Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints. In this paper, we propose TransVCL: an attention-enhanced video copy localization network, which is optimized directly from initial frame-level features and trained end-to-end with three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for similarity matrix generation, and a temporal alignment module for copied segments localization. In contrast to previous methods demanding the handcrafted similarity matrix, TransVCL incorporates long-range temporal information between feature sequence pair using self- and cross- attention layers. With the joint design and optimization of three components, the similarity matrix can be learned to present more discriminative copied patterns, leading to significant improvements over previous methods on segment-level labeled datasets (VCSL and VCDB). Besides the state-of-the-art performance in fully supervised setting, the attention architecture facilitates TransVCL to further exploit unlabeled or simply video-level labeled data. Additional experiments of supplementing video-level labeled datasets including SVD and FIVR reveal the high flexibility of TransVCL from full supervision to semi-supervision (with or without video-level annotation). Code is publicly available at https://github.com/transvcl/TransVCL.
翻译:视频复制本地化的目的是在视频检索应用程序中将所有复制的片段精确地本地化。 以往的方法通常从输入视频配对的框架级特征相似性生成的框架到框架的相似性矩阵,然后在时间限制下检测和完善类似矩阵上复制的片段的界限。 在本文中,我们提议 TransVCL:一个关注强化视频复制本地化网络,从初始框架级特征直接优化到经过培训的终端到终端,并有三个主要组成部分:功能增强定制变异器、相近矩阵生成的关联和软模层以及复制的片段本地化的时间校准模块。 与以前要求手工制作的相似性矩阵相比, TransVCLCL包含使用自关注层和交叉关注层对相配相配的长时间信息。 在三个组成部分的联合设计和优化下,类似的矩阵可以被学习为更具歧视性的复制模式,从而大大改进了以前关于分层级标签数据集( VCSLL和VDDB) 的透明性透明性透明性图像级别,除此之外,还只是用州级的透明性视频标签/透明性标签级别,在SDLLLA级上进一步提升的透明性数据库,在S-laV级上,在S-traclal-lab-laV级上,在S-laD-lablal-laD-laD-laV级的透明性层次上,在S-laural- 进一步的透明性层次上,在S-laural-laisal-laD-tra-laD-ladal-lad-lad-lad-lad-lad-lad-lad-lad-lad-lad-lax-lax-lax-lax-lax-lad-lad-lax-lax-lax-lad-lax-lax级的高级的高级的高级的高级的高级的高级的高级的高级的高级的高级的透明制上,在S-labal-lax-lax-lax-lax-lax-al-lax-lax-lax-lax-lax-lax-lax-lax-lax-lax-lax-lax-lax-lax-lax-