Currently, many approaches to the sentence query based moment location (SQML) task emphasize (inter-)modality interaction between video and language query via transformer-based cross-attention or contrastive learning. However, they could still face two issues: 1) modality interaction could be unexpectedly friendly to modality specific learning that merely learns modality specific patterns, and 2) modality interaction easily confuses spatio-temporal cues and ultimately makes time cues in the original video ambiguous. In this paper, we propose a modality synergy with spatio-temporal cue purification method (MS 2 P) for SQML to address the above two issues. Particularly, a conceptually simple modality synergy strategy is explored to keep features modality specific while absorbing the other modality complementary information with both carefully designed cross-attention unit and non-contrastive learning. As a result, modality specific semantics can be calibrated progressively in a safer way. To preserve time cues in original video, we further purify video representation into spatial and temporal parts to enhance localization resolution by the proposed two light-weight sentenceaware filtering operations. Experiments on Charades-STA, TACoS,
The quality of an enterprise's internal control affects the audit workflow, as well as the choice of audit procedures and scope, and ultimately the audit opinion. This paper takes A-share listed companies in 2016-2020 as the research sample and constructs a regression model to test the relationship between internal control quality and audit opinion in the context of digital transformation of enterprises. The empirical results show that internal control quality is significantly and negatively related to non-standard audit opinion, and this paper introduces the moderating variable of corporate digitization level, and the findings show that corporate digitization level can significantly moderate the effect of low internal control quality on the increase of non-standard audit opinion. The improvement of enterprise digitization level helps auditors to issue appropriate audit opinions. The article provides new perspectives on the importance of enterprise digitization construction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.