The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Understanding Low- and High-Level Contributions to Fixation Prediction
Abstract
Understanding where people look in images is an important problem in computer vision. Despite significant research, it remains unclear to what extent human fixations can be predicted by low-level (contrast) compared to highlevel (presence of objects) image features. Here we address this problem by introducing two novel models that use different feature spaces but the same readout architecture. The first model predicts human fixations based on deep neural network features trained on object recognition. This model sets a new state-of-the art in fixation prediction by achieving top performance in area under the curve metrics on the MIT300 hold-out benchmark (AUC = 88%, sAUC = 77%, NSS = 2.34). The second model uses purely low-level (isotropic contrast) features. This model achieves better performance than all models not using features pretrained on object recognition, making it a strong baseline to assess the utility of high-level features. We then evaluate and visualize which fixations are better explained by lowlevel compared to high-level image features. Surprisingly we find that a substantial proportion of fixations are better explained by the simple low-level model than the stateof- the-art model. Comparing different features within the same powerful readout architecture allows us to better understand the relevance of low- versus high-level features in predicting fixation locations, while simultaneously achieving state-of-the-art saliency prediction.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
A model of saliency-based visual attention for rapid scene analysis
Itti, L., Koch, C., & Niebur, E. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.730558 · Cited by 11,271
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Image Style Transfer Using Convolutional Neural Networks
Gatys, L. A., Ecker, A. S., & Bethge, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.265 · Cited by 6,025
Self-citationCaffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.5093 · Cited by 3,752
Harel, J., Koch, C., & Perona, P. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0073 · Cited by 3,439
Saliency Detection: A Spectral Residual Approach
Hou, X., & Zhang, L. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383267 · Cited by 3,422
Learning to predict where humans look
Judd, T., Ehinger, K., Durand, F., & Torralba, A. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459462 · Cited by 2,016
State-of-the-Art in Visual Attention Modeling
Borji, A., & Itti, L. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.89 · Cited by 1,817
Torralba, A., Oliva, A., Castelhano, M. S., & Henderson, J. M. (2006) · Psychological Review · doi:10.1037/0033-295x.113.4.766 · Cited by 1,639
Static Analysis of Shape in TensorFlow Programs
The Theano Development Team, Al‐Rfou, R., Alain, G., Almahairi, A., Angermueller, C., Bahdanau, D., Ballas, N., Bastien, F., Bayer, J., Belikov, A., et al. (2016) · arXiv (Cornell University) · doi:10.4230/lipics.ecoop.2020.15 · Cited by 1,589
Context-Aware Saliency Detection
Goferman, S., Zelnik-Manor, L., & Tal, A. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.272 · Cited by 1,567
SUN: A Bayesian framework for saliency using natural statistics
Zhang, L., Tong, M. H., Marks, T. K., Shan, H., & Cottrell, G. W. (2008) · Journal of Vision · doi:10.1167/8.7.32 · Cited by 1,227
Tatler, B. W. (2007) · Journal of Vision · doi:10.1167/7.14.4 · Cited by 1,028
Saliency, attention, and visual search: An information theoretic approach
Bruce, N. D. B., & Tsotsos, J. K. (2009) · Journal of Vision · doi:10.1167/9.3.5 · Cited by 855
Eye guidance in natural vision: reinterpreting salience
Tatler, B. W., Hayhoe, M. M., Land, M. F., & Ballard, D. H. (2011) · Journal of Vision · doi:10.1167/11.5.5 · Cited by 775
Components of bottom-up gaze allocation in natural images
Peters, R. J., Iyer, A., Itti, L., & Koch, C. (2005) · Vision Research · doi:10.1016/j.visres.2005.03.019 · Cited by 739
Jiang, M., Huang, S., Duan, J., & Zhao, Q. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298710 · Cited by 729
Visual correlates of fixation selection: effects of scale and time
Tatler, B. W., Baddeley, R. J., & Gilchrist, I. D. (2005) · Vision Research · doi:10.1016/j.visres.2004.09.017 · Cited by 700
SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
Huang, X., Shen, C., Boix, X., & Zhao, Q. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.38 · Cited by 597
Saliency Detection: A Boolean Map Approach
Zhang, J., & Sclaroff, S. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.26 · Cited by 495
DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations
Kruthiventi, S. S. S., Ayush, K., & Babu, R. V. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2710620 · Cited by 478
Predicting human gaze using low-level saliency combined with face detection
Cerf, M., Harel, J., Einhäuser, W., & Koch, C. (2008) · CaltechAUTHORS (California Institute of Technology) · Cited by 465
Objects predict fixations better than early saliency
Einhauser, W., Spain, M., & Perona, P. (2008) · Journal of Vision · doi:10.1167/8.14.18 · Cited by 451
Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images
Vig, E., Dorr, M., & Cox, D. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.358 · Cited by 428
Visual saliency estimation by nonlinearly integrating features using region covariances
Erdem, E., & Erdem, A. (2013) · Journal of Vision · doi:10.1167/13.4.11 · Cited by 396
Task and context determine where you look
Rothkopf, C. A., Ballard, D. H., & Hayhoe, M. M. (2016) · Journal of Vision · doi:10.1167/7.14.16 · Cited by 366
Predicting human gaze beyond pixels
Xu, J., Jiang, M., Wang, S., Kankanhalli, M. S., & Zhao, Q. (2014) · Journal of Vision · doi:10.1167/14.1.28 · Cited by 353
Explicit information for category-orthogonal object properties increases along the ventral stream
Hong, H., Yamins, D. L. K., Majaj, N. J., & DiCarlo, J. J. (2016) · Nature Neuroscience · doi:10.1038/nn.4247 · Cited by 337
Quantifying the contribution of low-level saliency to human eye movements in dynamic scenes
Itti, L. (2005) · Visual Cognition · doi:10.1080/13506280444000661 · Cited by 331
Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
Kümmerer, M., Theis, L., & Bethge, M. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.1045 · Cited by 231
Self-citationSystematic tendencies in scene viewing
Tatler, B. W., & Vincent, B. T. (2008) · Journal of Eye Movement Research · doi:10.16910/jemr.2.2.5 · Cited by 218
A Deep Spatial Contextual Long-Term Recurrent Convolutional Network for Saliency Detection
Liu, N., & Han, J. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2817047 · Cited by 207
Center-surround patterns emerge as optimal predictors for human saccade targets
Kienzle, W., Franz, M. O., Scholkopf, B., & Wichmann, F. A. (2009) · Journal of Vision · doi:10.1167/9.5.7 · Cited by 194
RARE2012: A multi-scale rarity-based saliency detection with its comparative statistical analysis
Riche, N., Mancas, M., Duvinage, M., Mibulumukini, M., Gosselin, B., & Dutoit, T. (2013) · Signal Processing: Image Communication · doi:10.1016/j.image.2013.03.009 · Cited by 189
Information-theoretic model comparison unifies saliency metrics
Kümmerer, M., Wallis, T. S. A., & Bethge, M. (2015) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1510393112 · Cited by 158
Self-citationWhat do saliency models predict?
Koehler, K., Guo, F., Zhang, S., & Eckstein, M. P. (2014) · Journal of Vision · doi:10.1167/14.3.14 · Cited by 156
End-to-End Saliency Mapping via Probability Distribution Prediction
Jetley, S., Murray, N., & Vig, E. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.620 · Cited by 140
On computational modeling of visual saliency: Examining what’s right, and what’s left
Bruce, N. D. B., Wloka, C., Frosst, N., Rahman, S., & Tsotsos, J. K. (2015) · Vision Research · doi:10.1016/j.visres.2015.01.010 · Cited by 96
Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methodsPreprint
Sohl‐Dickstein, J., Poole, B., & Ganguli, S. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1311.2115 · Cited by 89
Vincent, B. T., Baddeley, R., Correani, A., Trościanko, T., & Leonards, U. (2009) · Visual Cognition · doi:10.1080/13506280902916691 · Cited by 72
Modeling fixation locations using spatial point processes
Barthelmé, S., Trukenbrod, H. A., Engbert, R., & Wichmann, F. A. (2013) · Journal of Vision · doi:10.1167/13.12.1 · Cited by 70
A Deeper Look at Saliency: Feature Contrast, Semantics, and Beyond
Bruce, N. D. B., Catton, C., & Janjić, S. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.62 · Cited by 58
OpenSalicon: An Open Source Implementation of the Salicon Saliency ModelPreprint
Thomas, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.00110 · Cited by 28
Saliency, scale and information: towards a unifying theory
Rahman, S., & Bruce, N. D. B. (2015) · neural information processing systems · Cited by 7
Cited by
Using DeepLabCut for 3D markerless pose estimation across species and behaviors
Nath, T., Mathis, A., Chen, A. C., Patel, A., Bethge, M., & Mathis, M. W. (2019) · Nature Protocols · doi:10.1038/s41596-019-0176-0 · Cited by 1,505
Self-citationPredicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model
Cornia, M., Baraldi, L., Serra, G., & Cucchiara, R. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2851672 · Cited by 474
A Multimodal Saliency Model for Videos With High Audio-Visual Correspondence
Min, X., Zhai, G., Zhou, J., Zhang, X.-P., Yang, X., & Guan, X. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2966082 · Cited by 295
Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach
Xu, M., Song, Y., Wang, J., Qiao, M., Huo, L., & Wang, Z. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858783 · Cited by 259
Human Hands as Probes for Interactive Object Understanding
Goyal, M., Modi, S., Goyal, R., & Gupta, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00329 · Cited by 31
Metadata
- Authors
- Kummerer, M., Wallis, T. S. A., Gatys, L. A., & Bethge, M.
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 4799-4808
- OpenAlex
- W2738450183
- Cited by
- 282
- References
- 48
- FWCI
- 9.38
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.