Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
This addresses a specific bias issue in text-video retrieval, which is incremental as it focuses on mitigating a known temporal bias rather than introducing a new paradigm.
The paper tackles the problem of frame length bias in text-video retrieval, where models may rely on spurious correlations due to discrepancies between training and test sets, and proposes a causal debiasing approach that outperforms baseline and state-of-the-art methods on metrics like nDCG across multiple datasets.
Many studies focus on improving pretraining or developing new backbones in text-video retrieval. However, existing methods may suffer from the learning and inference bias issue, as recent research suggests in other text-video-related tasks. For instance, spatial appearance features on action recognition or temporal object co-occurrences on video scene graph generation could induce spurious correlations. In this work, we present a unique and systematic study of a temporal bias due to frame length discrepancy between training and test sets of trimmed video clips, which is the first such attempt for a text-video retrieval task, to the best of our knowledge. We first hypothesise and verify the bias on how it would affect the model illustrated with a baseline study. Then, we propose a causal debiasing approach and perform extensive experiments and ablation studies on the Epic-Kitchens-100, YouCook2, and MSR-VTT datasets. Our model overpasses the baseline and SOTA on nDCG, a semantic-relevancy-focused evaluation metric which proves the bias is mitigated, as well as on the other conventional metrics.