CVPR 2026 Open Access Repository

Workshop on Any-to-any Multimodal Learning

Neural Surface Reconstruction from Sparse Views Using Epipolar Geometry: Xinhai Chang,

Kaichen Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Chang_2026_CVPR, author = {Chang, Xinhai and Zhou, Kaichen}, title = {Neural Surface Reconstruction from Sparse Views Using Epipolar Geometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {7607-7617} }
VeRVE: Versatile Retrieval for Videos via Unified Embeddings: Shaunak Halbe,

Bhagyashree Puranik,

Jayakrishnan Unnikrishnan,

Kushan Thakkar,

Vimal Bhat,

Toufiq Parag; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Halbe_2026_CVPR, author = {Halbe, Shaunak and Puranik, Bhagyashree and Unnikrishnan, Jayakrishnan and Thakkar, Kushan and Bhat, Vimal and Parag, Toufiq}, title = {VeRVE: Versatile Retrieval for Videos via Unified Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {7624-7633} }
On The Application of Linear Attention in Multimodal Transformers: Armin Gerami,

Seyedehanita Madani,

Ramani Duraiswami; [pdf] [arXiv]
[bibtex]
@InProceedings{Gerami_2026_CVPR, author = {Gerami, Armin and Madani, Seyedehanita and Duraiswami, Ramani}, title = {On The Application of Linear Attention in Multimodal Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {7618-7623} }
Purify-then-Align: Towards Robust Human Sensing under Modality Missing with Knowledge Distillation from Noisy Multimodal Teacher: Pengcheng Weng,

Yanyu Qian,

Yangxin Xu,

Fei Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Weng_2026_CVPR, author = {Weng, Pengcheng and Qian, Yanyu and Xu, Yangxin and Wang, Fei}, title = {Purify-then-Align: Towards Robust Human Sensing under Modality Missing with Knowledge Distillation from Noisy Multimodal Teacher}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {7634-7643} }
Beyond Vision: Holistic World Models: Qianwen Yang,

Yanni Kang,

Guangkai Ren,

Qingwen Yang,

Nan Li; [pdf]
[bibtex]
@InProceedings{Yang_2026_CVPR, author = {Yang, Qianwen and Kang, Yanni and Ren, Guangkai and Yang, Qingwen and Li, Nan}, title = {Beyond Vision: Holistic World Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {7654-7662} }
CODA-Mask: Contrastive and Adaptive Mask Aware Open-set Semantic Segmentation: Keying Zhang,

Jiguang Zhao; [pdf]
[bibtex]
@InProceedings{Zhang_2026_CVPR, author = {Zhang, Keying and Zhao, Jiguang}, title = {CODA-Mask: Contrastive and Adaptive Mask Aware Open-set Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {7663-7672} }
Multimodal ELBO with Diffusion Decoders: Daniel Wesego,

Pedram Rooshenas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wesego_2026_CVPR, author = {Wesego, Daniel and Rooshenas, Pedram}, title = {Multimodal ELBO with Diffusion Decoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {7644-7653} }