Action Scene Graphs for Long-Form Understanding of Egocentric Videos

              @inproceedings{rodin2023action,
  primaryclass = { cs.CV },
  archiveprefix = { arXiv },
  eprint = { 2312.03391 },
  pdf = {https://arxiv.org/pdf/2312.03391.pdf},
  year = {2024},
  booktitle = {  Conference on Computer Vision and Pattern Recognition (CVPR)  },
  title = {Action Scene Graphs for Long-Form Understanding of Egocentric Videos},
  author = {Ivan Rodin and Antonino Furnari and Kyle Min and Subarna Tripathi and Giovanni Maria Farinella}
}