As a companion to the ICPR 2024 accepted paper “SalFoM: Dynamic Saliency Prediction with Video Foundation Models”, this work investigates how various model parameters and components impact its performance. Since SalFoM represents the first effort of its kind in this field, the additional experiments presented here are designed to provide insights into the application of video foundation models for dynamic saliency prediction. This is achieved by exploring different aspects of the model’s architecture and the use of large video models. Additionally, this work analyzes the impact of various strategies for defining training objectives on the model’s learning capabilities and overall performance. The code is available at https://github.com/mr17m/SalFoM—Video-Saliency-Prediction.
Exploring the Impact of Model Parameters and Components on Video Saliency Prediction with Foundation Models
Rundo F.;
2025-01-01
Abstract
As a companion to the ICPR 2024 accepted paper “SalFoM: Dynamic Saliency Prediction with Video Foundation Models”, this work investigates how various model parameters and components impact its performance. Since SalFoM represents the first effort of its kind in this field, the additional experiments presented here are designed to provide insights into the application of video foundation models for dynamic saliency prediction. This is achieved by exploring different aspects of the model’s architecture and the use of large video models. Additionally, this work analyzes the impact of various strategies for defining training objectives on the model’s learning capabilities and overall performance. The code is available at https://github.com/mr17m/SalFoM—Video-Saliency-Prediction.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
