融合视频、用户与上下文信息，精准预测社交媒体视频热度。
MVP: Winning Solution to SMP Challenge 2025 Video Track
- 结合预训练模型提取的视频特征与用户元数据、上下文信息构建表达性强的视频表示。
- 通过日志变换和异常值剔除提升模型鲁棒性，梯度提升回归模型捕捉多模态复杂模式。
- 在SMP挑战赛2025视频赛道中排名第一，适合内容推荐与趋势预测场景。
社交媒体平台是内容传播、观点表达和公众参与的核心枢纽，涵盖多种模态。准确预测社交媒体视频的流行度，对内容推荐、趋势检测和用户参与具有重要价值。本文提出多模态视频预测器（MVP），为SMP挑战赛2025视频赛道的获胜方案。MVP通过整合预训练模型提取的深层视频特征、用户元数据及上下文信息，构建富有表现力的视频表示。框架采用系统化预处理技术，包括对数变换和异常值剔除，以增强模型鲁棒性。使用梯度提升回归模型捕捉跨模态复杂模式。该方法在官方评估中位列第一，验证了其在社交平台多模态视频流行度预测中的有效性与可靠性。源代码见 https://anonymous.4open.science/r/SMPDVideo。
原文摘要 · Abstract (English)
Social media platforms serve as central hubs for content dissemination, opinion expression, and public engagement across diverse modalities. Accurately predicting the popularity of social media videos enables valuable applications in content recommendation, trend detection, and audience engagement. In this paper, we present Multimodal Video Predictor (MVP), our winning solution to the Video Track of the SMP Challenge 2025. MVP constructs expressive post representations by integrating deep video features extracted from pretrained models with user metadata and contextual information. The framework applies systematic preprocessing techniques, including log-transformations and outlier removal, to improve model robustness. A gradient-boosted regression model is trained to capture complex patterns across modalities. Our approach ranked first in the official evaluation of the Video Track, demonstrating its effectiveness and reliability for multimodal video popularity prediction on social platforms. The source code is available at https://anonymous.4open.science/r/SMPDVideo.
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。