VideoAds for Fast-Paced Video Understanding: Where Opensource Foundation Models Beat GPT-4o & Gemini-1.5 Pro. Zhang, Z., Dou, M., Peng, L., Pan, H., Bagci, U., & Gong, B. CoRR, 2025.
VideoAds for Fast-Paced Video Understanding: Where Opensource Foundation Models Beat GPT-4o & Gemini-1.5 Pro [link]Paper  doi  bibtex   
@article{DBLP:journals/corr/abs-2504-09282,
  author       = {Zheyuan Zhang and
                  Monica Dou and
                  Linkai Peng and
                  Hongyi Pan and
                  Ulas Bagci and
                  Boqing Gong},
  title        = {VideoAds for Fast-Paced Video Understanding: Where Opensource Foundation
                  Models Beat GPT-4o {\&} Gemini-1.5 Pro},
  journal      = {CoRR},
  volume       = {abs/2504.09282},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2504.09282},
  doi          = {10.48550/ARXIV.2504.09282},
  eprinttype    = {arXiv},
  eprint       = {2504.09282},
  timestamp    = {Wed, 21 May 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2504-09282.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 0