Video moment localization, also known as video moment retrieval, aims to search a target
segment within a video described by a given natural language query. Beyond the task of …

Temporal sentence grounding in videos (TSGV), aka, natural language video localization
(NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that …

The recent video grounding works attempt to introduce vanilla contrastive learning into video
grounding. However, we claim that this naive solution is suboptimal. Contrastive learning …

Almost all previous text-to-video retrieval works assume that videos are pre-trimmed with
short durations. However, in practice, videos are generally untrimmed containing much …

Current methods for text-to-video retrieval (T2VR) are trained and tested on video-captioning
oriented datasets such as MSVD, MSR-VTT and VATEX. A key property of these datasets is …

Temporal sentence grounding in videos (TSGV), which aims at localizing one target
segment from an untrimmed video with respect to a given sentence query, has drawn …

Moment retrieval in videos is a challenging task that aims to retrieve the most relevant video
moment in an untrimmed video given a sentence description. Previous methods tend to …

Information Extraction (IE) aims to extract structural information from unstructured texts. In
practice, long-tailed distributions caused by the selection bias of a dataset, may lead to …

In this paper, we study a challenging but less-touched problem in cross-modal retrieval, ie,
partially mismatched pairs (PMPs). Specifically, in real-world scenarios, a huge number of …

Cross-modal retrieval aims to enable a flexible bi-directional retrieval experience across
different modalities (eg, searching for videos with texts). Many existing efforts tend to learn a …