4D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling
本文通过提出BEAST模型及4D并行化方案，解决了高精度大气建模中的不确定性量化问题，实现了高效计算与准确预测。
0 citationsRead paper
Selected work
Representative Papers
DensFiLM: Density-Conditioned Video Saliency for Crowd Scenes
This work addresses the limitation of existing video saliency models, which employ a uniform gaze strategy and struggle to adapt to attentional variations across different crowd densities. To overcome this, the authors propose the first density-conditioned video saliency model by integrating a lightweight FiLM module into the bottleneck layer of a Video Swin Transformer. This module dynamically modulates feature channels through scaling and shifting based on crowd density embeddings, enabling adaptive modeling for both sparse and dense crowd scenes. The approach introduces only approximately 100K additional parameters and supports either ground-truth or predicted density labels. On the CrowdFix benchmark, it achieves an NSS of 1.434 and a CC of 0.517, surpassing ACLNet by over 14%. Ablation studies confirm that density conditioning yields substantial performance gains, with predicted density labels performing comparably to ground-truth ones.
0 citationsRead paper
Recent publications
Latest Papers
4D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling
本文通过提出BEAST模型及4D并行化方案，解决了高精度大气建模中的不确定性量化问题，实现了高效计算与准确预测。
0 citationsRead paper
DensFiLM: Density-Conditioned Video Saliency for Crowd Scenes
This work addresses the limitation of existing video saliency models, which employ a uniform gaze strategy and struggle to adapt to attentional variations across different crowd densities. To overcome this, the authors propose the first density-conditioned video saliency model by integrating a lightweight FiLM module into the bottleneck layer of a Video Swin Transformer. This module dynamically modulates feature channels through scaling and shifting based on crowd density embeddings, enabling adaptive modeling for both sparse and dense crowd scenes. The approach introduces only approximately 100K additional parameters and supports either ground-truth or predicted density labels. On the CrowdFix benchmark, it achieves an NSS of 1.434 and a CC of 0.517, surpassing ACLNet by over 14%. Ablation studies confirm that density conditioning yields substantial performance gains, with predicted density labels performing comparably to ground-truth ones.
0 citationsRead paper