captioning-videos 开源项目推荐（32 个）

OpenGVLab /Ask-Anything

[CVPR 2024亮点][VideoChatGPT] ChatGPT具有视频理解！还有更多支持LM，例如miniGPT 4、StableLM和MOSS。

TheShadow29 /awesome-grounding

awesome grounding: A curated list of research papers in visual grounding

TheShadow29 /vognet-pytorch

[CVPR20] Video Object Grounding using Semantic Roles in Language Description (https://arxiv.org/abs/2003.10606)

aimagelab /pacscore

[CVPR 2023 & IJCV 2025] Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

linto-ai /linto-studio

Open source transcription, live subtitling and meeting summarization. Web app, API and SDKs of the LinTO platform.

TheShadow29 /VidSitu

[CVPR21] Visual Semantic Role Labeling for Video Understanding (https://arxiv.org/abs/2104.00990)

mynlp /cst_captioning

PyTorch Implementation of Consensus-based Sequence Training for Video Captioning

chihyaoma /cyclical-visual-captioning

PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision

x-CK-x /Dataset-Curation-Tool

Data Curation Tool is a local-first dataset curation, tagging, model-management, downloader, 3D generation, media metadata, and tool-orchestration application. The current documentation set is stored in docs/wiki/

szq0214 /MSR-VTT-Challenge

Video to Language Challenge (MSR-VTT Challenge 2016)

sanjifr3 /Narrator

An image and video description generator using an CNN-RNN based architecture.

aimagelab /mvad-names-dataset

M-VAD Names Dataset. Multimedia Tools and Applications (2019)

PrabhanshuKamal2121 /N8N-ViralFlow

一个 AI 驱动、全自动的 n8n 工作流，可将单个文本提示转化为让人停下滑动的 YouTube Shorts，采用动态视觉、富有戏剧性的 TTS 旁白和实时剪辑——全部通过 Docker、Ollama、MinIO 和开源工具自托管。

preritj /show_attend_tell

Caption generator for live camera feed

apivideo /caption.new

Sample app to add captions to an uploaded video. From api.video (https://api.video)

Hyeongkeun /LAVCap

Official Pytorch Implementation of 'LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport' (ICASSP2025)

cd2bit /awesome-list-of-captioned-courses

Online professional courses that are captioned and/or subtitled

alimama-creative /VC4VG

[EMNLP 2025] VC4VG: Optimizing Video Captions for Text-to-Video Generation

tjoab /captionaize

Generate TikTok— and Instagram—tailored captions and hashtags for your videos using the power of some super creative robots up in the clouds ☁️ 🤖 💬 ☁️

BKHMSI /forget-me-not

Video Search using Natural Language