English

UATVR: Uncertainty-Adaptive Text-Video Retrieval

Computer Vision and Pattern Recognition 2023-08-22 v2

Abstract

With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities in specific granularities for semantic correspondence. Unfortunately, the intrinsic uncertainties of optimal entity combinations in appropriate granularities for cross-modal queries are understudied, which is especially critical for modalities with hierarchical semantics, e.g., video, text, etc. In this paper, we propose an Uncertainty-Adaptive Text-Video Retrieval approach, termed UATVR, which models each look-up as a distribution matching procedure. Concretely, we add additional learnable tokens in the encoders to adaptively aggregate multi-grained semantics for flexible high-level reasoning. In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation. Comprehensive experiments on four benchmarks justify the superiority of our UATVR, which achieves new state-of-the-art results on MSR-VTT (50.8%), VATEX (64.5%), MSVD (49.7%), and DiDeMo (45.8%). The code is available at https://github.com/bofang98/UATVR.

Keywords

Cite

@article{arxiv.2301.06309,
  title  = {UATVR: Uncertainty-Adaptive Text-Video Retrieval},
  author = {Bo Fang and Wenhao Wu and Chang Liu and Yu Zhou and Yuxin Song and Weiping Wang and Xiangbo Shu and Xiangyang Ji and Jingdong Wang},
  journal= {arXiv preprint arXiv:2301.06309},
  year   = {2023}
}

Comments

To appear at ICCV2023

R2 v1 2026-06-28T08:12:22.816Z