1 citations · 1 across the 3 of their papers we have counts for
4 papers
Which Tokens to Merge? Diffusion Dynamics for Efficient Image Generation
SeungJu Cha, Ye-Chan Kim, HyunGee Kim +2
Token merging has emerged as an effective training-free strategy for accelerating diffusion models by reducing redundant token computation while minimizing generation degradation.…
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
Ye-Chan Kim, Seunghee Choi, SeungJu Cha +4
Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work…
SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning
Ye-Chan Kim, SeungJu Cha, Si-Woo Kim +3
Weakly-Supervised Dense Video Captioning aims to localize and describe events in videos trained only on caption annotations, without temporal boundaries. Prior work introduced an i…
Pathological MRI Segmentation by Synthetic Pathological Data Generation in Fetuses and Neonates
Misha P. T Kaandorp, Damola Agbelese, Hosna Asma-ull +6
Developing new methods for the automated analysis of clinical fetal and neonatal MRI data is limited by the scarcity of annotated pathological datasets and privacy concerns that of…