|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM339971339 |
| 003 |
DE-627 |
| 005 |
20231226004106.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3169976
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1133.xml
|
| 035 |
|
|
|a (DE-627)NLM339971339
|
| 035 |
|
|
|a (NLM)35468059
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Dai, Rui
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Toyota Smarthome Untrimmed
|b Real-World Untrimmed Videos for 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 06.04.2023
|
| 500 |
|
|
|a Date Revised 06.04.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Designing activity detection systems that can be successfully deployed in daily-living environments requires datasets that pose the challenges typical of real-world scenarios. In this paper, we introduce a new untrimmed daily-living dataset that features several real-world challenges: Toyota Smarthome Untrimmed (TSU). TSU contains a wide variety of activities performed in a spontaneous manner. The dataset contains dense annotations including elementary, composite activities and activities involving interactions with objects. We provide an analysis of the real-world challenges featured by our dataset, highlighting the open issues for detection algorithms. We show that current state-of-the-art methods fail to achieve satisfactory performance on the TSU dataset. Therefore, we propose a new baseline method for activity detection to tackle the novel challenges provided by our dataset. This method leverages one modality (i.e. optic flow) to generate the attention weights to guide another modality (i.e RGB) to better detect the activity boundaries. This is particularly beneficial to detect activities characterized by high temporal variance. We show that the method we propose outperforms state-of-the-art methods on TSU and on another popular challenging dataset, Charades
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Das, Srijan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Sharma, Saurav
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Minciullo, Luca
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Garattoni, Lorenzo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Bremond, Francois
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Francesca, Gianpiero
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 2 vom: 30. Feb., Seite 2533-2550
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:2
|g day:30
|g month:02
|g pages:2533-2550
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3169976
|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 2
|b 30
|c 02
|h 2533-2550
|