Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset
Published in arXiv preprint arXiv:1809.00241, 2018
We present a large-scale study on activity recognition using the Moments in Time dataset, which contains over one million short video clips spanning a diverse set of human activities. Our approach combines visual and temporal features to classify activities in 3-second video clips. We analyze the challenges of recognizing fine-grained activities at scale and propose methods for handling the inherent class imbalance and visual complexity present in real-world video data.
Recommended citation: @article{shah2018activity, title={Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset}, author={Shah, Ankit and Kesavamoorthy, Harini and Rane, Poorva and Kalwad, Pramati and Hauptmann, Alexander and Metze, Florian}, journal={arXiv preprint arXiv:1809.00241}, year={2018} }
Download Paper