This paper aims for the task of text-to-video retrieval, where given a query in the form of a
natural-language sentence, it is asked to retrieve videos which are semantically relevant to …

Abstract Visual Semantic Embedding (VSE) is a dominant method for vision-language
retrieval. Its purpose is to learn an embedding space so that visual data can be embedded in …

With the current exponential growth of video-based social networks, video retrieval using
natural language is receiving ever-increasing attention. Most existing approaches tackle this …

Multi-modal cues presented in videos are usually beneficial for the challenging video-text
retrieval task on internet-scale datasets. Recent video retrieval methods take advantage of …

In this paper, we target the challenging task of video-text retrieval. The common way for this
task is to learn a text-video joint embedding space by cross-modal representation learning …

Cross-modal video-text retrieval has been an emerging task due to the rapid growth of user-
generated videos on the Internet. Most existing approaches focus on extracting visual …

Most existing video-language modeling methods densely sample dozens (or even
hundreds) of video clips from each raw video to learn the video representation for text-to …

In order to effectively solve the persistent problems of low accuracy and high computational
complexity in video retrieval, we propose a feature-controlled retrieval algorithm which …