Temporal Localization of Moments in Video Collections with Natural Language

114 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Hero: Hierarchical Encoder for Video+Language Omni-representation Pre-training (2020, methodology): “Escorcia et al. (2019) extends SVMR to Video Corpus Moment Retrieval (VCMR), extending searching pool from single video to large video corpus.”
TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval (2020, methodology): “Model references: MCN [1], CAL [8], MEE [22], ExCL [10].”
Video Self-Stitching Graph Network for Temporal Action Localization (2020, methodology): “TAL is not only the key technique of various application such as extracting highlights in sports, but also lays the foundation for other higher-level tasks such as video grounding [13, 8] and video captioning [18, 27].”
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers (2021, methodology): “Related to language-based visual search, re-ranking by a video-language temporal alignment model has been used to improve efficient moment retrieval in video [16].”
Egocentric Video-Language Pretraining (2022, methodology): “We then transfer the pretrained model to downstream tasks relevant to the egocentric domain. modality [27, 28].”
QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries (2021, methodology): “, proposal generation module and non-maximum suppression, commonly used in traditional methods [13, 35, 4, 48, 46, 40],and views moment localization as a direct set prediction problem.”