paper-with-me

Papers

Zero-Shot Video Captioning with Evolving Pseudo-Tokens

2022-07-22 · Yoad Tewel, Yoav Shalev, Roy Nadler, Idan Schwartz, Lior Wolf

We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has a high average matching score to a subset of the video frames. Unlike zero-shot image captioning methods, our work considers the entire sentence at once. This is achieved by optimizing, during the generation process, part of the prompt from scratch, by modifying the representation of all other tokens in the prompt, and by repeating the process iteratively, gradually improving the specificity and comprehensiveness of the generated sentence. Our experiments show that the generated captions are coherent and display a broad range of real-world knowledge. Our code is available at: https://github.com/YoadTew/zero-shot-video-to-text

📄 PDF Abstract BibTeX arXiv:2207.11100

Code (1)

yoadtew/zero-shot-video-to-text 공식 구현 pytorch

Tasks

Image CaptioningImage-text matchingLanguage ModelingLanguage ModellingSentenceSpecificityText MatchingVideo CaptioningWorld Knowledge

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Zero-shot Natural Language Video Localization

2021-08-29 · ICCV 2021 10 · Jinwoo Nam, Daechul Ahn, Dongyeop Kang, Seong Jong Ha 외

Understanding videos to localize moments with natural language often requires large expensive annotated video regions paired with language queries. To eliminate the annotation costs, we make a first attempt to train a na…

Image Captioning

SGCap: Decoding Semantic Group for Zero-shot Video Captioning

2025-08-02 · Zeyu Pan, Ping Li, Wenxiao Wang arxiv

Zero-shot video captioning aims to generate sentences for describing videos without training the model on video-text pairs, which remains underexplored. Existing zero-shot image captioning methods typically adopt a text-…

Video CaptioningImage Captioning

Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning

2018-11-07 · Xin Wang, Jiawei Wu, Da Zhang, Yu Su 외

Although promising results have been achieved in video captioning, existing models are limited to the fixed inventory of activities in the training corpus, and do not generalize to open vocabulary scenarios. Here we intr…

Mixture-of-ExpertsVideo Captioning

Fine-Grained Video Captioning through Scene Graph Consolidation

2025-02-23 · Sanghyeok Chu, Seonguk Seo, Bohyung Han

Recent advances in visual language models (VLMs) have significantly improved image captioning, but extending these gains to video understanding remains challenging due to the scarcity of fine-grained video captioning dat…

Caption GenerationImage CaptioningVideo CaptioningVideo Understanding

Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

2023-02-27 · CVPR 2023 1 · Antoine Yang, Arsha Nagrani, Paul Hongsuck Seo, Antoine Miech 외

In this work, we introduce Vid2Seq, a multi-modal single-stage dense event captioning model pretrained on narrated videos which are readily-available at scale. The Vid2Seq architecture augments a language model with spec…

Dense Video CaptioningLanguage ModelingLanguage ModellingSentence+1