DeepVS: A Deep Learning Based Video Saliency Prediction Approach

@inproceedings{Jiang2018DeepVSAD,
  title={DeepVS: A Deep Learning Based Video Saliency Prediction Approach},
  author={Lai Jiang and Mai Xu and Tie Liu and Minglang Qiao and Zulin Wang},
  booktitle={ECCV},
  year={2018}
}
In this paper, we propose a novel deep learning based video sa li ncy prediction method, named DeepVS. Specifically, we establ i h a large-scale eye-tracking database of videos (LEDOV), which includes 32 ubjects’ fixations on 538 videos. We find from LEDOV that human attention is more likely to be attracted by objects, particularly the moving objects or the moving parts of objects. Hence, an object-to-motion convolutional neural network (OM-CNN) is developed to predict the intra-frame saliency… CONTINUE READING
Tweets
This paper has been referenced on Twitter 16 times. VIEW TWEETS

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Similar Papers

Loading similar papers…