TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction
This work addresses a gap in saliency prediction for computer vision applications, but it is incremental as it builds on existing models by adding temporal features.
The paper tackles the problem of deep saliency prediction by incorporating temporal gaze shift information, which previous models ignored, and shows that their method outperforms state-of-the-art models on the SALICON benchmark.
Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information, such as scene context, semantic relationships, gaze direction, and object dissimilarity. However, none of these models consider the temporal nature of gaze shifts during image observation. We introduce a novel saliency prediction model that learns to output saliency maps in sequential time intervals by exploiting human temporal attention patterns. Our approach locally modulates the saliency predictions by combining the learned temporal maps. Our experiments show that our method outperforms the state-of-the-art models, including a multi-duration saliency model, on the SALICON benchmark. Our code will be publicly available on GitHub.