mlsanityData to 7 Oct 2026

A Deep Multi-Level Network for Saliency Prediction

arXiv 1609.01064 ↗First posted 5 Sep 2016cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel deep architecture for saliency prediction. Current state of the art models for saliency prediction employ Fully Convolutional networks that perform a non-linear combination of features extracted from the last convolutional layer to predict saliency maps. We propose an architecture which, instead, combines features extracted at different levels of a Convolutional Neural Network (CNN). Our model is composed of three main blocks: a feature extraction CNN, a feature encoding network, that weights low and high level feature maps, and a prior learning network. We compare our solution with state of the art saliency models on two public benchmarks datasets. Results show that our model outperforms under all evaluation metrics on the SALICON dataset, which is currently the largest public dataset for saliency prediction, and achieves competitive results on the MIT300 benchmark.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 8; 2023: 9; 2024: 10; 2025: 6; 2026: 8.

54 papers.

Sort:

By area:

  1. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  2. 2021DRIVE: Deep Reinforced Accident Anticipation with Visual Explanationcited by 46
  3. 2021TranSalNet: Towards perceptually relevant visual saliency predictioncited by 44
  4. 2023Affordance Grounding from Demonstration Video to Target Imagecited by 34
  5. 2021Learning Visual Affordance Grounding from Demonstration Videoscited by 25
  6. 2023TempSAL -- Uncovering Temporal Information for Deep Saliency Predictioncited by 25
  7. 2022Grounded Affordance from Exocentric Viewcited by 21
  8. 2021Spatio-Temporal Self-Attention Network for Video Saliency Predictioncited by 19
  9. 2023Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embeddingcited by 19
  10. 2022Saliency in Augmented Realitycited by 17
  11. 2022Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmarkcited by 16
  12. 2022Rectify ViT Shortcut Learning by Visual Saliencycited by 14
38 more
  1. 2024INTRA: Interaction Relationship-aware Weakly Supervised Affordance Groundingcited by 12
  2. 2021MAAD: A Model and Dataset for "Attended Awareness" in Drivingcited by 9
  3. 2021SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networkscited by 9
  4. 2021Attention mechanisms and deep learning for machine vision: A survey of the state of the artcited by 8
  5. 2021SALYPATH: A Deep-Based Architecture for visual attention predictioncited by 7
  6. 2023Audio-visual Saliency for Omnidirectional Videoscited by 7
  7. 2024How is Visual Attention Influenced by Text Guidance? Database and Modelcited by 7
  8. 2026Agentic Retoucher for Text-To-Image Generationcited by 7
  9. 2024Data Augmentation via Latent Diffusion for Saliency Predictioncited by 5
  10. 2023Scanpath Prediction in Panoramic Videos via Expected Code Length Minimizationcited by 4
  11. 2023Rethinking Object Saliency Ranking: A Novel Whole-flow Processing Paradigmcited by 4
  12. 2024Learning User Embeddings from Human Gaze for Personalised Saliency Predictioncited by 4
  13. 2024How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Modelcited by 4
  14. 2025SalM2: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attentioncited by 4
  15. 2025Closed-Loop Transfer for Weakly-supervised Affordance Groundingcited by 4
  16. 2024AD-Lite Net: A Lightweight and Concatenated CNN Model for Alzheimer's Detection from MRI Imagescited by 3
  17. 2021Modeling Object Dissimilarity for Deep Saliency Predictioncited by 2
  18. 2022Reinforcement Learning for Predicting Traffic Accidentscited by 2
  19. 2023Learning Saliency From Fixationscited by 2
  20. 2021DeepRare: Generic Unsupervised Visual Attention Modelscited by 1
  21. 2021A Simple and efficient deep Scanpath Predictioncited by 1
  22. 2022Where and What: Driver Attention-based Object Detectioncited by 1
  23. 2022Clustered Saliency Predictioncited by 1
  24. 2023Multi-Scale Estimation for Omni-Directional Saliency Maps Using Learnable Equator Biascited by 1
  25. 2024Learning Gaussian Representation for Eye Fixation Predictioncited by 1
  26. 2024Comparing Optical Flow and Deep Learning to Enable Computationally Efficient Traffic Event Detection with Space-Filling Curvescited by 1
  27. 2025Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformercited by 1
  28. 2026SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptationcited by 1
  29. 2026From Scene to Object: Text-Guided Dual-Gaze Predictioncited by 1
  30. 2026EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinementcited by 1
  31. 2026Exploring deep learning for Event-Based Saliency Prediction with a Transformer-based modelcited by 1
  32. 2021Learning from Shader Program Tracescited by 0
  33. 2021Saliency for free: Saliency prediction as a side-effect of object recognitioncited by 0
  34. 2023MRGAN360: Multi-stage Recurrent Generative Adversarial Network for 360 Degree Image Saliency Predictioncited by 0
  35. 2024AHMF: Adaptive Hybrid-Memory-Fusion Model for Driver Attention Predictioncited by 0
  36. 2024PatchEX: High-Quality Real-Time Temporal Supersampling through Patch-based Parallel Extrapolationcited by 0
  37. 2025Towards Robust Unsupervised Attention Prediction in Autonomous Drivingcited by 0
  38. 2025Visual Attention Graphcited by 0

50 most cited of 54 All 54 (JSON)