TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision

TL;DR

TransVCL introduces an attention-enhanced, end-to-end trainable network for precise video copy localization, leveraging a customized Transformer to incorporate long-range temporal information and improve discriminative pattern learning.

Contribution

The paper presents a novel Transformer-based architecture that directly optimizes from frame-level features, enabling flexible supervision and superior localization performance.

Findings

Achieves state-of-the-art results on VCSL and VCDB datasets.

Effectively utilizes semi-supervised learning with video-level annotations.

Demonstrates high flexibility from full supervision to semi-supervision.

Abstract

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.