Robustness Analysis of Video-Language Models Against Visual and Language PerturbationsDownload PDF

Published: 17 Sept 2022, Last Modified: 23 May 2023NeurIPS 2022 Datasets and Benchmarks Readers: Everyone
Keywords: robustness, multimodal modeling, text-to-video retrieval, benchmark, video-language modeling
TL;DR: Analysis of robustness on video-language models on text-to-video retrieval.
Abstract: Joint visual and language modeling on large-scale datasets has recently shown good progress in multi-modal tasks when compared to single modal learning. However, robustness of these approaches against real-world perturbations has not been studied. In this work, we perform the first extensive robustness study of video-language models against various real-world perturbations. We focus on text-to-video retrieval and propose two large-scale benchmark datasets, MSRVTT-P and YouCook2-P, which utilize 90 different visual and 35 different text perturbations. The study reveals some interesting initial findings from the studied models: 1) models are more robust when text is perturbed versus when video is perturbed, 2) models that are pre-trained are more robust than those trained from scratch, 3) models attend more to scene and objects rather than motion and action. We hope this study will serve as a benchmark and guide future research in robust video-language learning. The benchmark introduced in this study along with the code and datasets is available at
Supplementary Material: zip
Author Statement: Yes
Contribution Process Agreement: Yes
In Person Attendance: Yes
9 Replies