BridgeFormer: Bridging Video-text Retrieval with Multiple Choice Questions

by   Yuying Ge, et al.

Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local associations between videos and texts. Another line of research uses a joint encoder to interact video with texts, but results in low efficiency since each text-video pair needs to be fed into the model. In this work, we enable fine-grained video-text interactions while maintaining high efficiency for retrieval via a novel pretext task, dubbed as Multiple Choice Questions (MCQ), where a parametric module BridgeFormer is trained to answer the "questions" constructed by the text features via resorting to the video features. Specifically, we exploit the rich semantics of text (i.e., nouns and verbs) to build questions, with which the video encoder can be trained to capture more regional content and temporal dynamics. In the form of questions and answers, the semantic associations between local video-text features can be properly established. BridgeFormer is able to be removed for downstream retrieval, rendering an efficient and flexible model with only two encoders. Our method outperforms state-of-the-art methods on the popular text-to-video retrieval task in five datasets with different experimental setups (i.e., zero-shot and fine-tune), including HowTo100M (one million videos). We further conduct zero-shot action recognition, which can be cast as video-to-text retrieval, and our approach also significantly surpasses its counterparts. As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e.g., action recognition with linear evaluation.


page 2

page 3

page 6

page 7

page 8

page 9

page 11

page 12


MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval

Dominant pre-training work for video-text retrieval mainly adopt the "du...

Temporal Perceiving Video-Language Pre-training

Video-Language Pre-training models have recently significantly improved ...

Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions

We study joint video and language (VL) pre-training to enable cross-moda...

Learning Spatiotemporal Features via Video and Text Pair Discrimination

Current video representations heavily rely on learning from manually ann...

LocVTP: Video-Text Pre-training for Temporal Localization

Video-Text Pre-training (VTP) aims to learn transferable representations...

Prompting Visual-Language Models for Efficient Video Understanding

Visual-language pre-training has shown great success for learning joint ...

GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

Generating videos from text is a challenging task due to its high comput...

Please sign up or login with your details

Forgot password? Click here to reset