Weakly-Supervised Temporal Article Grounding

TL;DR

This paper introduces a new weakly-supervised task called temporal article grounding, addressing limitations of existing video grounding methods by handling multiple semantic scales and ungroundable sentences, supported by a new dataset and a novel DualMIL method.

Contribution

It proposes the first WSAG task, creates the YouwikiHow dataset, and develops the DualMIL model with specialized loss functions for weak supervision and hierarchical semantics.

Findings

DualMIL outperforms baseline models in experiments.

The dataset enables research on multi-scale and ungroundable sentence grounding.

Extensive ablations confirm the effectiveness of the proposed method.

Abstract

Given a long untrimmed video and natural language queries, video grounding (VG) aims to temporally localize the semantically-aligned video segments. Almost all existing VG work holds two simple but unrealistic assumptions: 1) All query sentences can be grounded in the corresponding video. 2) All query sentences for the same video are always at the same semantic scale. Unfortunately, both assumptions make today's VG models fail to work in practice. For example, in real-world multimodal assets (eg, news articles), most of the sentences in the article can not be grounded in their affiliated videos, and they typically have rich hierarchical relations (ie, at different semantic scales). To this end, we propose a new challenging grounding task: Weakly-Supervised temporal Article Grounding (WSAG). Specifically, given an article and a relevant video, WSAG aims to localize all ``groundable'' sentences to the video, and these sentences are possibly at different semantic scales. Accordingly, we collect the first WSAG dataset to facilitate this task: YouwikiHow, which borrows the inherent multi-scale descriptions in wikiHow articles and plentiful YouTube videos. In addition, we propose a simple but effective method DualMIL for WSAG, which consists of a two-level MIL loss and a single-/cross- sentence constraint loss. These training objectives are carefully designed for these relaxed assumptions. Extensive ablations have verified the effectiveness of DualMIL.