|
| Reduce the influence of implicit bias by adding static image (background). |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Reduce the influence of implicit bias by adding static image (background). |
| 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 will be released at \url{this https URL}. |
 |
| Visualization about fine-grained word alignment. |
 |
Alex Jinpeng Wang, Yixiao Ge, Guanyu Cai, Rui Yan, Xudong Lin, Ying Shan, Xiaohu Qie, Mike Zheng Shou. Object-aware Video-language Pre-training for Retrieval. In CVPR, 2022. (hosted on ArXiv) |
Acknowledgements |