Object-Aware Video-Language Pre-Training for Retrieval

Jinpeng Wang, Yixiao Ge, Guanyu Cai, Rui Yan, Xudong Lin, Ying Shan, Xiaohu Qie, Mike Zheng Shou; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 3313-3322


Recently, by introducing large-scale dataset and strong transformer network, video-language pre-training has shown great success especially for retrieval. Yet, existing video-language transformer models do not explicitly fine-grained semantic align. In this work, we present Object-aware Transformers, an object-centric approach that extends video-language transformer to incorporate object representations. The key idea is to leverage the bounding boxes and object tags to guide the training process. We evaluate our model on three standard sub-tasks of video-text matching on four widely used benchmarks. We also provide deep analysis and detailed ablation about the proposed method. We show clear improvement in performance across all tasks and datasets considered, demonstrating the value of a model that incorporates object representations into a video-language architecture. The code has been released in https://github.com/FingerRec/OA-Transformer.

Related Material

[pdf] [arXiv]
@InProceedings{Wang_2022_CVPR, author = {Wang, Jinpeng and Ge, Yixiao and Cai, Guanyu and Yan, Rui and Lin, Xudong and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng}, title = {Object-Aware Video-Language Pre-Training for Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3313-3322} }