Scholarlink

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 .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Exploring the Impact of Model Parameters and Components on Video Saliency Prediction with Foundation Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Morteza Moradi,
  • Mohammad Moradi,
  • Francesco Rundo,
  • Concetto Spampinato,
  • Ali Borji,
  • Simone Palazzo

摘要

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 .