Hierarchical Modular Network for Video Captioning
This work addresses the problem of generating accurate natural language descriptions for videos, which is incremental as it builds on existing supervised learning methods by better exploiting linguistic semantics.
The paper tackles video captioning by proposing a hierarchical modular network that bridges video representations and linguistic semantics at entity, predicate, and sentence levels, achieving state-of-the-art results with CIDEr scores of 104.0% on MSVD and 51.5% on MSR-VTT.
Video captioning aims to generate natural language descriptions according to the content, where representation learning plays a crucial role. Existing methods are mainly developed within the supervised learning framework via word-by-word comparison of the generated caption against the ground-truth text without fully exploiting linguistic semantics. In this work, we propose a hierarchical modular network to bridge video representations and linguistic semantics from three levels before generating captions. In particular, the hierarchy is composed of: (I) Entity level, which highlights objects that are most likely to be mentioned in captions. (II) Predicate level, which learns the actions conditioned on highlighted objects and is supervised by the predicate in captions. (III) Sentence level, which learns the global semantic representation and is supervised by the whole caption. Each level is implemented by one module. Extensive experimental results show that the proposed method performs favorably against the state-of-the-art models on the two widely-used benchmarks: MSVD 104.0% and MSR-VTT 51.5% in CIDEr score.