Research map / Video / Video generation
EmoVid: A Multimodal Emotion Video Dataset for Emotion-Centric Video Understanding and Generation
Zongyang Qiu, Bingyuan Wang, Xingbei Chen, Yingqing He, Zeyu Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-T2V-14B · EmoVid benchmark T2V | EA-8cls: 44.16 -> 48.33 | Improved |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-T2V-14B · EmoVid benchmark T2V | EA-2cls: 84.17 -> 88.33 | Improved |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-T2V-14B · EmoVid benchmark T2V | FVD: 594.3 -> 573.7 | Improved |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-T2V-14B · EmoVid benchmark T2V | Flicker: 0.0091 -> 0.0143 | Hurt |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-T2V-14B · EmoVid benchmark T2V | CLIP score: 0.2982 -> 0.3021 | No clear effect |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-I2V-480P · EmoVid benchmark I2V | EA-8cls: 71.30 -> 76.25 | Improved |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-I2V-480P · EmoVid benchmark I2V | EA-2cls: 91.25 -> 94.58 | Improved |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-I2V-480P · EmoVid benchmark I2V | FVD: 517.9 -> 517.8 | No clear effect |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-I2V-480P · EmoVid benchmark I2V | SD score: 0.7146 -> 0.7193 | No clear effect |
| fine-tune Wan2.1 with LoRA on EmoVid | Wan2.1-I2V-480P · EmoVid benchmark I2V | Flicker: 0.0325 -> 0.0324 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- DynamiCrafter512 — DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors (ECCV 2024) · better on 2 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- $E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset (NeurIPS 2024 · similarity 0.89)
- EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.89)
- VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models (NeurIPS 2025 · similarity 0.88)
- EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025 · similarity 0.88)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.87)
- EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
