activity
20152023
most citedMedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification

1k citations · 2.3k across the 59 of their papers we have counts for

collaborators
Showing 2017 · cs.CVShow all

6 papers · 2 filters

cs.CV2017

Flexible Network Binarization with Layer-wise Priority

Lixue Zhuang, Yi Xu, Bingbing Ni +1

How to effectively approximate real-valued parameters with binary codes plays a central role in neural network binarization. In this work, we reveal an important fact that binarizi…

cs.CV2017★ 19 cited

Performance Guaranteed Network Acceleration via High-Order Residual Quantization

Zefan Li, Bingbing Ni, Wenjun Zhang +2

Input binarization has shown to be an effective way for network acceleration. However, previous binarization scheme could be regarded as simple pixel-wise thresholding operations (…

cs.CV2017★ 1 cited

Skeleton-aided Articulated Motion Generation

Yichao Yan, Jingwei Xu, Bingbing Ni +1

This work make the first attempt to generate articulated human motion sequence from a single image. On the one hand, we utilize paired inputs including human skeleton information a…

cs.CV2017★ 3 cited

Depth Structure Preserving Scene Image Generation

Wendong Zhang, Bingbing Ni, Yichao Yan +2

Key to automatically generate natural scene images is to properly arrange among various spatial elements, especially in the depth direction. To this end, we introduce a novel depth…

cs.CV2017★ 5 cited

Predicting Human Interaction via Relative Attention Model

Yichao Yan, Bingbing Ni, Xiaokang Yang

Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video. Essentially, a good algorithm should effectively model…

cs.CV2017★ 2 cited

Person Re-Identification via Recurrent Feature Aggregation

Yichao Yan, Bingbing Ni, Zhichao Song +3

We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches. This is…