Object-aware Video-language Pre-training For Retrieval

Abstract

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 https://github.com/FingerRec/OA-Transformer.

Stats

• citations46
• S2 citations—
• github stars62
• HF likes0
• heat score16.14
• arxiv keywang2021object

Code

• FingerRec/OA-Transformer—

Related papers

• Multi-modal Transformer For Video Retrieval (2020)19.47
• Semantic Role Aware Correlation Transformer For Text To Video Retrieval (2022)6.34
• Helping Hands: An Object-aware Ego-centric Video Recognition Model (2023)10.07
• Revisiting Human-in-the-loop Object Retrieval With Pre-trained Vision Transformers (2026)0.00
• Temporal Perceiving Video-language Pre-training (2023)0.00
• MDMMT-2: Multidomain Multimodal Transformer For Video Retrieval, One More Step Towards Generalization (2022)0.00
• Everything At Once -- Multi-modal Fusion Transformer For Video Retrieval (2021)15.78
• Object Priors For Classifying And Localizing Unseen Actions (2021)9.41