|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM342304801 |
| 003 |
DE-627 |
| 005 |
20231226013808.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3183586
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1140.xml
|
| 035 |
|
|
|a (DE-627)NLM342304801
|
| 035 |
|
|
|a (NLM)35709117
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhang, Lingling
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a TN-ZSTAD
|b Transferable Network for Zero-Shot Temporal Activity Detection
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 07.04.2023
|
| 500 |
|
|
|a Date Revised 07.04.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training still need to be detected. We design an end-to-end deep transferable network TN-ZSTAD as the architecture for this solution. On the one hand, this network utilizes an activity graph transformer to predict a set of activity instances that appear in the video, rather than produces many activity proposals in advance. On the other hand, this network captures the common semantics of seen and unseen activities from their corresponding label embeddings, and it is optimized with an innovative loss function that considers the classification property on seen activities and the transfer property on unseen activities together. Experiments on the THUMOS'14, Charades, and ActivityNet datasets show promising performance in terms of detecting unseen activities
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Chang, Xiaojun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Jun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Luo, Minnan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Zhihui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yao, Lina
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hauptmann, Alex
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 3 vom: 16. März, Seite 3848-3861
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:3
|g day:16
|g month:03
|g pages:3848-3861
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3183586
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 3
|b 16
|c 03
|h 3848-3861
|