paper-with-me

Papers

Multimodal Pretraining for Dense Video Captioning

2020-11-10 · Asian Chapter of the Association for Computational Linguistics 2020 · Gabriel Huang, Bo Pang, Zhenhai Zhu, Clara Rivera, Radu Soricut

Learning specific hands-on skills such as cooking, car maintenance, and home repairs increasingly happens via instructional videos. The user experience with such videos is known to be improved by meta-information such as time-stamped annotations for the main steps involved. Generating such annotations automatically is challenging, and we describe here two relevant contributions. First, we construct and release a new dense video captioning dataset, Video Timeline Tags (ViTT), featuring a variety of instructional videos together with time-stamped annotations. Second, we explore several multimodal sequence-to-sequence pretraining strategies that leverage large unsupervised datasets of videos and caption-like texts. We pretrain and subsequently finetune dense video captioning models using both YouCook2 and ViTT. We show that such models generalize well and are robust over a wide variety of instructional videos.

📄 PDF Abstract BibTeX arXiv:2011.11760

Code (1)

google-research-datasets/Video-Timeline-Tags-ViTT 공식 구현

Tasks

Dense Video CaptioningVideo Captioning

Similar Papers 제목 키워드 기반

Semantic-Aware Pretraining for Dense Video Captioning

2022-04-13 · Teng Wang, Zhu Liu, Feng Zheng, Zhichao Lu 외

This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021. We present a semantic-aware pretraining method for dense video captioning, which empowers the learned f…

Dense CaptioningDense Video CaptioningVideo Captioning

End-to-end Generative Pretraining for Multimodal Video Captioning

2022-01-20 · CVPR 2022 1 · Paul Hongsuck Seo, Arsha Nagrani, Anurag Arnab, Cordelia Schmid

Recent video and language pretraining frameworks lack the ability to generate sentences. We present Multimodal Video Generative Pretraining (MV-GPT), a new pretraining framework for learning from unlabelled videos which …

Action ClassificationDecoderRetrievalSentence+3

End-to-end Dense Video Captioning as Sequence Generation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Dense video captioning aims to identify the events of interest in an input video, and generate descriptive captions for each event. Previous approaches usually follow a two-stage generative process, which first proposes …

Dense Video CaptioningDescriptiveVideo Captioning

End-to-end Dense Video Captioning as Sequence Generation

2022-04-18 · COLING 2022 10 · Wanrong Zhu, Bo Pang, Ashish V. Thapliyal, William Yang Wang 외

Dense video captioning aims to identify the events of interest in an input video, and generate descriptive captions for each event. Previous approaches usually follow a two-stage generative process, which first proposes …

Dense Video CaptioningDescriptiveVideo Captioning

CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning

2026-06-08 · Penghui Yang, Long Xing, Xiaoyi Dong, Yuhang Zang 외 arxiv

Image and video captioning are fundamental tasks that bridge the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are…

Reinforcement LearningVideo CaptioningDense Captioning