Object-aware Video-language Pre-training for Retrieval
By Alex Wang, Yixiao Ge, Guanyu Cai, Rui Yan, Xudong Lin, Ying Shan, Xiaohu Qie, Mike Zheng Shou. 2021
90 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, Multimodal Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Cordelia Schmid
- Andrew Zisserman
- Ivan Laptev
- Josef Sivic
- Arsha Nagrani
- Dima Damen
- Antoine Miech
- Bernard Ghanem
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Cordelia Schmid
- Andrew Zisserman
- Jitendra Malik
- Trevor Darrell
- Dacheng Tao
- Kristen Grauman
- Andrea Vedaldi
In Information Retrieval & Search
- Josef Sivic
- Ivan Laptev
- Cordelia Schmid
- Antoine Miech
- Kevin Qinghong Lin
- Rui Yan
- Alex Wang
- Michael Wray
In Multimodal Learning
- Cordelia Schmid
- Arsha Nagrani
- Josef Sivic
- Ivan Laptev
- Paul Hongsuck Seo
- Antoine Miech
- Alex Wang
- Dima Damen
Citations in the corpus
- Egocentric Video-Language Pretraining (2022, methodology): “Conversely, methods like [3, 26] exploit dual encoders to independently project the video and text inputs into a common space and minimize the distance between the paired representations.”
- Pre-training image-language transformers for open-vocabulary tasks (2022, methodology): “Rather than using large image-text data [5,10] or pre-trained object detectors [7, 8, 16], we use image-text tasks generated from image or box level labels.”
- Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning (2023, background): “[98] Jinpeng Wang, Yixiao Ge, Guanyu Cai, Rui Yan, Xudong Lin, Ying Shan, Xiaohu Qie, and Mike Zheng Shou.”