Daniel
Daniel
Home
Publications
Light
Dark
Automatic
1
Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scene
Self-driving cars relying solely on ego-centric perception face limitations in sensing, often failing to detect occluded, faraway …
Tai-Yu Daniel Pan
,
Sooyoung Jeon
,
Mengdi Fan
,
Jinsu Yoo
,
Zhenyang Feng
,
Mark Campbell
,
Kilian Q. Weinberger
,
Bharath Hariharan
,
Wei-Lun Chao
PDF
Cite
arXiv
Learning 3D Perception from Others' Predictions
Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data …
Jinsu Yoo
,
Zhenyang Feng
,
Tai-Yu Daniel Pan
,
Yihong Sun
,
Cheng Perng Phoo
,
Xiangyu Chen
,
Mark Campbell
,
Kilian Q. Weinberger
,
Bharath Hariharan
,
Wei-Lun Chao
PDF
Cite
Project
arXiv
Pre-Training LiDAR-Based 3D Object Detectors Through Colorization
Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts …
Tai-Yu Daniel Pan
,
Chenyang Ma
,
Tianle Chen
,
Cheng Perng Phoo
,
Katie Z Luo
,
Yurong You
,
Mark Campbell
,
Kilian Q. Weinberger
,
Bharath Hariharan
,
Wei-Lun Chao
PDF
Cite
arXiv
Towards Open-World Segmentation of Parts
Segmenting object parts such as cup handles and animal bodies is important in many real-world applications but requires more annotation …
Tai-Yu Daniel Pan
,
Qing Liu
,
Wei-Lun Chao
,
Brian Price
PDF
Cite
Code
arXiv
One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones
We study the problem of developing autonomous agents that can follow human instructions to infer and perform a sequence of actions to …
Chan Hee Song
,
Jihyung Kil
,
Tai-Yu Daniel Pan
,
Brian M. Sadler
,
Wei-Lun Chao
,
Yu Su
PDF
Cite
arXiv
Learning with Free Object Segments for Long-Tailed Instance Segmentation
One fundamental challenge in building an instance segmen- tation model for a large number of classes in complex scenes is the lack of …
Cheng Zhang
,
Tai-Yu Daniel Pan
,
Tianle Chen
,
Jike Zhong
,
Wenjin Fu
,
Wei-Lun Chao
PDF
Cite
arXiv
On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the …
Tai-Yu Daniel Pan
,
Cheng Zhang
,
Yandong Li
,
Hexiang Hu
,
Dong Xuan
,
Soravit Changpinyo
,
Boqing Gong
,
Wei-Lun Chao
PDF
Cite
Code
arXiv
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
Many objects do not appear frequently enough in complex scenes (
e.g.
, certain handbags in living rooms) for training an accurate object …
Cheng Zhang
,
Tai-Yu Daniel Pan
,
Yandong Li
,
Hexiang Hu
,
Dong Xuan
,
Soravit Changpinyo
,
Boqing Gong
,
Wei-Lun Chao
PDF
Cite
Code
arXiv
Cite
×