Abstract
Text-video retrieval (TVR) systems often suffer from visual-linguistic biases present in datasets, which cause pre-trained vision-language models to overlook key details. To address this, we propose BiMa, a novel framework designed to mitigate biases in both visual and textual representations. Our approach begins by generating scene elements that characterize each video by identifying relevant entities/objects and activities. For visual debiasing, we integrate these scene elements into the video embeddings, enhancing them to emphasize fine-grained and salient details. For textual debiasing, we introduce a mechanism to disentangle text features into content and bias components, enabling the model to focus on meaningful content while separately handling biased information. Extensive experiments and ablation studies across five major TVR benchmarks (i.e., MSR-VTT, MSVD, LSMDC, ActivityNet, and DiDeMo) demonstrate the competitive performance of BiMa. Additionally, the model's bias mitigation capability is consistently validated by its strong results on out-of-distribution retrieval tasks.
Abstract (translated)
文本-视频检索（TVR）系统通常会受到数据集中存在的视觉-语言偏见的影响，导致预训练的视觉-语言模型忽视关键细节。为解决这一问题，我们提出了BiMa，这是一个旨在减轻视觉和文本表示中偏差的新颖框架。我们的方法从生成场景元素开始，这些元素通过识别相关的实体/对象和活动来表征每个视频。为了进行视觉去偏，我们将这些场景元素整合到视频嵌入中，增强它们以强调细微的和显著的细节。对于文本去偏，我们引入了一种机制，将文本特征分解为内容和偏差部分，使模型能够在处理有偏信息的同时专注于有意义的内容。 在五个主要的TVR基准测试（即MSR-VTT、MSVD、LSMDC、ActivityNet 和DiDeMo）上进行的广泛实验和消融研究显示了BiMa的竞争性能。此外，该模型通过其在外分布检索任务上的强大结果，持续验证了其减轻偏差的能力。
URL
https://arxiv.org/abs/2506.03589
