MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding

• Published in: Proceedings / IEEE International Conference on Computer Vision pp. 8657 - 8666
• Main Authors: Kong, Quan, Wu, Ziming, Deng, Ziwei, Klinkigt, Martin, Tong, Bin, Murakami, Tomokazu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2019
• Subjects: Adaptation models; Cameras; Gyroscopes; Sensors; Task analysis; Three-dimensional displays; Videos
• DOI: 10.1109/ICCV.2019.00875

Unlike vision modalities, body-worn sensors or passive sensing can avoid the failure of action understanding in vision related challenges, e.g. occlusion and appearance variation. However, a standard large-scale dataset does not exist, in which different types of modalities across vision and sensors are integrated. To address the disadvantage of vision-based modalities and push towards multi/cross modal action understanding, this paper introduces a new large-scale dataset recorded from 20 distinct subjects with seven different types of modalities: RGB videos, keypoints, acceleration, gyroscope, orientation, Wi-Fi and pressure signal. The dataset consists of more than 36k video clips for 37 action classes covering a wide range of daily life activities such as desktop-related and check-in-based ones in four different distinct scenarios. On the basis of our dataset, we propose a novel multi modality distillation model with attention mechanism to realize an adaptive knowledge transfer from sensor-based modalities to vision-based modalities. The proposed model significantly improves performance of action recognition compared to models trained with only RGB information. The experimental results confirm the effectiveness of our model on cross-subject, -view, -scene and -session evaluation criteria. We believe that this new large-scale multimodal dataset will contribute the community of multimodal based action understanding.