Towards Balanced Learning for Instance Recognition von Pang, Jiangmiao, Chen, Kai, Li, Qi, Xu, Zhihai, Feng, Huajun, Shi, Jianping, Ouyang, Wanli, Lin, Dahua

Volltext

Self-Adversarial Disentangling for Specific Domain Adaptation von Zhou, Qianyu, Gu, Qiqi, Pang, Jiangmiao, Lu, Xuequan, Ma, Lizhuang

Volltext

Context-Aware Mixup for Domain Adaptive Semantic Segmentation von Zhou, Qianyu, Feng, Zhengyang, Gu, Qiqi, Pang, Jiangmiao, Cheng, Guangliang, Lu, Xuequan, Shi, Jianping, Ma, Lizhuang

Volltext

QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking von Fischer, Tobias, Huang, Thomas E., Pang, Jiangmiao, Qiu, Linlu, Chen, Haofeng, Darrell, Trevor, Yu, Fisher

Volltext

Position-Guided Point Cloud Panoptic Segmentation Transformer von Xiao, Zeqi, Zhang, Wenwei, Wang, Tai, Loy, Chen Change, Lin, Dahua, Pang, Jiangmiao

Volltext

Transformer-Based Visual Segmentation: A Survey von Li, Xiangtai, Ding, Henghui, Yuan, Haobo, Zhang, Wenwei, Pang, Jiangmiao, Cheng, Guangliang, Chen, Kai, Liu, Ziwei, Loy, Chen Change

Volltext

3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting von Lyu, Xiaoyang, Sun, Yang-Tian, Huang, Yi-Hua, Wu, Xiuzhe, Yang, Ziyi, Chen, Yilun, Pang, Jiangmiao, Qi, Xiaojuan

Volltext

mathcal^2 -CNN: Fast Tiny Object Detection in Large-Scale Remote Sensing Images von Pang, Jiangmiao, Li, Cong, Shi, Jianping, Xu, Zhihai, Feng, Huajun

Volltext

[Formula Omitted]-CNN: Fast Tiny Object Detection in Large-Scale Remote Sensing Images von Pang, Jiangmiao, Li, Cong, Shi, Jianping, Xu, Zhihai, Feng, Huajun

Volltext

Side-Aware Boundary Localization for More Precise Object Detection von Wang, Jiaqi, Zhang, Wenwei, Cao, Yuhang, Chen, Kai, Pang, Jiangmiao, Gong, Tao, Shi, Jianping, Loy, Chen Change, Lin, Dahua

Volltext

Monocular 3D Object Detection with Depth from Motion von Wang, Tai, Pang, Jiangmiao, Lin, Dahua

Volltext

Dense Siamese Network for Dense Unsupervised Learning von Zhang, Wenwei, Pang, Jiangmiao, Chen, Kai, Loy, Chen Change

Volltext

PointLLM: Empowering Large Language Models to Understand Point Clouds von Xu, Runsen, Wang, Xiaolong, Wang, Tai, Chen, Yilun, Pang, Jiangmiao, Lin, Dahua

Volltext

Multi-Object Tracking by Hierarchical Visual Representations von Cao, Jinkun, Pang, Jiangmiao, Kitani, Kris

Volltext bestellen

LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness von Zhu, Chenming, Wang, Tai, Zhang, Wenwei, Pang, Jiangmiao, Liu, Xihui

Volltext bestellen

What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights von Wen, Xin, Zhao, Bingchen, Chen, Yilun, Pang, Jiangmiao, Qi, Xiaojuan

Volltext bestellen

Monocular 3D Object Detection with Depth from Motion von Wang, Tai, Pang, Jiangmiao, Lin, Dahua

Volltext bestellen

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction von Chen, Xiao, Li, Quanyi, Wang, Tai, Xue, Tianfan, Pang, Jiangmiao

Volltext bestellen

MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction von Chen, Jiahe, Cao, Jinkun, Lin, Dahua, Kitani, Kris, Pang, Jiangmiao

Volltext bestellen

Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation von Tian, Yang, Yang, Sizhe, Zeng, Jia, Wang, Ping, Lin, Dahua, Dong, Hao, Pang, Jiangmiao

Volltext bestellen