Spaces:
Running on Zero
Running on Zero
| title: OneEmo Affective Reasoning | |
| emoji: 🎭 | |
| colorFrom: gray | |
| colorTo: pink | |
| sdk: gradio | |
| sdk_version: 6.22.0 | |
| app_file: app.py | |
| short_description: Unified multimodal reasoning for emotion perception | |
| python_version: "3.12" | |
| startup_duration_timeout: 30m | |
| # OneEmo: A Unified Multimodal Reasoning Model for Emotion Perception | |
| This Space demonstrates [OneEmo](https://huggingface.co/Jiaha0Hu4ng/OneEmo), a unified | |
| multimodal reasoning model for emotion perception, understanding, and interaction in | |
| video scenarios. It supports eight tasks: | |
| - **B-MER** – Basic Multimodal Emotion Recognition (single label) | |
| - **MSA** – Multimodal Sentiment Analysis (positive/neutral/negative) | |
| - **OV-MER** – Open-Vocabulary Multimodal Emotion Recognition | |
| - **MHD** – Multimodal Humor Detection | |
| - **MSD** – Multimodal Sarcasm Detection | |
| - **ERG** – Empathetic Response Generation | |
| Upload a video, select a task, and click **Analyze** to see the model's emotion | |
| analysis with chain-of-thought reasoning. | |
| ## References | |
| - Paper: [OneEmo: A Unified Multimodal Reasoning Model for Emotion Perception, Understanding, and Interaction](https://arxiv.org/abs/2608.06013) | |
| - Model: [Jiaha0Hu4ng/OneEmo](https://huggingface.co/Jiaha0Hu4ng/OneEmo) | |
| - Code: [GitHub](https://github.com/waHAHJIAHAO/OneEmo) | |
| Example videos are CC0-licensed, sourced from the | |
| [Gradio Space Example Inputs — Videos](https://huggingface.co/datasets/linoyts/repo-to-space-example-videos) dataset. |