What makes a video task uniquely suited for videos, beyond what can be understood from a single image? Building on recent progress in self-supervised image-language models, we revisit this question in the context of video and language tasks. We propose the atemporal probe (ATP), a new model for video-language analysis which provides a stronger bound on the baseline accuracy of multimodal models constrained by image-level understanding. By applying this model to standard discriminative video and language tasks, such as video question answering and text-to-video retrieval, we characterize the limitations and potential of current video-language benchmarks. We find that understanding of event temporality is often not necessary to achieve strong or state-of-the-art performance, even compared with recent large-scale video-language models and in contexts intended to benchmark deeper video-level understanding. We also demonstrate how ATP can improve both video-language dataset and model design. We describe a technique for leveraging ATP to better disentangle dataset subsets with a higher concentration of temporally challenging data, improving benchmarking efficacy for causal and temporal understanding. Further, we show that effectively integrating ATP into full video-level temporal models can improve efficiency and state-of-the-art accuracy.

pull figure

Video Overview

(see our CVPR 2022 poster [here])


  title={ {Revisiting the ``Video'' in Video-Language Understanding} },
  author={Shyamal Buch and Cristobal Eyzaguirre and Adrien Gaidon and Jiajun Wu and Li Fei-Fei and Juan Carlos Niebles},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

Funding Acknowledgements

The work is in part supported by Toyota Research Institute (TRI), the Stanford Institute for Human-Centered AI (HAI), Samsung, and Salesforce. The authors also acknowledge fellowship support. Please refer to the paper for full acknowledgements, thank you!