UniVL

UniVL is a video-language pretrain model. It is designed with four modules and five objectives for both video language understanding and generation tasks. It is also a flexible model for most of the multimodal downstream tasks considering both efficiency and effectiveness.

Features

Finetune on YoucookII
Documentation available
Examples available
Run caption task on YoucookII
Pretrain on HowTo100M
Licensed under the MIT License

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow UniVL

UniVL Web Site

Other Useful Business Software

Build AI Apps with Gemini 3 on Vertex AI

Access Google’s most capable multimodal models. Train, test, and deploy AI with 200+ foundation models on one platform.

Vertex AI gives developers access to Gemini 3—Google’s most advanced reasoning and coding model—plus 200+ foundation models including Claude, Llama, and Gemma. Build generative AI apps with Vertex AI Studio, customize with fine-tuning, and deploy to production with enterprise-grade MLOps. New customers get $300 in free credits.

Try Vertex AI Free

Rate This Project

User Reviews

Be the first to post a review of UniVL!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

Python

Related Categories

Python Localization (L10N) Software, Python Object Detection Models

Registered

2024-07-12

Similar Business Software

LTX

Control every aspect of your video using AI, from ideation to final edits, on one holistic platform. We’re pioneering the integration of AI and video production, enabling the transformation of a single idea into a cohesive, AI-generated video. LTX empowers individuals to share their visions,...

See Software
Vertex AI

Build, deploy, and scale machine learning (ML) models faster, with fully managed ML tools for any use case. Through Vertex AI Workbench, Vertex AI is natively integrated with BigQuery, Dataproc, and Spark. You can use BigQuery ML to create and execute machine learning models in BigQuery...

See Software
Bitrise

Bitrise is a CI/CD platform built for mobile development, helping teams speed up builds, automate testing, and deliver high-quality apps faster. It supports native languages like Swift, Objective-C, Java, and Kotlin, as well as cross-platform frameworks including React Native, Flutter, Xamarin,...

See Software
LM-Kit.NET

LM-Kit.NET is a cutting-edge, high-level inference SDK designed specifically to bring the advanced capabilities of Large Language Models (LLM) into the C# ecosystem. Tailored for developers working within .NET, LM-Kit.NET provides a comprehensive suite of powerful Generative AI tools, making...

See Software
Windsurf Editor

The Windsurf Editor is a free AI-powered IDE and AI coding assistant that accelerates development by providing intelligent code generation and agents in over 70 programming languages and more than 40 IDEs, including VSCode, JetBrains, and Jupyter Notebooks. With Windsurf, developers can write...

See Software
SafetyCulture

SafetyCulture is a workplace operations platform trusted by 85,000+ teams to work safely, meet higher standards, and improve every day. 1. Streamline operations by eliminating paper processes - with simple checklists your teams can complete on any device. 2. Get the job done with seamless...

See Software