4 papers
MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations
Jongsuk Kim, Qiyu Wu, Zhuoyuan Mao +3
Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at compositionality, particularly attribute-object and relational structures. Recent st…
Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
Gyojin Han, Junmo Kim
We address text-based 3D human motion editing, where the goal is to preserve the style and structure of a source motion while applying edits described in natural language. The rele…
Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
Youngtaek Oh, Jae Won Cho, Dong-Jin Kim +2
In this paper, we propose a new method to enhance compositional understanding in pre-trained vision and language models (VLMs) without sacrificing performance in zero-shot multi-mo…
Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition
Youngtaek Oh, Pyunghwan Ahn, Jinhyung Kim +4
Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot recognition abilities yet face challenges in visio-linguistic compositionality, particularly in l…