多专家协作的视频显著性预测模型，提升关键指标表现。
ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction
- 采用自适应门控专家框架，融合多路特征
- 私有测试集上两项指标排名第一，三项优于多数方案
- 适合关注视频注意力建模的研究者和开发者
本文介绍我们在2026年CVPR联合举办的NTIRE 2026视频显著性预测挑战赛中的冠军解决方案。为利用视频显著性任务中互补的归纳偏置，我们提出视频显著性自适应门控专家模型（ViSAGE），一种多专家集成框架。每个专用解码器通过自适应门控与调制机制优化时空特征，推理阶段融合不同专家的互补预测结果。该方法有效聚合多样化的归纳偏置，捕捉视频中复杂的时空显著性线索。在私有测试集上，ViSAGE在四项评估指标中的两项排名第一，其余两项也优于多数参赛方案，验证了其有效性与泛化能力。代码已开源：https://github.com/iLearn-Lab/CVPRW26-ViSAGE。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。