update ego-exo4d

content/publication/Ego-exo4D/cite.bib

@@ -1,6 +1,6 @@
-@article{grauman2023egoexo4d,
+@article{grauman2024egoexo4d,
   title={Ego-Exo4D: Understanding Skilled Human Activity from First-and Third-Person Perspectives},
   author={Grauman, Kristen and Westbury, Andrew and Torresani, Lorenzo and Kitani, Kris and Malik, Jitendra and Afouras, Triantafyllos and Ashutosh, Kumar and Baiyya, Vijay and Bansal, Siddhant and Boote, Bikram and others},
-  journal={arXiv preprint arXiv:2311.18259},
-  year={2023}
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2024}
 }

content/publication/Ego-exo4D/index.md

@@ -2,7 +2,7 @@
 title: "Ego-Exo4D: Understanding Skilled Human Activity from First-and Third-Person Perspectives"
 
 publication_types:
-  - "3"
+  - "1"
 authors:
   - admin
   - with other 100 authors
@@ -91,8 +91,8 @@ authors:
 # - Lorenzo Torresani+
 # - Mingfei Yan+
 # - Jitendra Malik
-publication: arxiv 2023
-publication_short: arxiv 2023
+publication: IEEE Conference on Computer Vision and Pattern Recognition (**CVPR**), 2024
+publication_short: CVPR 2024
 abstract: "We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). More than 800 participants from 13 cities worldwide performed these activities in 131 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,422 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel `expert commentary' done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources will be open sourced to fuel new research in the community."
 draft: false
 featured: false