mlsanityData to 14 Oct 2026

ViASNet: A Video Ad Saliency Network for Predicting Dynamic Saliency and Viewer Engagement

arXiv 2605.29302 ↗First posted 28 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The digital media landscape has seen a pervasive shift toward short-form video advertising on TV, social media and e-commerce platforms. The present study focuses on deep saliency prediction for short-form video advertising. Deep saliency models have been used to generate predictions of human eye fixation patterns with the purpose of enhancing user interaction with digital technology and optimizing its design. For video ads, dynamic saliency maps capture where and when viewers are looking, revealing why video ads are effective, and how their content should be optimized. We develop and test a new deep dynamic saliency prediction model called ViASNet (Video Ad Saliency Network), which has an architecture founded on the 3D U-Net, and accommodates the influence of audio and the semantic meaning of scenes. We assess the model's performance on 151 video ads, each seen by about 20 viewers wile their eye movements were tracked, and explore the critical factors influencing model performance through ablation experiments. We calculate the entropy of the predicted saliency maps frame-by-frame as a diagnostic tool to identify ads and scenes that fail to engage viewers, and illustrate its use on test data of 15 unseen ads. Our study reveals that ad design and testing can be sped up considerably through automated systems built on deep saliency models such as ViASNet.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 165 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

40 of 165 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  7. 2025Qwen3-VL Technical Reportcited by 2,793
  8. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  9. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  10. 2016What do different evaluation metrics tell us about saliency models?cited by 185
  11. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  12. 2020Actor-Context-Actor Relation Network for Spatio-Temporal Action Localizationcited by 91
28 more
  1. 2020Unified Image and Video Saliency Modelingcited by 75
  2. 2017Deep Visual Attention Predictioncited by 70
  3. 2018Revisiting Video Saliency: A Large-scale Benchmark and a New Modelcited by 67
  4. 2017SalGAN: Visual Saliency Prediction with Generative Adversarial Networkscited by 65
  5. 2014Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNetcited by 60
  6. 2019TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detectioncited by 59
  7. 2019Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentationcited by 57
  8. 2021DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modelingcited by 56
  9. 2016DeepGaze II: Reading fixations from deep features trained on object recognitioncited by 55
  10. 2015DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixationscited by 48
  11. 2020ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Predictioncited by 43
  12. 2016Shallow and Deep Convolutional Networks for Saliency Predictioncited by 42
  13. 2023Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attentioncited by 38
  14. 2013Actions in the Eye: Dynamic Gaze Datasets and Learnt Saliency Models for Visual Recognitioncited by 37
  15. 2021Temporal-Spatial Feature Pyramid for Video Saliency Detectioncited by 22
  16. 2017Predicting Video Saliency with Object-to-Motion CNN and Two-layer Convolutional LSTMcited by 17
  17. 2016Recurrent Mixture Density Network for Spatiotemporal Visual Attentioncited by 16
  18. 2023CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspectivecited by 15
  19. 2024GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpathscited by 15
  20. 2024DiffSal: Joint Audio and Video Learning for Diffusion Saliency Predictioncited by 13
  21. 2020GAZED- Gaze-guided Cinematic Editing of Wide-Angle Monocular Video Recordingscited by 11
  22. 2016Learning Gaze Transitions from Depth to Improve Video Saliency Estimationcited by 9
  23. 2019Multimodal Unified Attention Networks for Vision-and-Language Interactionscited by 9
  24. 2024Transformer-based Video Saliency Prediction with High Temporal Dimension Decodingcited by 7
  25. 2018SG-FCN: A Motion and Memory-Based Deep Learning Model for Video Saliency Detectioncited by 6
  26. 2021Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Modelcited by 6
  27. 2025Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cuescited by 4
  28. 2021A Gated Fusion Network for Dynamic Saliency Predictioncited by 3

Built on by

Not cited yet.