The 4th DataCV Workshop and Challenge

Synthetic Hands Meet Legacy Data: A Synthetic Dataset for Structured, Controllable, and Multimodal Evaluation

Menghe Zhang,

Haley M. So,

Mohammad Asadi,

Dongfang Zhao,

Yangwen Liang,

Shuangquan Wang,

Gordon Wetzstein,

Kee-Bong Song,

Donghoon Kim

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2025_ICCV, author = {Zhang, Menghe and So, Haley M. and Asadi, Mohammad and Zhao, Dongfang and Liang, Yangwen and Wang, Shuangquan and Wetzstein, Gordon and Song, Kee-Bong and Kim, Donghoon}, title = {Synthetic Hands Meet Legacy Data: A Synthetic Dataset for Structured, Controllable, and Multimodal Evaluation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {466-477} }

Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark

Yaron Aloni,

Rotem Shalev-Arkushin,

Yonatan Shafir,

Guy Tevet,

Ohad Fried,

Amit Haim Bermano

[pdf]

[bibtex]

@InProceedings{Aloni_2025_ICCV, author = {Aloni, Yaron and Shalev-Arkushin, Rotem and Shafir, Yonatan and Tevet, Guy and Fried, Ohad and Bermano, Amit Haim}, title = {Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {496-505} }

Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations

Sparsh Garg,

Abhishek Aich

[pdf] [arXiv]

[bibtex]

@InProceedings{Garg_2025_ICCV, author = {Garg, Sparsh and Aich, Abhishek}, title = {Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {513-520} }

LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning

Kaihong Wang,

Donghyun Kim,

Margrit Betke

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2025_ICCV, author = {Wang, Kaihong and Kim, Donghyun and Betke, Margrit}, title = {LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {456-465} }

Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation

Feiran Li,

Qianqian Xu,

Shilong Bao,

Boyu Han,

Zhiyong Yang,

Qingming Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2025_ICCV, author = {Li, Feiran and Xu, Qianqian and Bao, Shilong and Han, Boyu and Yang, Zhiyong and Huang, Qingming}, title = {Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {506-512} }

Enhancing Domain Diversity in Synthetic Data Face Recognition with Dataset Fusion

Anjith George,

Sébastien Marcel

[pdf] [arXiv]

[bibtex]

@InProceedings{George_2025_ICCV, author = {George, Anjith and Marcel, S\'ebastien}, title = {Enhancing Domain Diversity in Synthetic Data Face Recognition with Dataset Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {489-495} }

On the Generalization of Optical Flow: Quantifying Robustness to Dataset Shifts

Katrin Bauer,

Andres Bruhn,

Jenny Schmalfuss

[pdf] [supp]

[bibtex]

@InProceedings{Bauer_2025_ICCV, author = {Bauer, Katrin and Bruhn, Andres and Schmalfuss, Jenny}, title = {On the Generalization of Optical Flow: Quantifying Robustness to Dataset Shifts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {478-488} }