Projekteja vuodessa
Abstrakti
In this work, we investigate activity recognition using multimodal inputs from heterogeneous sensors. Activity recognition is commonly tackled from a single-modal perspective using videos. In case multiple signals are used, they come from the same homogeneous modality, e.g. in the case of color and optical flow. Here, we propose an activity network that fuses multimodal inputs coming from completely different and heterogeneous sensors. We frame such a heterogeneous fusion as a non-local operation. The observation is that in a non-local operation, only the channel dimensions need to match. In the network, heterogeneous inputs are fused, while maintaining the shapes and dimensionalities that fit each input. We outline both asymmetric fusion, where one modality serves to enforce the other, and symmetric fusion variants. To further promote research into multimodal activity recognition, we introduce GloVid, a first-person activity dataset captured with video recordings and smart glove sensor readings. Experiments on GloVid show the potential of heterogeneous non-local fusion for activity recognition, outperforming individual modalities and standard fusion techniques.
Alkuperäiskieli | Englanti |
---|---|
Otsikko | ICMR 2020 - Proceedings of the 2020 International Conference on Multimedia Retrieval |
Kustantaja | ACM |
Sivut | 63-72 |
Sivumäärä | 10 |
ISBN (elektroninen) | 9781450370875 |
DOI - pysyväislinkit | |
Tila | Julkaistu - 8 kesäk. 2020 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisuussa |
Tapahtuma | ACM International Conference on Multimedia Retrieval - Dublin, Irlanti Kesto: 8 kesäk. 2020 → 11 kesäk. 2020 Konferenssinumero: 10 |
Conference
Conference | ACM International Conference on Multimedia Retrieval |
---|---|
Lyhennettä | ICMR |
Maa/Alue | Irlanti |
Kaupunki | Dublin |
Ajanjakso | 08/06/2020 → 11/06/2020 |
Sormenjälki
Sukella tutkimusaiheisiin 'Heterogeneous non-local fusion for multimodal activity recognition'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.Projektit
- 2 Päättynyt
-
CEAMA: CEAMA Cognitive Engine for Assembly and Maintenance Automation
Xiao, Y., Byvshev, P., Pouta, E., Hirvonen, V., Lee, J., Souza Leite, C., Wirtanen, S., Nyman, P. & Pham, T.
01/08/2018 → 31/01/2020
Projekti: Business Finland: New business from research ideas (TUTLI)
-
ATTRACT: breAkThrough innovaTion pRogrAmme for a pan-European Detection and Imaging eCosysTem
01/08/2018 → 30/11/2020
Projekti: EU: Framework programmes funding