Controllable Image Captioning via Prompting

[2212.01803] Controllable Image Captioning via Prompting - arXiv

Such a controllable capability is achieved by embedding the prompt learning into the image captioning framework. To be specific, we design a set ...

Such a controllable capability is achieved by embedding the prompt learning into the image captioning framework. To be specific, we design a set of prompts to ...

Controllable image captioning via prompting - ACM Digital Library

In this paper, we show that a unified model is qualified to perform well in diverse domains and freely switch among multiple styles. Such a controllable ...

Controllable Image Captioning via Prompting - ResearchGate

Controllable Image Captioning via Prompting ... Despite the remarkable progress of image captioning, existing captioners typically lack the ...

Controllable Image Captioning Via Prompting | PDF - Scribd

Controllable Image Captioning via Prompting - Free download as Word Doc (.doc / .docx), PDF File (.pdf), Text File (.txt) or read online for free.

Controllable Image Captioning via Prompting - ResearchGate

Controllable Image Captioning via Prompting ... Despite the remarkable progress of image captioning, existing captioners typically lack the controllable ...

Learning Combinatorial Prompts for Universal Controllable Image ...

Controllable Image Captioning (CIC) -- generating natural language descriptions about images under the guidance of given control signals -- is ...

[PDF] Length-Controllable Image Captioning - Semantic Scholar

Controllable Image Captioning via Prompting. Ning WangJiahao XieJihao WuMingbo JiaLinlin Li. Computer Science. AAAI. 2023. TLDR. This paper designs a set of ...

PromptCap: Prompt-Guided Task-Aware Image Captioning - Yushi Hu

We propose PROMPTCAP (Prompt-guided image Captioning), a captioning model designed to serve as a better connector between images and black-box LMs.

Fully-attentive iterative networks for region-based controllable image ...

Controllable image captioning via prompting. In: Proceedings of the AAAI Conference on Artificial Intelligence. Google Scholar. Wang et al., 2022b. Wang, Z ...

Controllable Image Captioning with Feature Refinement and ... - MDPI

... control signals to generate captions, called controllable image captions (CIC). ... Controllable Image Captioning via Prompting. arXiv 2022, arXiv ...

Official implementation of "ConZIC: Controllable Zero-shot ... - GitHub

Official implementation of "ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing" - joeyz0z/ConZIC.

A Framework for Generating Controllable and Grounded Captions

Controllable Image Captioning via Prompting. Ning WangJiahao XieJihao WuMingbo JiaLinlin Li. Computer Science. AAAI. 2023. TLDR. This paper designs a set of ...

SamCap: Energy-based Controllable Image Captioning by Gradient ...

Controllable Image Captioning via Prompting. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2 (June 2023), 2617 ...

controllable image captioning - Papers With Code

Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. 1.

Towards Human-Interactive Controllable Video Captioning with ...

With the success of large-scale image caption models [1,2,3,4,5,6,7] using large amounts of image–text pairs in a transfer learning paradigm, interest has ...

PromptCap: Prompt-Guided Task-Aware Image Captioning | DeepAI

To address this challenge, we propose PromptCap, a captioning model that takes a natural-language prompt to control the contents of the ...

‪Zhen Wang‬ - ‪Google Scholar‬

Learning combinatorial prompts for universal controllable image captioning. Z ... DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism.

PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3

language prompt to control the visual entities to describe ... A popular solution is to project images into texts that black-box LMs can process, via a generic ...

similar - arxiv-sanity

... captioning models, without requiring any supervised training on any captioning data. similar · inspect. -72.63. Controllable Image Captioning via Prompting.