7 citations · 12 across the 8 of their papers we have counts for
5 papers · 1 filter
Semantic and Visual Evidence for Efficient Long-Video Reasoning: A Solution for the HD-EPIC VQA Challenge
Yinsong Xu, Wei Jing, Liuxin Zhang +2
Understanding long-form egocentric videos remains challenging for multimodal large language models (MLLMs) due to limited context length and insufficient grounding of fine-grained…
Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness
Jiaqi Tang, Yinsong Xu, Qingchao Chen
Object classification models utilizing point cloud data are fundamental for 3D media understanding, yet they often struggle with unseen or out-of-distribution (OOD) scenarios. Exis…
EviPrompt: A Training-Free Evidential Prompt Generation Method for Segment Anything Model in Medical Images
Yinsong Xu, Jiaqi Tang, Aidong Men +1
Medical image segmentation has immense clinical applicability but remains a challenge despite advancements in deep learning. The Segment Anything Model (SAM) exhibits potential in…
Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation
Yinsong Xu, Aidong Men, Yang Liu +2
In deep learning, initializing models with pre-trained weights has become the de facto practice for various downstream tasks. Many unsupervised domain adaptation (UDA) methods typi…
Delving into the Continuous Domain Adaptation
Yinsong Xu, Zhuqing Jiang, Aidong Men +2
Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e.g., art, real, painting, quickdraw, etc. We argue that…