在NTIRE 2026上视频显著性预测挑战中的ViSAGE
ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction
AI总结：
本文提出ViSAGE框架，通过多专家集合方法融合互补的归纳偏置，提升视频显著性预测性能，在私人测试集上取得优异成绩。
摘要：
在本文中，我们报告了在CVPR 2026上举行的视频显著性预测挑战中我们的冠军解决方案。为了利用互补的归纳偏置进行视频显著性预测，我们提出了Video Saliency with Adaptive Gated Experts (ViSAGE)，一种多专家集合框架。每个专门的解码器执行自适应门控和调制以细化时空特征。不同专家的互补预测然后在推理时融合。ViSAGE因此聚合了多样化的归纳偏置，以捕捉视频中的复杂时空显著性线索。在私人测试集上，ViSAGE在两个出四的评估指标上排名第一，并在另外两个指标上优于大多数竞争解决方案，证明了其有效性和泛化能力。我们的代码已发布在https://github.com/iLearn-Lab/CVPRW26-ViSAGE。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
