# ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction

arXiv: https://arxiv.org/abs/2604.08613 · HTML: https://mlsanity.com/paper/2604.08613/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [InternVideo2: Scaling Foundation Models for Multimodal Video Understanding](https://mlsanity.com/paper/2403.15377/) (2024)
- [What do different evaluation metrics tell us about saliency models?](https://mlsanity.com/paper/1604.03605/) (2016)
- [Revisiting Video Saliency: A Large-scale Benchmark and a New Model](https://mlsanity.com/paper/1801.07424/) (2018)
- [TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection](https://mlsanity.com/paper/1908.05786/) (2019)
- [ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction](https://mlsanity.com/paper/2012.06170/) (2020)
- [STAViS: Spatio-Temporal AudioVisual Saliency Network](https://mlsanity.com/paper/2001.03063/) (2020)
- [Spatial Understanding from Videos: Structured Prompts Meet Simulation Data](https://mlsanity.com/paper/2506.03642/) (2025)
- [Temporal-Spatial Feature Pyramid for Video Saliency Detection](https://mlsanity.com/paper/2105.04213/) (2021)
- [DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture](https://mlsanity.com/paper/2409.03550/) (2024)
- [CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective](https://mlsanity.com/paper/2303.06357/) (2023)
- [DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction](https://mlsanity.com/paper/2403.01226/) (2024)
- [AIM 2024 Challenge on Video Saliency Prediction: Methods and Results](https://mlsanity.com/paper/2409.14827/) (2024)
- [Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization](https://mlsanity.com/paper/2312.07384/) (2023)
- [Towards Generalizable Deepfake Detection by Primary Region Regularization](https://mlsanity.com/paper/2307.12534/) (2023)

## Built on by (most cited first, 2 of 2)

- [NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results](https://mlsanity.com/paper/2604.14816/) (2026)
- [TINA+: Probing Residual Visual Knowledge in Unlearned Diffusion Models via Diffusion-Consistent Text-Free Inversion](https://mlsanity.com/paper/2608.17747/) (2026)

## Abstract (arXiv)

In this report, we present our champion solution for the NTIRE 2026 Challenge on Video Saliency Prediction held in conjunction with CVPR 2026. To exploit complementary inductive biases for video saliency, we propose Video Saliency with Adaptive Gated Experts (ViSAGE), a multi-expert ensemble framework. Each specialized decoder performs adaptive gating and modulation to refine spatio-temporal features. The complementary predictions from different experts are then fused at inference. ViSAGE thereby aggregates diverse inductive biases to capture complex spatio-temporal saliency cues in videos. On the Private Test set, ViSAGE ranked first on two out of four evaluation metrics, and outperformed most competing solutions on the other two metrics, demonstrating its effectiveness and generalization ability. Our code has been released at https://github.com/iLearn-Lab/CVPRW26-ViSAGE.