HiPrompt: Hierarchical Variational Prompting for Dense Video Captioning
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 14547-14556
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Fujian Province (2026J008077)
- Fujian Provincial Education and Scientific Research Program for Young and Middle-aged Teachers (JZ230006)
- Natural Science Foundation of Shandong Province (ZR2026QC1054)
This publication has 26 references indexed in Scilit:
- Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval2024
- Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning2023
- ActionFormer: Localizing Moments of Actions with Transformers2022
- SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning2022
- End-to-end Generative Pretraining for Multimodal Video Captioning2022
- Captioning Images Taken by People Who Are Blind2020
- SODA: Story Oriented Dense Video Captioning Evaluation Framework2020
- Dual Encoding for Zero-Example Video Retrieval2019
- End-to-End Dense Video Captioning with Masked Transformer2018
- CIDEr: Consensus-based image description evaluation2015