Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2022

Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection

Résumé

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.
Fichier principal
Vignette du fichier
TSU_FINAL.pdf (10.64 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03698616 , version 1 (18-06-2022)

Identifiants

Citer

Rui Dai, Srijan Das, Saurav Sharma, Luca Minciullo, Lorenzo Garattoni, et al.. Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, In press, ⟨10.1109/tpami.2022.3169976⟩. ⟨hal-03698616⟩
23 Consultations
33 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More