TimeChat
Video understanding model
A large language model designed to understand long videos by binding visual content with timestamps and producing video token sequences of varying lengths.
[CVPR 2024] TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
314 stars
5 watching
26 forks
Language: Python
last commit: 3 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 rese1f/moviechat | Develops a method for long video understanding by optimizing memory usage | 550 |
 pku-yuangroup/video-bench | Evaluates and benchmarks large language models' video understanding capabilities | 121 |
 mbzuai-oryx/video-chatgpt | A video conversation model that generates meaningful conversations about videos using large vision and language models | 1,246 |
 yuangongnd/ltu | An audio and speech large language model implementation with pre-trained models, datasets, and inference options | 396 |
 llyx97/tempcompass | A tool to evaluate video language models' ability to understand and describe video content | 91 |
 liuzhao1225/youdub-webui | A web-based video processing tool that uses AI to facilitate cultural and linguistic tasks such as transcription, translation, and audio synthesis. | 1,980 |
 shangwei5/vidue | A deep learning model that jointly performs video frame interpolation and deblurring with unknown exposure time | 69 |
 boheumd/ma-lmm | This project develops an AI model for long-term video understanding | 254 |
 kendryte/toucan-llm | A large language model with 70 billion parameters designed for chatbot and conversational AI tasks | 29 |
 thu-coai/opd | A large-scale pre-trained dialogue model for Chinese language | 74 |
 lightyear-turing/turingmm-34b-chat | An English-Chinese chat model developed from a large language model for conversational AI | 9 |
| pku-yuangroup/chronomagic-bench | Provides a benchmarking framework for evaluating the quality of text-to-video generation models | 191 |
 yunwentechnology/unilm | This project provides pre-trained models and tools for natural language understanding (NLU) and generation (NLG) tasks in Chinese. | 439 |
 brightmart/xlnet_zh | Trains a large Chinese language model on massive data and provides a pre-trained model for downstream tasks | 230 |
 andrewnguonly/chatabstractions | Provides a framework for creating custom chat models with dynamic failover and load balancing features | 79 |