---
title: "MSVBench — paper by Shi et al. (2026) — summary and ideas"
description: "Video generators increasingly produce story-like videos made of many shots, but most evaluation benchmarks still judge… 48 references."
authors: ["Haoyuan Shi", "Yunxin li", "Nanhao Deng", "Zhenran Xu", "Xinyu Chen", "Longyue Wang", "Baotian Hu", "Min Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1203/"
doi: "10.18653/v1/2026.findings-acl.1203"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/shi-2026-msvbench-human-level-evaluation-multi/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shi-2026-msvbench-human-level-evaluation-multi/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/) / MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation

# MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation

**Authors:** Haoyuan Shi, [Yunxin li](https://md.research.elamur.ai/free/en/authors/yunxin-li/), Nanhao Deng, [Zhenran Xu](https://md.research.elamur.ai/free/en/authors/zhenran-xu/), [Xinyu Chen](https://md.research.elamur.ai/free/en/authors/xinyu-chen/), [Longyue Wang](https://md.research.elamur.ai/free/en/authors/longyue-wang/), [Baotian Hu](https://md.research.elamur.ai/free/en/authors/baotian-hu/) and [Min Zhang](https://md.research.elamur.ai/free/en/authors/min-zhang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1203/) · [PDF](https://aclanthology.org/2026.findings-acl.1203.pdf) · [DOI 10.18653/v1/2026.findings-acl.1203](https://doi.org/10.18653/v1/2026.findings-acl.1203) · [OpenAlex](https://openalex.org/W7166822142)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Video generators increasingly produce story-like videos made of many shots, but most evaluation benchmarks still judge single clips. They lack full scripts, per-shot references and metrics for coherence across shots. MSVBench addresses this gap. It reorganizes 20 stories from ViStoryBench into a three-level structure: global characters and environments, scenes, and annotated shots with reference frames and camera instructions.

Its scoring combines specialized perceptual models (e.g., DOVER, RAFT, SAM-Track) with Gemini-2.5-Flash for semantic judgments. This split is meant to stop image quality problems from skewing semantic scores. The authors test 20 generation systems across commercial, open-source, agent-based and continuous paradigms. Even strong models follow prompts well but lose stability and consistency over long sequences, behaving more like "visual interpolators" than world models.

Benchmark rankings agree closely with human ratings, outperforming earlier benchmarks. The evaluation traces can also train a small evaluator, offering a cheaper substitute for human video assessment.

## Key points
- Resource: 20 stories with 136 character and 276 shot reference images, generated with GPT-Image-1 and Nano Banana. Camera-motion prompts were produced with Gemini-2.5-Flash.
- Metrics: 20 sub-metrics grouped under four dimensions, namely Motion Quality, Video Consistency, Story Video Alignment and Visual Quality.
- Human alignment: overall Spearman ρ = 0.944 and Kendall τ = 0.836. For comparison, ViStoryBench scores 0.836/0.660 and VBench 0.585/0.504.
- Supervision: Qwen3-VL-4B was trained with GRPO for one epoch on 1,000+ samples built from 15 stories. It reaches ρ = 0.836, above Gemini-2.5-Flash (0.792) but below Gemini-2.5-Pro (0.857).
- Limitations: no audio metrics, small story set, and shot-level metrics are hard to apply to continuous generation without clear shot boundaries.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🖥️ Computer Graphics and Computer-Aided Design](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-graphics-and-computer-aided-design/) · 7 works

## Cite

Cite as: Haoyuan Shi, Yunxin li, Nanhao Deng, Zhenran Xu, Xinyu Chen, Longyue Wang, Baotian Hu and Min Zhang. 2026. MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{shi2026msvbench,
  title = {{MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation}},
  author = {Haoyuan Shi, Yunxin li, Nanhao Deng, Zhenran Xu, Xinyu Chen, Longyue Wang, Baotian Hu and Min Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1203},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1203}
}
```

- [← previous mSCoRe: A Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning](https://md.research.elamur.ai/free/en/papers/ngo-2026-mscore-multilingual-scalable-benchmark-skill/)
- [next → MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues](https://md.research.elamur.ai/free/en/papers/pan-2026-mt-video-bench-holistic-video/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/)

## References

48 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Lin Chen, Xilin Wei, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Zhenyu Tang, Li Yuan, and 1 others. 2024. Sharegpt4video: Improving video understanding and generation with better captions. Advances in Neural Information Processing Systems, 37:19472–19495. [find](https://scholar.google.com/scholar?q=Lin+Chen%2C+Xilin+Wei%2C+Jinsong+Li%2C+Xiaoyi+Dong%2C+Pan+Zhang%2C+Yuhang+Zang%2C+Zehui+Chen%2C+Haodong+Duan%2C+Zhenyu+Tang%2C+Li+Yuan%2C+and+1+others%2E+2024%2E+Sharegpt4video%3A+Improving+video+understanding+and+generation+w)
2. Yangming Cheng, Liulei Li, Yuanyou Xu, Xiaodi Li, Zongxin Yang, Wenguan Wang, and Yi Yang. 2023. Segment and track anything. arXiv preprint arXiv:2305.06558. — [arXiv:2305.06558](https://arxiv.org/abs/2305.06558) [find](https://scholar.google.com/scholar?q=Yangming+Cheng%2C+Liulei+Li%2C+Yuanyou+Xu%2C+Xiaodi+Li%2C+Zongxin+Yang%2C+Wenguan+Wang%2C+and+Yi+Yang%2E+2023%2E+Segment+and+track+anything%2E+arXiv+preprint+arXiv%3A2305%2E06558%2E+%E2%80%94+%5BarXiv%3A2305%2E06558%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs)
3. Karan Dalal, Daniel Koceja, Jiarui Xu, Yue Zhao, Shihao Han, Ka Chun Cheung, Jan Kautz, Yejin Choi, Yu Sun, and Xiaolong Wang. 2025. One-minute video generation with test-time training. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 17702–17711. [find](https://scholar.google.com/scholar?q=Karan+Dalal%2C+Daniel+Koceja%2C+Jiarui+Xu%2C+Yue+Zhao%2C+Shihao+Han%2C+Ka+Chun+Cheung%2C+Jan+Kautz%2C+Yejin+Choi%2C+Yu+Sun%2C+and+Xiaolong+Wang%2E+2025%2E+One%2Dminute+video+generation+with+test%2Dtime+training%2E+In+Proceedings)
4. Stephanie Fu, Netanel Tamir, Shobhita Sundaram, Lucy Chai, Richard Zhang, Tali Dekel, and Phillip Isola. 2023. Dreamsim: Learning new dimensions of human visual similarity using synthetic data. arXiv preprint arXiv:2306.09344. — [arXiv:2306.09344](https://arxiv.org/abs/2306.09344) [find](https://scholar.google.com/scholar?q=Stephanie+Fu%2C+Netanel+Tamir%2C+Shobhita+Sundaram%2C+Lucy+Chai%2C+Richard+Zhang%2C+Tali+Dekel%2C+and+Phillip+Isola%2E+2023%2E+Dreamsim%3A+Learning+new+dimensions+of+human+visual+similarity+using+synthetic+data%2E+arXiv+)
5. Google. 2025. Veo 3 launch. [find](https://scholar.google.com/scholar?q=Google%2E+2025%2E+Veo+3+launch%2E)
6. Yoav HaCohen, Nisan Chiprut, Benny Brazowski, Daniel Shalem, Dudu Moshe, Eitan Richardson, Eran Levin, Guy Shiran, Nir Zabari, Ori Gordon, and 1 others. 2024. Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:2501.00103. [find](https://scholar.google.com/scholar?q=Yoav+HaCohen%2C+Nisan+Chiprut%2C+Benny+Brazowski%2C+Daniel+Shalem%2C+Dudu+Moshe%2C+Eitan+Richardson%2C+Eran+Levin%2C+Guy+Shiran%2C+Nir+Zabari%2C+Ori+Gordon%2C+and+1+others%2E+2024%2E+Ltx%2Dvideo%3A+Realtime+video+latent+diffusio)
7. Hui Han, Siyuan Li, Jiaqi Chen, Yiwen Yuan, Yuling Wu, Yufan Deng, Chak Tou Leong, Hanwen Du, Junchen Fu, Youhua Li, and 1 others. 2025. Video-bench: Human-aligned video generation benchmark. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 18858–18868. [find](https://scholar.google.com/scholar?q=Hui+Han%2C+Siyuan+Li%2C+Jiaqi+Chen%2C+Yiwen+Yuan%2C+Yuling+Wu%2C+Yufan+Deng%2C+Chak+Tou+Leong%2C+Hanwen+Du%2C+Junchen+Fu%2C+Youhua+Li%2C+and+1+others%2E+2025%2E+Video%2Dbench%3A+Human%2Daligned+video+generation+benchmark%2E+In+Proce)
8. Kaiyi Huang, Yukun Huang, Xintao Wang, Zinan Lin, Xuefei Ning, Pengfei Wan, Di Zhang, Yu Wang, and Xihui Liu. 2025a. Filmaster: Bridging cinematic principles and generative ai for automated film generation. arXiv preprint arXiv:2506.18899. — [arXiv:2506.18899](https://arxiv.org/abs/2506.18899) [find](https://scholar.google.com/scholar?q=Kaiyi+Huang%2C+Yukun+Huang%2C+Xintao+Wang%2C+Zinan+Lin%2C+Xuefei+Ning%2C+Pengfei+Wan%2C+Di+Zhang%2C+Yu+Wang%2C+and+Xihui+Liu%2E+2025a%2E+Filmaster%3A+Bridging+cinematic+principles+and+generative+ai+for+automated+film+gener)
9. Junjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar, and Feng Yang. 2021. Musiq: Multi-scale image quality transformer. In Proceedings of the IEEE/CVF international conference on computer vision, pages 5148–5157. [find](https://scholar.google.com/scholar?q=Junjie+Ke%2C+Qifei+Wang%2C+Yilin+Wang%2C+Peyman+Milanfar%2C+and+Feng+Yang%2E+2021%2E+Musiq%3A+Multi%2Dscale+image+quality+transformer%2E+In+Proceedings+of+the+IEEE%2FCVF+international+conference+on+computer+vision%2C+pages)
10. Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, and 1 others. 2024. [Hunyuanvideo: A systematic framework for large video generative models](https://md.research.elamur.ai/free/en/papers/kong-2024-hunyuanvideo-systematic-framework-large/). arXiv preprint arXiv:2412.03603.
11. Yunxin Li, Xinyu Chen, Shenyuan Jiang, Haoyuan Shi, Zhenyu Liu, Xuanyu Zhang, Nanhao Deng, Zhenran Xu, Yicheng Ma, Meishan Zhang, and 1 others. 2025a. Uni-moe-2.0-omni: Scaling language-centric omnimodal large model with advanced moe, training and data. arXiv preprint arXiv:2511.12609. — [arXiv:2511.12609](https://arxiv.org/abs/2511.12609) [find](https://scholar.google.com/scholar?q=Yunxin+Li%2C+Xinyu+Chen%2C+Shenyuan+Jiang%2C+Haoyuan+Shi%2C+Zhenyu+Liu%2C+Xuanyu+Zhang%2C+Nanhao+Deng%2C+Zhenran+Xu%2C+Yicheng+Ma%2C+Meishan+Zhang%2C+and+1+others%2E+2025a%2E+Uni%2Dmoe%2D2%2E0%2Domni%3A+Scaling+language%2Dcentric+omnimo)
12. Yunxin Li, Zhenyu Liu, Zitao Li, Xuanyu Zhang, Zhenran Xu, Xinyu Chen, Haoyuan Shi, Shenyuan Jiang, Xintong Wang, Jifang Wang, and 1 others. 2025b. Perception, reason, think, and plan: A survey on large multimodal reasoning models. arXiv preprint arXiv:2505.04921. — [arXiv:2505.04921](https://arxiv.org/abs/2505.04921) [find](https://scholar.google.com/scholar?q=Yunxin+Li%2C+Zhenyu+Liu%2C+Zitao+Li%2C+Xuanyu+Zhang%2C+Zhenran+Xu%2C+Xinyu+Chen%2C+Haoyuan+Shi%2C+Shenyuan+Jiang%2C+Xintong+Wang%2C+Jifang+Wang%2C+and+1+others%2E+2025b%2E+Perception%2C+reason%2C+think%2C+and+plan%3A+A+survey+on+lar)
13. Yunxin Li, Haoyuan Shi, Baotian Hu, Longyue Wang, Jiashun Zhu, Jinyi Xu, Zhen Zhao, and Min Zhang. 2024. Anim-director: A large multimodal model powered agent for controllable animation video generation. In SIGGRAPH Asia 2024 Conference Papers, pages 1–11. [find](https://scholar.google.com/scholar?q=Yunxin+Li%2C+Haoyuan+Shi%2C+Baotian+Hu%2C+Longyue+Wang%2C+Jiashun+Zhu%2C+Jinyi+Xu%2C+Zhen+Zhao%2C+and+Min+Zhang%2E+2024%2E+Anim%2Ddirector%3A+A+large+multimodal+model+powered+agent+for+controllable+animation+video+generati)
14. Zhiqiu Lin, Deepak Pathak, Baiqi Li, Jiayao Li, Xide Xia, Graham Neubig, Pengchuan Zhang, and Deva Ramanan. 2024. Evaluating text-to-visual generation with image-to-text generation. In European Conference on Computer Vision, pages 366–384. Springer. [find](https://scholar.google.com/scholar?q=Zhiqiu+Lin%2C+Deepak+Pathak%2C+Baiqi+Li%2C+Jiayao+Li%2C+Xide+Xia%2C+Graham+Neubig%2C+Pengchuan+Zhang%2C+and+Deva+Ramanan%2E+2024%2E+Evaluating+text%2Dto%2Dvisual+generation+with+image%2Dto%2Dtext+generation%2E+In+European+Confer)
15. Chang Liu, Haoning Wu, Yujie Zhong, Xiaoyun Zhang, Yanfeng Wang, and Weidi Xie. 2024a. Intelligent grimm-open-ended visual storytelling via latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6190–6200. [find](https://scholar.google.com/scholar?q=Chang+Liu%2C+Haoning+Wu%2C+Yujie+Zhong%2C+Xiaoyun+Zhang%2C+Yanfeng+Wang%2C+and+Weidi+Xie%2E+2024a%2E+Intelligent+grimm%2Dopen%2Dended+visual+storytelling+via+latent+diffusion+models%2E+In+Proceedings+of+the+IEEE%2FCVF+Conf)
16. Xun Huang, Zhengqi Li, Guande He, Mingyuan Zhou, and Eli Shechtman. 2025b. Self forcing: Bridging the train-test gap in autoregressive video diffusion. arXiv preprint arXiv:2506.08009. [find](https://scholar.google.com/scholar?q=Xun+Huang%2C+Zhengqi+Li%2C+Guande+He%2C+Mingyuan+Zhou%2C+and+Eli+Shechtman%2E+2025b%2E+Self+forcing%3A+Bridging+the+train%2Dtest+gap+in+autoregressive+video+diffusion%2E+arXiv+preprint+arXiv%3A2506%2E08009%2E)
17. Kunhao Liu, Wenbo Hu, Jiale Xu, Ying Shan, and Shijian Lu. 2025a. Rolling forcing: Autoregressive long video diffusion in real time. arXiv preprint arXiv:2509.25161. [find](https://scholar.google.com/scholar?q=Kunhao+Liu%2C+Wenbo+Hu%2C+Jiale+Xu%2C+Ying+Shan%2C+and+Shijian+Lu%2E+2025a%2E+Rolling+forcing%3A+Autoregressive+long+video+diffusion+in+real+time%2E+arXiv+preprint+arXiv%3A2509%2E25161%2E)
18. Ziqi Huang, Yinan He, Jiashuo Yu, Fan Zhang, Chenyang Si, Yuming Jiang, Yuanhan Zhang, Tianxing Wu, Qingyang Jin, Nattapol Chanpaisit, and 1 others. 2024. Vbench: Comprehensive benchmark suite for video generative models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog… [find](https://scholar.google.com/scholar?q=Ziqi+Huang%2C+Yinan+He%2C+Jiashuo+Yu%2C+Fan+Zhang%2C+Chenyang+Si%2C+Yuming+Jiang%2C+Yuanhan+Zhang%2C+Tianxing+Wu%2C+Qingyang+Jin%2C+Nattapol+Chanpaisit%2C+and+1+others%2E+2024%2E+Vbench%3A+Comprehensive+benchmark+suite+for+vid)
19. Shiyu Liu, Yucheng Han, Peng Xing, Fukun Yin, Rui Wang, Wei Cheng, Jiaqi Liao, Yingming Wang, Honghao Fu, Chunrui Han, and 1 others. 2025b. [Step1x-edit: A practical framework for general image editing](https://md.research.elamur.ai/free/en/papers/liu-2025-step1x-edit-practical-framework/). arXiv preprint arXiv:2504.17761.
20. Yudong Jiang, Baohan Xu, Siqian Yang, Mingyu Yin, Jing Liu, Chao Xu, Siqi Wang, Yidi Wu, Bingwen Zhu, Xinwen Zhang, and 1 others. 2024. Anisora: Exploring the frontiers of animation video generation in the sora era. arXiv preprint arXiv:2412.10255. — [arXiv:2412.10255](https://arxiv.org/abs/2412.10255) [find](https://scholar.google.com/scholar?q=Yudong+Jiang%2C+Baohan+Xu%2C+Siqian+Yang%2C+Mingyu+Yin%2C+Jing+Liu%2C+Chao+Xu%2C+Siqi+Wang%2C+Yidi+Wu%2C+Bingwen+Zhu%2C+Xinwen+Zhang%2C+and+1+others%2E+2024%2E+Anisora%3A+Exploring+the+frontiers+of+animation+video+generation+i)
21. Yaofang Liu, Xiaodong Cun, Xuebo Liu, Xintao Wang, Yong Zhang, Haoxin Chen, Yang Liu, Tieyong Zeng, Raymond Chan, and Ying Shan. 2024b. Evalcrafter: Benchmarking and evaluating large video generation models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages… [find](https://scholar.google.com/scholar?q=Yaofang+Liu%2C+Xiaodong+Cun%2C+Xuebo+Liu%2C+Xintao+Wang%2C+Yong+Zhang%2C+Haoxin+Chen%2C+Yang+Liu%2C+Tieyong+Zeng%2C+Raymond+Chan%2C+and+Ying+Shan%2E+2024b%2E+Evalcrafter%3A+Benchmarking+and+evaluating+large+video+generation+)
22. Jiawei Mao, Xiaoke Huang, Yunfei Xie, Yuanqi Chang, Mude Hui, Bingjie Xu, and Yuyin Zhou. 2024. Story-adapter: A training-free iterative framework for long story visualization. arXiv preprint arXiv:2410.06244. — [arXiv:2410.06244](https://arxiv.org/abs/2410.06244) [find](https://scholar.google.com/scholar?q=Jiawei+Mao%2C+Xiaoke+Huang%2C+Yunfei+Xie%2C+Yuanqi+Chang%2C+Mude+Hui%2C+Bingjie+Xu%2C+and+Yuyin+Zhou%2E+2024%2E+Story%2Dadapter%3A+A+training%2Dfree+iterative+framework+for+long+story+visualization%2E+arXiv+preprint+arXiv%3A24)
23. Yihao Meng, Hao Ouyang, Yue Yu, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Hanlin Wang, Yixuan Li, Cheng Chen, Yanhong Zeng, and 1 others. 2025. Holocine: Holistic generation of cinematic multi-shot long video narratives. arXiv preprint arXiv:2510.20822. — [arXiv:2510.20822](https://arxiv.org/abs/2510.20822) [find](https://scholar.google.com/scholar?q=Yihao+Meng%2C+Hao+Ouyang%2C+Yue+Yu%2C+Qiuyu+Wang%2C+Wen+Wang%2C+Ka+Leong+Cheng%2C+Hanlin+Wang%2C+Yixuan+Li%2C+Cheng+Chen%2C+Yanhong+Zeng%2C+and+1+others%2E+2025%2E+Holocine%3A+Holistic+generation+of+cinematic+multi%2Dshot+long+v)
24. Martinus Grady Naftali, Jason Sebastian Sulistyawan, and Kelvin Julian. 2022. Aniwho: A quick and accurate way to classify anime character faces in images. arXiv preprint arXiv:2208.11012. — [arXiv:2208.11012](https://arxiv.org/abs/2208.11012) [find](https://scholar.google.com/scholar?q=Martinus+Grady+Naftali%2C+Jason+Sebastian+Sulistyawan%2C+and+Kelvin+Julian%2E+2022%2E+Aniwho%3A+A+quick+and+accurate+way+to+classify+anime+character+faces+in+images%2E+arXiv+preprint+arXiv%3A2208%2E11012%2E+%E2%80%94+%5BarXiv%3A22)
25. OpenAI. 2024. Sora: Creating video from text. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Sora%3A+Creating+video+from+text%2E)
26. Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Dollár, and Christoph Feichtenhofer. 2024. Sam 2: Segm… [find](https://scholar.google.com/scholar?q=Nikhila+Ravi%2C+Valentin+Gabeur%2C+Yuan%2DTing+Hu%2C+Ronghang+Hu%2C+Chaitanya+Ryali%2C+Tengyu+Ma%2C+Haitham+Khedr%2C+Roman+R%C3%A4dle%2C+Chloe+Rolland%2C+Laura+Gustafson%2C+Eric+Mintun%2C+Junting+Pan%2C+Kalyan+Vasudev+Alwala%2C+Nicol)
27. Haoyuan Shi, Yunxin Li, Xinyu Chen, Longyue Wang, Baotian Hu, and Min Zhang. 2025. Animaker: Automated multi-agent animated storytelling with mcts-driven clip generation. arXiv preprint arXiv:2506.10540. — [arXiv:2506.10540](https://arxiv.org/abs/2506.10540) [find](https://scholar.google.com/scholar?q=Haoyuan+Shi%2C+Yunxin+Li%2C+Xinyu+Chen%2C+Longyue+Wang%2C+Baotian+Hu%2C+and+Min+Zhang%2E+2025%2E+Animaker%3A+Automated+multi%2Dagent+animated+storytelling+with+mcts%2Ddriven+clip+generation%2E+arXiv+preprint+arXiv%3A2506%2E105)
28. Gowthami Somepalli, Anubhav Gupta, Kamal Gupta, Shramay Palta, Micah Goldblum, Jonas Geiping, Abhinav Shrivastava, and Tom Goldstein. 2024. Measuring style similarity in diffusion models. arXiv preprint arXiv:2404.01292. splcher. 2019. Anime Face Dataset. — [arXiv:2404.01292](https://arxiv.org/abs/2404.01292) [find](https://scholar.google.com/scholar?q=Gowthami+Somepalli%2C+Anubhav+Gupta%2C+Kamal+Gupta%2C+Shramay+Palta%2C+Micah+Goldblum%2C+Jonas+Geiping%2C+Abhinav+Shrivastava%2C+and+Tom+Goldstein%2E+2024%2E+Measuring+style+similarity+in+diffusion+models%2E+arXiv+prepri)
29. Yaniv Taigman, Ming Yang, Marc’Aurelio Ranzato, and Lior Wolf. 2014. Deepface: Closing the gap to human-level performance in face verification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1701–1708. [find](https://scholar.google.com/scholar?q=Yaniv+Taigman%2C+Ming+Yang%2C+Marc%E2%80%99Aurelio+Ranzato%2C+and+Lior+Wolf%2E+2014%2E+Deepface%3A+Closing+the+gap+to+human%2Dlevel+performance+in+face+verification%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision)
30. Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In European conference on computer vision, pages 402–419. Springer. [find](https://scholar.google.com/scholar?q=Zachary+Teed+and+Jia+Deng%2E+2020%2E+Raft%3A+Recurrent+all%2Dpairs+field+transforms+for+optical+flow%2E+In+European+conference+on+computer+vision%2C+pages+402%E2%80%93419%2E+Springer%2E)
31. Team Wan, Ang Wang, Baole Ai, Bin Wen, Chaojie Mao, Chen-Wei Xie, Di Chen, Feiwu Yu, Haiming Zhao, Jianxiao Yang, and 1 others. 2025. Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314. [find](https://scholar.google.com/scholar?q=Team+Wan%2C+Ang+Wang%2C+Baole+Ai%2C+Bin+Wen%2C+Chaojie+Mao%2C+Chen%2DWei+Xie%2C+Di+Chen%2C+Feiwu+Yu%2C+Haiming+Zhao%2C+Jianxiao+Yang%2C+and+1+others%2E+2025%2E+Wan%3A+Open+and+advanced+large%2Dscale+video+generative+models%2E+arXiv+)
32. Limin Wang, Bingkun Huang, Zhiyu Zhao, Zhan Tong, Yinan He, Yi Wang, Yali Wang, and Yu Qiao. 2023. Videomae v2: Scaling video masked autoencoders with dual masking. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14549–14560. [find](https://scholar.google.com/scholar?q=Limin+Wang%2C+Bingkun+Huang%2C+Zhiyu+Zhao%2C+Zhan+Tong%2C+Yinan+He%2C+Yi+Wang%2C+Yali+Wang%2C+and+Yu+Qiao%2E+2023%2E+Videomae+v2%3A+Scaling+video+masked+autoencoders+with+dual+masking%2E+In+Proceedings+of+the+IEEE%2FCVF+conf)
33. Haoning Wu, Erli Zhang, Liang Liao, Chaofeng Chen, Jingwen Hou Hou, Annan Wang, Wenxiu Sun Sun, Qiong Yan, and Weisi Lin. 2023. Exploring video quality assessment on user generated contents from aesthetic and technical perspectives. In International Conference on Computer Vision (ICCV). [find](https://scholar.google.com/scholar?q=Haoning+Wu%2C+Erli+Zhang%2C+Liang+Liao%2C+Chaofeng+Chen%2C+Jingwen+Hou+Hou%2C+Annan+Wang%2C+Wenxiu+Sun+Sun%2C+Qiong+Yan%2C+and+Weisi+Lin%2E+2023%2E+Exploring+video+quality+assessment+on+user+generated+contents+from+aesth)
34. Weijia Wu, Zeyu Zhu, and Mike Zheng Shou. 2025. Automated movie generation via multi-agent cot planning. arXiv preprint arXiv:2503.07314. — [arXiv:2503.07314](https://arxiv.org/abs/2503.07314) [find](https://scholar.google.com/scholar?q=Weijia+Wu%2C+Zeyu+Zhu%2C+and+Mike+Zheng+Shou%2E+2025%2E+Automated+movie+generation+via+multi%2Dagent+cot+planning%2E+arXiv+preprint+arXiv%3A2503%2E07314%2E+%E2%80%94+%5BarXiv%3A2503%2E07314%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503%2E07314%29)
35. Zhangyang Xiong, Chenghong Li, Kenkun Liu, Hongjie Liao, Jianqiao Hu, Junyi Zhu, Shuliang Ning, Lingteng Qiu, Chongjie Wang, Shijie Wang, and 1 others. 2024. Mvhumannet: A large-scale dataset of multi-view daily dressing human captures. In Proceedings of the IEEE/CVF Conference on Computer Vision an… [find](https://scholar.google.com/scholar?q=Zhangyang+Xiong%2C+Chenghong+Li%2C+Kenkun+Liu%2C+Hongjie+Liao%2C+Jianqiao+Hu%2C+Junyi+Zhu%2C+Shuliang+Ning%2C+Lingteng+Qiu%2C+Chongjie+Wang%2C+Shijie+Wang%2C+and+1+others%2E+2024%2E+Mvhumannet%3A+A+large%2Dscale+dataset+of+multi)
36. Xuenan Xu, Jiahao Mei, Chenliang Li, Yuning Wu, Ming Yan, Shaopeng Lai, Ji Zhang, and Mengyue Wu. 2025a. Mm-storyagent: Immersive narrated storybook video generation with a multi-agent paradigm across text, image and audio. arXiv preprint arXiv:2503.05242. — [arXiv:2503.05242](https://arxiv.org/abs/2503.05242) [find](https://scholar.google.com/scholar?q=Xuenan+Xu%2C+Jiahao+Mei%2C+Chenliang+Li%2C+Yuning+Wu%2C+Ming+Yan%2C+Shaopeng+Lai%2C+Ji+Zhang%2C+and+Mengyue+Wu%2E+2025a%2E+Mm%2Dstoryagent%3A+Immersive+narrated+storybook+video+generation+with+a+multi%2Dagent+paradigm+across)
37. Zhenran Xu, Longyue Wang, Jifang Wang, Zhouyi Li, Senbao Shi, Xue Yang, Yiyu Wang, Baotian Hu, Jun Yu, and Min Zhang. 2025b. Filmagent: A multi-agent framework for end-to-end film automation in virtual 3d spaces. arXiv preprint arXiv:2501.12909. — [arXiv:2501.12909](https://arxiv.org/abs/2501.12909) [find](https://scholar.google.com/scholar?q=Zhenran+Xu%2C+Longyue+Wang%2C+Jifang+Wang%2C+Zhouyi+Li%2C+Senbao+Shi%2C+Xue+Yang%2C+Yiyu+Wang%2C+Baotian+Hu%2C+Jun+Yu%2C+and+Min+Zhang%2E+2025b%2E+Filmagent%3A+A+multi%2Dagent+framework+for+end%2Dto%2Dend+film+automation+in+virtua)
38. Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, and 1 others. 2025. Longlive: Real-time interactive long video generation. arXiv preprint arXiv:2509.22622. [find](https://scholar.google.com/scholar?q=Shuai+Yang%2C+Wei+Huang%2C+Ruihang+Chu%2C+Yicheng+Xiao%2C+Yuyang+Zhao%2C+Xianbang+Wang%2C+Muyang+Li%2C+Enze+Xie%2C+Yingcong+Chen%2C+Yao+Lu%2C+and+1+others%2E+2025%2E+Longlive%3A+Real%2Dtime+interactive+long+video+generation%2E+arX)
39. Xianghui Yang, Huiwen Shi, Bowen Zhang, Fan Yang, Jiacheng Wang, Hongxu Zhao, Xinhai Liu, Xinzhou Wang, Qingxiang Lin, Jiaao Yu, and 1 others. 2024a. Hunyuan3d 1.0: A unified framework for text-to-3d and image-to-3d generation. arXiv preprint arXiv:2411.02293. — [arXiv:2411.02293](https://arxiv.org/abs/2411.02293) [find](https://scholar.google.com/scholar?q=Xianghui+Yang%2C+Huiwen+Shi%2C+Bowen+Zhang%2C+Fan+Yang%2C+Jiacheng+Wang%2C+Hongxu+Zhao%2C+Xinhai+Liu%2C+Xinzhou+Wang%2C+Qingxiang+Lin%2C+Jiaao+Yu%2C+and+1+others%2E+2024a%2E+Hunyuan3d+1%2E0%3A+A+unified+framework+for+text%2Dto%2D3d+)
40. Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, and 1 others. 2024b. [Cogvideox: Text-to-video diffusion models with an expert transformer](https://md.research.elamur.ai/free/en/papers/yang-2024-cogvideox-text-video-diffusion/). arXiv preprint arXiv:2408.06072.
41. Weihao Yu, Pan Zhou, Shuicheng Yan, and Xinchao Wang. 2024. Inceptionnext: When inception meets convnext. In Proceedings of the IEEE/cvf conference on computer vision and pattern recognition, pages 5672–5683. [find](https://scholar.google.com/scholar?q=Weihao+Yu%2C+Pan+Zhou%2C+Shuicheng+Yan%2C+and+Xinchao+Wang%2E+2024%2E+Inceptionnext%3A+When+inception+meets+convnext%2E+In+Proceedings+of+the+IEEE%2Fcvf+conference+on+computer+vision+and+pattern+recognition%2C+pages+56)
42. Shenghai Yuan, Xianyi He, Yufan Deng, Yang Ye, Jinfa Huang, Bin Lin, Jiebo Luo, and Li Yuan. 2025. Opens2v-nexus: A detailed benchmark and million-scale dataset for subject-to-video generation. arXiv preprint arXiv:2505.20292. — [arXiv:2505.20292](https://arxiv.org/abs/2505.20292) [find](https://scholar.google.com/scholar?q=Shenghai+Yuan%2C+Xianyi+He%2C+Yufan+Deng%2C+Yang+Ye%2C+Jinfa+Huang%2C+Bin+Lin%2C+Jiebo+Luo%2C+and+Li+Yuan%2E+2025%2E+Opens2v%2Dnexus%3A+A+detailed+benchmark+and+million%2Dscale+dataset+for+subject%2Dto%2Dvideo+generation%2E+arXiv+)
43. Junyi Zhang, Charles Herrmann, Junhwa Hur, Varun Jampani, Trevor Darrell, Forrester Cole, Deqing Sun, and Ming-Hsuan Yang. 2024. Monst3r: A simple approach for estimating geometry in the presence of motion. arXiv preprint arXiv:2410.03825. [find](https://scholar.google.com/scholar?q=Junyi+Zhang%2C+Charles+Herrmann%2C+Junhwa+Hur%2C+Varun+Jampani%2C+Trevor+Darrell%2C+Forrester+Cole%2C+Deqing+Sun%2C+and+Ming%2DHsuan+Yang%2E+2024%2E+Monst3r%3A+A+simple+approach+for+estimating+geometry+in+the+presence+of+m)
44. Xinping Zhao, Xinshuo Hu, Zifei Shan, Shouzheng Huang, Yao Zhou, Xin Zhang, Zetian Sun, Zhenyu Liu, Dongfang Li, Xinyuan Wei, and 1 others. 2025. Kalm-embedding-v2: Superior training techniques and data inspire a versatile embedding model. arXiv preprint arXiv:2506.20923. — [arXiv:2506.20923](https://arxiv.org/abs/2506.20923) [find](https://scholar.google.com/scholar?q=Xinping+Zhao%2C+Xinshuo+Hu%2C+Zifei+Shan%2C+Shouzheng+Huang%2C+Yao+Zhou%2C+Xin+Zhang%2C+Zetian+Sun%2C+Zhenyu+Liu%2C+Dongfang+Li%2C+Xinyuan+Wei%2C+and+1+others%2E+2025%2E+Kalm%2Dembedding%2Dv2%3A+Superior+training+techniques+and+da)
45. Mingzhe Zheng, Yongqi Xu, Haojian Huang, Xuran Ma, Yexin Liu, Wenjie Shu, Yatian Pang, Feilong Tang, Qifeng Chen, Harry Yang, and 1 others. 2024. Videogen-of-thought: A collaborative framework for multi-shot video generation. arXiv e-prints, pages arXiv–2412. [find](https://scholar.google.com/scholar?q=Mingzhe+Zheng%2C+Yongqi+Xu%2C+Haojian+Huang%2C+Xuran+Ma%2C+Yexin+Liu%2C+Wenjie+Shu%2C+Yatian+Pang%2C+Feilong+Tang%2C+Qifeng+Chen%2C+Harry+Yang%2C+and+1+others%2E+2024%2E+Videogen%2Dof%2Dthought%3A+A+collaborative+framework+for+mul)
46. Yi Zheng, Yifan Zhao, Mengyuan Ren, He Yan, Xiangju Lu, Junhui Liu, and Jia Li. 2020. Cartoon face recognition: A benchmark dataset. In Proceedings of the 28th ACM international conference on multimedia, pages 2264–2272. [find](https://scholar.google.com/scholar?q=Yi+Zheng%2C+Yifan+Zhao%2C+Mengyuan+Ren%2C+He+Yan%2C+Xiangju+Lu%2C+Junhui+Liu%2C+and+Jia+Li%2E+2020%2E+Cartoon+face+recognition%3A+A+benchmark+dataset%2E+In+Proceedings+of+the+28th+ACM+international+conference+on+multimed)
47. Yupeng Zhou, Daquan Zhou, Ming-Ming Cheng, Jiashi Feng, and Qibin Hou. 2024. Storydiffusion: Consistent self-attention for long-range image and video generation. Advances in Neural Information Processing Systems, 37:110315–110340. [find](https://scholar.google.com/scholar?q=Yupeng+Zhou%2C+Daquan+Zhou%2C+Ming%2DMing+Cheng%2C+Jiashi+Feng%2C+and+Qibin+Hou%2E+2024%2E+Storydiffusion%3A+Consistent+self%2Dattention+for+long%2Drange+image+and+video+generation%2E+Advances+in+Neural+Information+Process)
48. Cailin Zhuang, Ailin Huang, Wei Cheng, Jingwei Wu, Yaoqi Hu, Jiaqi Liao, Hongyuan Wang, Xinyao Liao, Weiwei Cai, Hengyuan Xu, and 1 others. 2025. Vistorybench: Comprehensive benchmark suite for story visualization. arXiv preprint arXiv:2505.24862. — [arXiv:2505.24862](https://arxiv.org/abs/2505.24862) [find](https://scholar.google.com/scholar?q=Cailin+Zhuang%2C+Ailin+Huang%2C+Wei+Cheng%2C+Jingwei+Wu%2C+Yaoqi+Hu%2C+Jiaqi+Liao%2C+Hongyuan+Wang%2C+Xinyao+Liao%2C+Weiwei+Cai%2C+Hengyuan+Xu%2C+and+1+others%2E+2025%2E+Vistorybench%3A+Comprehensive+benchmark+suite+for+story+)

*Updated 1 November 2026*