论文标题
说唱：文本视频检索的冗余视频语言预培训
RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval
论文作者
论文摘要
视频语言预训练方法主要采用稀疏抽样技术来减轻视频的时间冗余。尽管有效，但稀疏采样仍然遭受模式间冗余的影响：视觉冗余和文本冗余。与高度概括的文本相比，稀疏采样的框架通常包含与文本无关的部分，称为视觉冗余。稀疏采样也可能会错过与某些文本部分相对应的重要帧，从而导致文本冗余。模式间的冗余导致视频和文本信息的不匹配，从而阻碍了模型从更好地学习跨模式的共享语义。为了减轻它，我们建议预先培训冗余视频语言。我们通过计算跨模式的最小相似性来设计视频贴片和文本令牌的冗余测量。然后，我们通过拟议的冗余意识对比学习来惩罚高繁殖的视频补丁和文本令牌。我们在四个基准数据集（MSRVTT，MSVD，DIDEMO和LSMDC）上评估了我们的方法，从而对先前的状态结果取得了重大改进。我们的代码可在https://github.com/caskcsg/vlp/tree/main/rap上找到。
Video language pre-training methods have mainly adopted sparse sampling techniques to alleviate the temporal redundancy of videos. Though effective, sparse sampling still suffers inter-modal redundancy: visual redundancy and textual redundancy. Compared with highly generalized text, sparsely sampled frames usually contain text-independent portions, called visual redundancy. Sparse sampling is also likely to miss important frames corresponding to some text portions, resulting in textual redundancy. Inter-modal redundancy leads to a mismatch of video and text information, hindering the model from better learning the shared semantics across modalities. To alleviate it, we propose Redundancy-aware Video-language Pre-training. We design a redundancy measurement of video patches and text tokens by calculating the cross-modal minimum dis-similarity. Then, we penalize the highredundant video patches and text tokens through a proposed redundancy-aware contrastive learning. We evaluate our method on four benchmark datasets, MSRVTT, MSVD, DiDeMo, and LSMDC, achieving a significant improvement over the previous stateof-the-art results. Our code are available at https://github.com/caskcsg/VLP/tree/main/RaP.
