mlsanityData to 7 Oct 2026

NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results

arXiv 2604.14816 ↗First posted 16 Apr 2026cs.CV cs.HC cs.MMcited by 10

Not on the map. Why?

Abstract (arXiv)

This paper presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction. The goal of the challenge participants was to develop automatic saliency map prediction methods for the provided video sequences. The novel dataset of 2,000 diverse videos with an open license was prepared for this challenge. The fixations and corresponding saliency maps were collected using crowdsourced mouse tracking and contain viewing data from over 5,000 assessors. Evaluation was performed on a subset of 800 test videos using generally accepted quality metrics. The challenge attracted over 20 teams making submissions, and 7 teams passed the final phase with code review. All data used in this challenge is made publicly available - https://github.com/msu-video-group/NTIRE26_Saliency_Prediction.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 54 of its 107 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

54 of 107 references.

References · 54

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  5. 2022A ConvNet for the 2020scited by 3,545
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  7. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  8. 2017The Kinetics Human Action Video Datasetcited by 1,894
  9. 2025DINOv3cited by 1,297
  10. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  11. 2021Video Swin Transformercited by 1,090
  12. 2024VMamba: Visual State Space Modelcited by 955
38 more
  1. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  2. 2024InternVideo2: Scaling Foundation Models for Multimodal Video Understandingcited by 310
  3. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 287
  4. 2021Wav2CLIP: Learning Robust Audio Representations From CLIPcited by 210
  5. 2016What do different evaluation metrics tell us about saliency models?cited by 184
  6. 2020Unified Image and Video Saliency Modelingcited by 74
  7. 2018Revisiting Video Saliency: A Large-scale Benchmark and a New Modelcited by 66
  8. 2025Intuitive physics understanding emerges from self-supervised pretraining on natural videoscited by 66
  9. 2019Contextual Encoder-Decoder Network for Visual Saliency Predictioncited by 44
  10. 2021TranSalNet: Towards perceptually relevant visual saliency predictioncited by 44
  11. 2020ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Predictioncited by 42
  12. 2013Actions in the Eye: Dynamic Gaze Datasets and Learnt Saliency Models for Visual Recognitioncited by 36
  13. 2026The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Reportcited by 25
  14. 2019DAVE: A Deep Audio-Visual Embedding for Dynamic Saliency Predictioncited by 21
  15. 2026NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wildcited by 18
  16. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)cited by 16
  17. 2022Panoramic Vision Transformer for Saliency Detection in 360deg Videoscited by 15
  18. 2023CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspectivecited by 15
  19. 2026NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Resultscited by 15
  20. 2026NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methodscited by 15
  21. 2023Realistic Saliency Guided Image Enhancementcited by 14
  22. 2026NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Resultscited by 14
  23. 2026NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Resultscited by 14
  24. 2024DiffSal: Joint Audio and Video Learning for Diffusion Saliency Predictioncited by 13
  25. 2026The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Resultscited by 13
  26. 2017Saliency Revisited: Analysis of Mouse Movements versus Fixationscited by 12
  27. 2024CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusioncited by 12
  28. 2025NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Resultscited by 12
  29. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)cited by 12
  30. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)cited by 12
  31. 2025KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perceptioncited by 11
  32. 2022A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key!cited by 9
  33. 2024SalFoM: Dynamic Saliency Prediction with Video Foundation Modelscited by 9
  34. 2024YouTube SFV+HDR Quality Datasetcited by 9
  35. 2025Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Imagescited by 9
  36. 2019Context-Aware Saliency Detection for Image Retargeting Using Convolutional Neural Networkscited by 7
  37. 2024AIM 2024 Challenge on Video Saliency Prediction: Methods and Resultscited by 7
  38. 2024Textured Mesh Saliency: Bridging Geometry and Texture for Human Perception in 3D Graphicscited by 4

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge Reportcited by 8
  2. 2026Low Light Image Enhancement Challenge at NTIRE 2026cited by 7
  3. 2026The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overviewcited by 6
  4. 2026The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overviewcited by 6
  5. 2026Robust Deepfake Detection, NTIRE 2026 Challenge: Reportcited by 6
  6. 2026The First Controllable Bokeh Rendering Challenge at NTIRE 2026cited by 2
  7. 2026The Third Challenge on Image Denoising at NTIRE 2026: Methods and Resultscited by 1
  8. 2026NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Resultscited by 0
  9. 2026Pixel-Space Diffusion Transformerscited by 0
  10. 2026NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challengecited by 0