Seongsu Ha — accepted AI-conference papers

2024

Finding NeMo: Negative-mined Mosaic Augmentation for Referring Image Segmentation

Seongsu Ha, Chaeyun Kim, Donghwa Kim, Junho Lee, Sangho Lee, Joonseok Lee*

ECCV 2024poster

"Referring Image Segmentation is a comprehensive task to segment an object referred by a textual query from an image. In nature, the level of difficulty in this task is affected by the existence of similar objects and the complexity of the referring expression. Recent RIS models still show a signifi…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Towards a Complete Benchmark on Video Moment Localization

Jinyeong Chae, Donghwa Kim, Kwanseok Kim, Doyeon Lee, Sangho Lee, Seongsu Ha +4

AISTATS 2024poster

In this paper, we propose and conduct a comprehensive benchmark on moment localization task, which aims to retrieve a segment that corresponds to a text query from a single untrimmed video. Our study starts from an observation that most moment localization papers report experimental results only on…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗