activity
20232026
most citedRefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets

16 citations · 16 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV2026

PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation

Qingyu Fan, Zhaoxiang Li, Jinrui Hu +8

Bimanual manipulation in cluttered scenes requires policies that remain stable under occlusions, viewpoint changes and scene variations. Existing vision-language-action models ofte…

cs.CV2025

M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

Kailai Zhou, Fuqiang Yang, Shixian Wang +5

RGB-Thermal (RGBT) multispectral vision is essential for robust perception in complex environments. Most RGBT tasks follow a case-by-case research paradigm, relying on manually cus…

cs.CV2025

MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond

Shenghao Ren, Yi Lu, Jiayi Huang +5

Existing human Motion Capture (MoCap) methods mostly focus on the visual similarity while neglecting the physical plausibility. As a result, downstream tasks such as driving virtua…

cs.CV2024

Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography

Kailai Zhou, Lijing Cai, Yibo Wang +4

The integration of miniaturized spectrometers into mobile devices offers new avenues for image quality enhancement and facilitates novel downstream tasks. However, the broader appl…

cs.CV2024

MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors

He Zhang, Shenghao Ren, Haolei Yuan +7

Foot contact is an important cue for human motion capture, understanding, and generation. Existing datasets tend to annotate dense foot contact using visual matching with threshold…

cs.CV202316 cited

RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets

Zhicheng Cai, Xiaohan Ding, Qiu Shen +1

We propose Re-parameterized Refocusing Convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without a…