Showing cs.CVShow all
3 papers · 1 filter
cs.CV2024
Dual-task Mutual Reinforcing Embedded Joint Video Paragraph Retrieval and Grounding
Mengzhao Wang, Huafeng Li, Yafei Zhang +3
Video Paragraph Grounding (VPG) aims to precisely locate the most appropriate moments within a video that are relevant to a given textual paragraph query. However, existing methods…
cs.CV2024
Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding
Minghong Xie, Mengzhao Wang, Huafeng Li +3
Visual grounding has attracted wide attention thanks to its broad application in various visual language tasks. Although visual grounding has made significant research progress, ex…
cs.CV2024
CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-Identification
Xiaoyan Yu, Neng Dong, Liehuang Zhu +2
Visible-infrared person re-identification (VIReID) primarily deals with matching identities across person images from different modalities. Due to the modality gap between visible…