Transform-Equivariant Consistency Learning for Temporal Sentence Grounding

TL;DR

This paper proposes a self-supervised learning framework called ECRL for temporal sentence grounding that enhances discriminative video representations through transform-equivariant consistency, reducing reliance on large paired datasets.

Contribution

Introduction of a novel ECRL framework utilizing self-supervised consistency loss and data augmentation to improve temporal grounding accuracy.

Findings

Effective on ActivityNet, TACoS, and Charades-STA datasets.

Reduces dependency on large annotated datasets.

Improves boundary prediction accuracy.

Abstract

This paper addresses the temporal sentence grounding (TSG). Although existing methods have made decent achievements in this task, they not only severely rely on abundant video-query paired data for training, but also easily fail into the dataset distribution bias. To alleviate these limitations, we introduce a novel Equivariant Consistency Regulation Learning (ECRL) framework to learn more discriminative query-related frame-wise representations for each video, in a self-supervised manner. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted under various video-level transformations. Concretely, we first design a series of spatio-temporal augmentations on both foreground and background video segments to generate a set of synthetic video samples. In particular, we devise a self-refine module to enhance the completeness and smoothness of the augmented video. Then, we present a novel self-supervised consistency loss (SSCL) applied on the original and augmented videos to capture their invariant query-related semantic by minimizing the KL-divergence between the sequence similarity of two videos and a prior Gaussian distribution of timestamp distance. At last, a shared grounding head is introduced to predict the transform-equivariant query-guided segment boundaries for both the original and augmented videos. Extensive experiments on three challenging datasets (ActivityNet, TACoS, and Charades-STA) demonstrate both effectiveness and efficiency of our proposed ECRL framework.