCwLIb2YwTApQ0v0C4mLl9I0BqWIflGqOV9QGvDSzJ09EKg7RuN8bdQfEp0ogGs5QSSLLpzIFCGqMSunU5lox0VYyUVxJqnPTFgAEKRNMcGvpVCotmbAJKDDd1oliR6hWLApzjGDSREYKcJ6lOpbSsTyMUFKlxuY2jWQD0SCxTPs44i6dxTxbR0B2Us5Aylkl5SxpoIuPPs-rKBp_tm6Ghcj8iVpmoEYBzcB7Faovw-Ksq38f7eR_zU_RVlTtD-fj10S18uXVnAHuKFUL1TvXj7e9VrXd3gGLZ87z |
| linkProvider | Springer Nature |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LTwMhEJ5UPejFt_EtBz0pSVkW2Jp4MGpTH-1B26S3tbDgRVdja4z_xx_qsGWtGjXx4BVY2AzDzAfzAtgWItE9axl1llkaZ0JQnfk3eBcZxHI8k84HODdbstGJz7qiW4HXMham8HYvTZKFpP4Q7FaNY4o6hnrjgaRJcKU8ty_PeFHrH5we467uRFH9pH3UoKGWADXIZAMaOdFTNcRo1uoa67nMaC6rWiVaaMVMZqsSkRLjkkvhHOspbRSXLkEJb6om0RznHYMJBB-JPzud6LCU95zzooIrAg9OlYhZCM35_p8_q78Rpv1ihi20W30WpgMsJYdDPpqDis3nYSZAVBIEQB-byioQZdsCHLWvLlv7ZPB8TxFp3liCiyJ09a-OJB86mRNExiQkwbolw1AK0rc3dyHwKV-Ezr-QcwnG8_vcLgMumqhII650zMRK-agSK7XSNesyV4vUCrCSYqkJect9-YzbdJRx2VM5RSqnBZXTZAV23795GGbt-HX0erkRaTjB_RTVNqInvB9j9165OaPun2db_dvwLZhstJsX6cVp63wNpqKCV7x_4TqMDx6f7AZinoHeLFiOwPV_8_gbWkoK-w |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Pb9MwFH7aioR22fgxRFnZfIATs1bHsZ1M4lCtVCuDCsEq7RZqx96lpNUSVPFf8SfuOXHoQGzSDrvajh09P_t9tt_3HsAbIRI9s5ZRZ5mlcS4E1bm_g3eRQSzHc-k8wfnzRJ5O448X4mIDfrdcmNrbvX2SbDgNPkpTUR0tc3d0g_jWj2OK9ob6hwRJk-BWeWZ_rfDQVr4fD3GG30bR6MP5ySkNeQWoQYWraOTETKWI16zVKZu53Ggu-1olWmjFTG77ElET45JL4RybKW0Uly7B3d70TaI59rsJj2LPPsYVNI0G7d7POa-zuSII4VSJmAWazv__-W9TuMa3_zzJ1pZu9AS2A0Qlg0annsKGLZ7BToCrJGwGJRa1GSHasudwcv7t6-SYVKsFRdR5aQkOijDW30CSonE4J4iSSQiINScNrYKU9vJHIEEVuzB9EHG-gE6xKOxLwEETFWnEmI6ZWCnPMLFSK51al7s0Ul1grcQyE2KY-1Qa82wdfdlLOUMpZ7WUs6QL7_58s2wieNzZutdORBZWc5mhCUckhWdlrD5sJ2ddfXtvr-7X_AAefxmOsk_jydkebEW1qnhXwx50qquf9jXCn0rv1xpH4PtDq_g1IhYPLg |
| 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=TSRN%3A+two-stage+refinement+network+for+temporal+action+segmentation&rft.jtitle=Pattern+analysis+and+applications+%3A+PAA&rft.au=Tian%2C+Xiaoyan&rft.au=Jin%2C+Ye&rft.au=Tang%2C+Xianglong&rft.date=2023-08-01&rft.issn=1433-7541&rft.eissn=1433-755X&rft.volume=26&rft.issue=3&rft.spage=1375&rft.epage=1393&rft_id=info:doi/10.1007%2Fs10044-023-01166-8&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s10044_023_01166_8 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1433-7541&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1433-7541&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1433-7541&client=summon |