activity
20172024
most citedSpatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition

38 citations · 119 across the 10 of their papers we have counts for

collaborators

10 papers

cs.CV2024★ 3 cited

Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery

Fan Zhang, Lingling Li, Licheng Jiao +4

Satellite imagery, due to its long-range imaging, brings with it a variety of scale-preferred tasks, such as the detection of tiny/small objects, making the precise localization an…

cs.CV2024★ 1 cited

Masked Angle-Aware Autoencoder for Remote Sensing Images

Zhihao Li, Biao Hou, Siteng Ma +4

To overcome the inherent domain gap between remote sensing (RS) images and natural images, some self-supervised representation learning methods have made promising progress. Howeve…

cs.CV2022★ 38 cited

Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition

Helei Qiu, Biao Hou, Bo Ren +1

Capturing the dependencies between joints is critical in skeleton-based action recognition task. Transformer shows great potential to model the correlation of important joints. How…

quant-ph2021★ 1 cited

A Variation-Aware Quantum Circuit Mapping Approach Based on Multi-agent Cooperation

Pengcheng Zhu, Weiping Ding, Lihua Wei +2

The quantum circuit mapping approach is an indispensable part of the software stack for the noisy intermediatescale quantum (NISQ) device. It has a significant impact on the reliab…

cs.CV2021★ 1 cited

More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation

Shuang Wang, Dong Zhao, Yi Li +5

Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation. Existing feature alignment methods for semantic s…

cs.CV2018★ 2 cited

Modified Diversity of Class Probability Estimation Co-training for Hyperspectral Image Classification

Yan Ju, Lingling Li, Licheng Jiao +3

Due to the limited amount and imbalanced classes of labeled training data, the conventional supervised learning can not ensure the discrimination of the learned feature for hypersp…