MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness
MAGIC: 少样本掩码引导的异常修复与提示扰动、空间自适应引导和上下文意识
JaeHyuck Choi, MinJun Kim, Je Hyeong Hong
机构
*
Department of AI Semiconductor Engineering, Hanyang University, Seoul, Korea(汉阳大学人工智能半导体工程系)
;
Department of Electronic Engineering, Hanyang University, Seoul, Korea(汉阳大学电子工程系)
CommentsAccepted at CVPR 2026 Findings. Supplementary material included after references. 47 pages, 47 figures, 28 tables. Code : https://github.com/SpatialAILab/MAGIC
Motion-Driven Multi-Object Tracking of Model Organisms in Space Science Experiments
空间科学实验中模型生物的运动驱动多目标跟踪
Jianing You, Han Wang, Kang Liu, Jiale Ding, Fengjie Chu, Zihan Guo, Shengyang Li
机构
*
Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences(中国科学院空间利用技术与工程中心)
;
School of Space Exploration, University of Chinese Academy of Sciences(中国科学院大学空间探索学院)
机构
*
Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(人工智能研究院,合肥国家科学中心)
;
Anhui Polytechnic University(安徽理工大学)
;
Hefei University of Technology(合肥工业大学)
;
Anhui University(安徽大学)
;
IGS, Imperial College London(帝国理工学院伦敦分校)
Comments4 pages, 2 figures, and 1 table. This is a methodology paper for the DataCV 2026 Challenge (CVPR Workshops), Task 1, where our method ranked 2nd
The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation
经典知识蒸馏在语义分割中的意外有效性
Muhammad Ali, Kevin Alexander Laube, Madan Ravi Ganesh, Lukas Schott, Niclas Popp, Thomas Brox
机构
*
University of Freiburg(弗赖堡大学)
;
Bosch Center for Artificial Intelligence(博世人工智能中心)
;
Aleph Alpha Research(Aleph Alpha研究)
;
University of Tübingen(图宾根大学)
Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention
告诉模型该看哪里:通过视觉引导注意力缓解大语言模型的幻觉
Jianfei Zhao, Feng Zhang, Xin Sun, Chong Feng, Zhixing Tan
机构
*
School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学院)
;
Zhongguancun Academy(中关村学院)
;
Southeast Academy of Information Technology, Beijing Institute of Technology(北京理工大学信息科技东南学院)
;
Zhongguancun Laboratory(中关村实验室)
机构
*
University of Science and Technology of China(中国科学技术大学)
;
Shanghai Advanced Research Institute, Chinese Academy of Sciences(上海先进研究院,中国科学院)
;
University of Chinese Academy of Sciences(中国科学院大学)
OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding
OmniVTG:一种大规模数据集和开放世界视频时间定位的训练范式
Minghang Zheng, Zihao Yin, Yi Yang, Yuxin Peng, Yang Liu
机构
*
Wangxuan Institute of Computer Technology, Peking University(北京大学王轩计算机技术研究所)
;
State Key Laboratory of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室)
;
Central Media Technology Institute, Huawei Technologies Ltd.(华为技术有限公司中央媒体技术研究所)
;
PKU-WUHAN Institute for Artificial Intelligence, Peking University(北京大学武汉人工智能研究所)