activity
20212023
most citedGeometric-aware Pretraining for Vision-centric 3D Object Detection

5 citations · 14 across the 12 of their papers we have counts for

collaborators

12 papers

cs.CV20231 cited

Pseudo-label Alignment for Semi-supervised Instance Segmentation

Jie Hu, Chen Chen, Liujuan Cao +4

Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in ex…

cs.CV20232 cited

A Unified Framework for 3D Point Cloud Visual Grounding

Haojia Lin, Yongdong Luo, Xiawu Zheng +7

Thanks to its precise spatial referencing, 3D point cloud visual grounding is essential for deep understanding and dynamic interaction in 3D environments, encompassing 3D Referring…

cs.CV20235 cited

Geometric-aware Pretraining for Vision-centric 3D Object Detection

Linyan Huang, Huijie Wang, Jia Zeng +4

Multi-camera 3D object detection for autonomous driving is a challenging problem that has garnered notable attention from both academia and industry. An obstacle encountered in vis…

cs.CV20233 cited

You Only Segment Once: Towards Real-Time Panoptic Segmentation

Jie Hu, Linyan Huang, Tianhe Ren +3

In this paper, we propose YOSO, a real-time panoptic segmentation framework. YOSO predicts masks via dynamic convolutions between panoptic kernels and image feature maps, in which…

cs.IR2023

Practical Cross-System Shilling Attacks with Limited Access to Data

Meifang Zeng, Ke Li, Bingchuan Jiang +2

In shilling attacks, an adversarial party injects a few fake user profiles into a Recommender System (RS) so that the target item can be promoted or demoted. Although much effort h…

cs.CV2023

DistilPose: Tokenized Pose Regression with Heatmap Distillation

Suhang Ye, Yingyi Zhang, Jie Hu +6

In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to tak…