Large Scale Holistic Video Understanding

MDMMT: Multidomain Multimodal Transformer for Video Retrieval

Maksim Dzabraev,

Maksim Kalashnikov,

Stepan Komkov,

Aleksandr Petiushko

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dzabraev_2021_CVPR, author = {Dzabraev, Maksim and Kalashnikov, Maksim and Komkov, Stepan and Petiushko, Aleksandr}, title = {MDMMT: Multidomain Multimodal Transformer for Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3354-3363} }

SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction From Video Data

Yuan-Ting Hu,

Jiahong Wang,

Raymond A. Yeh,

Alexander G. Schwing

[pdf] [arXiv]

[bibtex]

@InProceedings{Hu_2021_CVPR, author = {Hu, Yuan-Ting and Wang, Jiahong and Yeh, Raymond A. and Schwing, Alexander G.}, title = {SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction From Video Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3364-3374} }

CoCon: Cooperative-Contrastive Learning

Nishant Rai,

Ehsan Adeli,

Kuan-Hui Lee,

Adrien Gaidon,

Juan Carlos Niebles

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rai_2021_CVPR, author = {Rai, Nishant and Adeli, Ehsan and Lee, Kuan-Hui and Gaidon, Adrien and Niebles, Juan Carlos}, title = {CoCon: Cooperative-Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3384-3393} }

Rethinking Training Data for Mitigating Representation Biases in Action Recognition

Kensho Hara,

Yuchi Ishikawa,

Hirokatsu Kataoka

[pdf]

[bibtex]

@InProceedings{Hara_2021_CVPR, author = {Hara, Kensho and Ishikawa, Yuchi and Kataoka, Hirokatsu}, title = {Rethinking Training Data for Mitigating Representation Biases in Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3349-3353} }

ObjectGraphs: Using Objects and a Graph Convolutional Network for the Bottom-Up Recognition and Explanation of Events in Video

Nikolaos Gkalelis,

Andreas Goulas,

Damianos Galanopoulos,

Vasileios Mezaris

[pdf]

[bibtex]

@InProceedings{Gkalelis_2021_CVPR, author = {Gkalelis, Nikolaos and Goulas, Andreas and Galanopoulos, Damianos and Mezaris, Vasileios}, title = {ObjectGraphs: Using Objects and a Graph Convolutional Network for the Bottom-Up Recognition and Explanation of Events in Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3375-3383} }

IntegralAction: Pose-Driven Feature Integration for Robust Human Action Recognition in Videos

Gyeongsik Moon,

Heeseung Kwon,

Kyoung Mu Lee,

Minsu Cho

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Moon_2021_CVPR, author = {Moon, Gyeongsik and Kwon, Heeseung and Lee, Kyoung Mu and Cho, Minsu}, title = {IntegralAction: Pose-Driven Feature Integration for Robust Human Action Recognition in Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3339-3348} }