压缩视频聚合器:用于高效微视频推荐的内容驱动模块
Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation
AI总结:
本文提出压缩视频聚合器(CVA),通过解耦视频信息与偏好学习,利用冻结的VFM嵌入进行聚合,生成紧凑的视频嵌入以提升推荐效果。实验显示,通过CLIP重新选择关键帧可显著减少训练时间和GPU内存消耗,并提升所有方法的性能。
摘要:
我们提出压缩视频聚合器(CVA),一个轻量级的微视频推荐模块,将视频信息与偏好学习解耦。它聚合冻结的VFM嵌入,并在不使用交叉注意力投影的情况下利用潜在推理,生成紧凑的视频嵌入以供推荐器使用。由于原始基准在帧数上的冗余及其过于粗略的采样,我们使用标题基于CLIP重新选择关键帧。在MicroLens和Short-Video上的实验显示,训练时间和GPU内存消耗减少了数量级,且重新选择的帧可以进一步提升所有方法的性能,包括CVA。此外,我们还讨论了几种涉及错误标题的场景对我们的方法的影响。代码将很快发布。
英文摘要:
We propose \textbf{Compressed Video Aggregator} (CVA), a lightweight micro-video recommendation module that decouples video information from preference learning. CVA first summarizes frozen VFM frame embeddings into a semantic-consensus anchor through masked mean pooling, projects this anchor into a compact latent space, and refines the projected representation with residual self-attention and feedforward blocks before producing a single video embedding for the recommender. Due to the redundancy in the frame count of the original benchmark and its overly coarse sampling, we used titles to re-select key frames based on CLIP. Experiments on MicroLens and Short-Video show consistent gains with orders-of-magnitude reductions in training time and GPU memory, and re-selected frames can further enhance the performance of all methods, including CVA. Furthermore, we also discussed the impact of several scenarios involving erroneous titles on our method.
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。