Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
OmniPrism: Learning Disentangled Visual Concept for Image Generation
Yangyang Li, Daqing Liu, Wu Liu +4
Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constra…
cs.CV2026
A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos
Allen He, Qi Liu, Kun Liu +2
Temporal sentence grounding in videos (TSGV) aims to localize a temporal segment that semantically corresponds to a sentence query from an untrimmed video. Most current methods ado…