activity
20142025
most citedDeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection

134 citations · 495 across the 68 of their papers we have counts for

collaborators
Showing cs.CVShow all

46 papers · 1 filter

cs.CV2024

Fast Information Streaming Handler (FisH): A Unified Seismic Neural Network for Single Station Real-Time Earthquake Early Warning

Tianning Zhang, Feng Liu, Yuming Yuan +3

Existing EEW approaches often treat phase picking, location estimation, and magnitude estimation as separate tasks, lacking a unified framework. Additionally, most deep learning mo…

cs.CV2024

Point Transformer V3 Extreme: 1st Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation

Xiaoyang Wu, Xiang Xu, Lingdong Kong +5

In this technical report, we detail our first-place solution for the 2024 Waymo Open Dataset Challenge's semantic segmentation track. We significantly enhanced the performance of P…

cs.CV2024

VegeDiff: Latent Diffusion Model for Geospatial Vegetation Forecasting

Sijie Zhao, Hao Chen, Xueliang Zhang +3

In the context of global climate change and frequent extreme weather events, forecasting future geospatial vegetation states under these conditions is of significant importance. Th…

cs.CV20241 cited

TCFormer: Visual Recognition via Token Clustering Transformer

Wang Zeng, Sheng Jin, Lumin Xu +5

Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid…

cs.CV2024

Semi-supervised 3D Object Detection with PatchTeacher and PillarMix

Xiaopei Wu, Liang Peng, Liang Xie +6

Semi-supervised learning aims to leverage numerous unlabeled data to improve the model performance. Current semi-supervised 3D object detection methods typically use a teacher to g…

cs.CV2024

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

Xiaopei Wu, Yuenan Hou, Xiaoshui Huang +8

Training deep models for LiDAR semantic segmentation is challenging due to the inherent sparsity of point clouds. Utilizing temporal data is a natural remedy against the sparsity p…