@article{Fu_Shi_Song_Ge_Lu_Li_2020, title={Ultrafast Video Attention Prediction with Coupled Knowledge Distillation}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/6710}, DOI={10.1609/aaai.v34i07.6710}, abstractNote={<p>Large convolutional neural network models have recently demonstrated impressive performance on video attention prediction. Conventionally, these models are with intensive computation and large memory. To address these issues, we design an extremely light-weight network with ultrafast speed, named UVA-Net. The network is constructed based on depth-wise convolutions and takes low-resolution images as input. However, this straight-forward acceleration method will decrease performance dramatically. To this end, we propose a coupled knowledge distillation strategy to augment and train the network effectively. With this strategy, the model can further automatically discover and emphasize implicit useful cues contained in the data. Both spatial and temporal knowledge learned by the high-resolution complex teacher networks also can be distilled and transferred into the proposed low-resolution light-weight spatiotemporal network. Experimental results show that the performance of our model is comparable to 11 state-of-the-art models in video attention prediction, while it costs only 0.68 MB memory footprint, runs about 10,106 FPS on GPU and 404 FPS on CPU, which is 206 times faster than previous models.</p>}, number={07}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Fu, Kui and Shi, Peipei and Song, Yafei and Ge, Shiming and Lu, Xiangju and Li, Jia}, year={2020}, month={Apr.}, pages={10802-10809} }