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

10/28/2020
by   Rui Dai, et al.
14

This work aims at building a large scale dataset with daily-living activities performed in a natural manner. Activities performed in a spontaneous manner lead to many real-world challenges that are often ignored by the vision community. This includes low inter-class due to the presence of similar activities and high intra-class variance, low camera framing, low resolution, long-tail distribution of activities, and occlusions. To this end, we propose the Toyota Smarthome Untrimmed (TSU) dataset, which provides spontaneous activities with rich and dense annotations to address the detection of complex activities in real-world scenarios.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset