Summary about Video-to-Text datasets. This repository is part of the review paper *Bridging Vision and Language from the Video-to-Text Perspective: A Comprehensive Review*

A curated list of video-text datasets in a variety of languages. These datasets can be used for video captioning (video description) or video retrieval.

Source code of the paper titled *Improving Video Captioning with Temporal Composition of a Visual-Syntactic Embedding*

Audio Visual Scene-Aware Dialog (AVSD) Challenge at the 10th Dialog System Technology Challenge (DSTC)

Source code of the paper titled *Attentive Visual Semantic Specialized Network for Video Captioning*

Video content description technique for generating descriptions for unconstrained videos.

A Video.js 7 middleware that uses browser speech synthesis to speak descriptions contained in a description text track

Qwen-VL-Narrator is an expert model for understanding video clips to generate fine-grained descriptions. Qwen-VL-Narrator 是一个影视领域专家模型，能够提供影视频片段详细描述，应用于视频检索、摘要、理解、细粒度标注等场景，也能用于视频生成工作流来实现视频反推。

A simple attention deep learning model to answer questions about a given video with the most relevant video intervals as answers.

MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian (Bahasa Indonesia).

Video description library with modern Python tooling compatibility and improving multimedia accessibility

A new package that processes user-submitted text descriptions of images or videos containing watermarks and returns structured, watermark-free descriptions. It uses an LLM to reinterpret the content w

This project processes videos by extracting frames, generating detailed visual descriptions for each frame using the BLIP model, and then summarizing these descriptions with the BART model.

FrVD: French Video Description dataset

Tool employed to visualize synchronized FrVD metadata and videos simultaneously.