SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling

In recent years, large-scale video-language pre-training (VidLP) has received considerable attention for its effectiveness in relevant tasks. In this paper, we propose a novel action-centric VidLP framework that employs video tube features for temporal modeling and language features based on semantic role labeling (SRL). Our video encoder generates multiple tube features along object trajectories, identifying action-related regions within videos, to overcome the limitations of existing temporal attention mechanisms. Additionally, our text encoder incorporates highlevel, action-related language knowledge, previously underutilized in current VidLP models. The SRL captures actionverbs and related semantics among objects in sentences and enhances the ability to perform instance-level text matching, thus enriching the cross-modal (CM) alignment process. We also introduce two novel pre-training objectives and a self-supervision strategy to produce a more faithful CM representation. Experimental results demonstrate that our method outperforms existing VidLP frameworks in various downstream tasks and datasets, establishing our model a baseline in the modern VidLP framework.