VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning

28 Nov 2022  ·  Kashu Yamazaki, Khoa Vo, Sang Truong, Bhiksha Raj, Ngan Le ·

Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and non-visual components (e.g. action, relations) under the mutual influence of vision and language, we first propose a visual-linguistic (VL) feature. In the proposed VL feature, the scene is modeled by three modalities including (i) a global visual environment; (ii) local visual main agents; (iii) linguistic scene elements. We then introduce an autoregressive Transformer-in-Transformer (TinT) to simultaneously capture the semantic coherence of intra- and inter-event contents within a video. Finally, we present a new VL contrastive loss function to guarantee learnt embedding features are matched with the captions semantics. Comprehensive experiments and extensive ablation studies on ActivityNet Captions and YouCookII datasets show that the proposed Visual-Linguistic Transformer-in-Transform (VLTinT) outperforms prior state-of-the-art methods on accuracy and diversity.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Video Captioning ActivityNet Captions VLTinT (ae-test split) C3D/Ling ROUGE-L 36.56 # 1
METEOR 17.97 # 1
BLEU4 14.5 # 2
CIDEr 31.13 # 3


No methods listed for this paper. Add relevant methods here