Discriminative Latent Semantic Graph for Video Captioning
This work addresses the problem of generating semantic-rich captions for videos, which is incremental as it builds on existing encoder-decoder frameworks by explicitly modeling object interactions and frame-level information.
The paper tackles video captioning by proposing a joint framework that enhances object proposals, aggregates visual knowledge, and validates sentences, resulting in significant improvements over state-of-the-art methods on metrics like BLEU-4 and CIDEr on MVSD and MSR-VTT datasets.
Video captioning aims to automatically generate natural language sentences that can describe the visual contents of a given video. Existing generative models like encoder-decoder frameworks cannot explicitly explore the object-level interactions and frame-level information from complex spatio-temporal data to generate semantic-rich captions. Our main contribution is to identify three key problems in a joint framework for future video summarization tasks. 1) Enhanced Object Proposal: we propose a novel Conditional Graph that can fuse spatio-temporal information into latent object proposal. 2) Visual Knowledge: Latent Proposal Aggregation is proposed to dynamically extract visual words with higher semantic levels. 3) Sentence Validation: A novel Discriminative Language Validator is proposed to verify generated captions so that key semantic concepts can be effectively preserved. Our experiments on two public datasets (MVSD and MSR-VTT) manifest significant improvements over state-of-the-art approaches on all metrics, especially for BLEU-4 and CIDEr. Our code is available at https://github.com/baiyang4/D-LSG-Video-Caption.