Search Results for author: Wenbo Zhang

Found 17 papers, 8 papers with code

Light Source Point Cluster Selection Based Atmosphere Light Estimation

no code implementations12 Jan 2017 Wenbo Zhang, Xiaorong Hou

To address this problem, this paper propose a method that relies on clustering statistics to estimate atmosphere light value.

Clustering

Incident Light Frequency-based Image Defogging Algorithm

no code implementations3 Mar 2017 Wenbo Zhang, Xiaorong Hou

Considering the problem of color distortion caused by the defogging algorithm based on dark channel prior, an improved algorithm was proposed to calculate the transmittance of all channels respectively.

Image Restoration

End-to-end Hand Mesh Recovery from a Monocular RGB Image

2 code implementations ICCV 2019 Xiong Zhang, Qiang Li, Hong Mo, Wenbo Zhang, Wen Zheng

In this paper, we present a HAnd Mesh Recovery (HAMR) framework to tackle the problem of reconstructing the full 3D mesh of a human hand from a single RGB image.

3D Hand Pose Estimation

StyleRemix: An Interpretable Representation for Neural Image Style Transfer

no code implementations27 Feb 2019 Hongmin Xu, Qiang Li, Wenbo Zhang, Wen Zheng

Multi-Style Transfer (MST) intents to capture the high-level visual vocabulary of different styles and expresses these vocabularies in a joint model to transfer each specific style.

Style Transfer

MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding

no code implementations25 Oct 2019 Wenbo Zhang, Osbert Bastani, Vijay Kumar

Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks.

Multi-agent Reinforcement Learning reinforcement-learning +1

Siamese Keypoint Prediction Network for Visual Object Tracking

1 code implementation7 Jun 2020 Qiang Li, Zekui Qin, Wenbo Zhang, Wen Zheng

Visual object tracking aims to estimate the location of an arbitrary target in a video sequence given its initial bounding box.

Object Visual Object Tracking

IncNSA: Detecting communities incrementally from time-evolving networks based on node similarity

1 code implementation International Journal of Modern Physics C 2020 Xing Su, Jianjun Cheng, Haijuan Yang, Mingwei Leng, Wenbo Zhang, Xiaoyun Chen

When the network evolves from the previous snapshot to the current one, the proposed method only considers the community affiliations of partial nodes efficiently, which are either newborn nodes or some active nodes from the previous snapshot.

Community Detection Dynamic Community Detection +1

A Effective Carrier Phase Recovery Method in Tigth Time-Packing Fast than Nyquist Optical Communication System

no code implementations24 Aug 2020 Peng Sun, Xiaoguang Zhang, Dongwei Pan, Lixia Xi, Wenbo Zhang, Xianfeng Tang

We propose a new scheme that combines polybinary transformaton and corrected-BPS to compensate noise for PDM-FTN-QPSK when its accelerated factor is 0. 5, which has 3. 3 dB OSNR gain when phase noise is 800 kHz.

Deformable Linear Object Prediction Using Locally Linear Latent Dynamics

1 code implementation26 Mar 2021 Wenbo Zhang, Karl Schmeckpeper, Pratik Chaudhari, Kostas Daniilidis

We empirically demonstrate that our approach can predict the rope state accurately up to ten steps into the future and that our algorithm can find the optimal action given an initial state and a goal state.

Object

Identifying modulation formats using integrated clustering algorithm

no code implementations28 Apr 2021 Wenbo Zhang, Jinmei Ye, Zixian Yue, Yuxiang Wang, Xulun Zhang, Xiaoguang Zhang, Lixia Xi

Modulation format identification (MFI) is crucial in next-generation optical networks such as cognitive optical networks.

Clustering

Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection

1 code implementation5 Jul 2021 Wenbo Zhang, Ge-Peng Ji, Zhuo Wang, Keren Fu, Qijun Zhao

To tackle this dilemma and also inspired by the fact that depth quality is a key factor influencing the accuracy, we propose a novel depth quality-inspired feature manipulation (DQFM) process, which is efficient itself and can serve as a gating mechanism for filtering depth features to greatly boost the accuracy.

object-detection RGB-D Salient Object Detection +1

Multi-Source Uncertainty Mining for Deep Unsupervised Saliency Detection

no code implementations CVPR 2022 Yifan Wang, Wenbo Zhang, Lijun Wang, Ting Liu, Huchuan Lu

We design an Uncertainty Mining Network (UMNet) which consists of multiple Merge-and-Split (MS) modules to recursively analyze the commonality and difference among multiple noisy labels and infer pixel-wise uncertainty map for each label.

object-detection Object Detection +2

ME-Net: Multi-Encoder Net Framework for Brain Tumor Segmentation

no code implementations21 Mar 2022 Wenbo Zhang, Guang Yang, He Huang, Weiji Yang, Xiaomei Xu, Yongkai Liu, Xiaobo Lai

Moreover, the serious voxel imbalance between the brain tumor and the background as well as the different sizes and locations of the brain tumor makes the segmentation of 3D images a challenging problem.

Brain Tumor Segmentation Segmentation +1

Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object Detection

1 code implementation8 Aug 2022 Wenbo Zhang, Keren Fu, Zhuo Wang, Ge-Peng Ji, Qijun Zhao

Inspired by the fact that depth quality is a key factor influencing the accuracy, we propose an efficient depth quality-inspired feature manipulation (DQFM) process, which can dynamically filter depth features according to depth quality.

object-detection RGB-D Salient Object Detection +2

Towards Trustworthy Explanation: On Causal Rationalization

1 code implementation25 Jun 2023 Wenbo Zhang, Tong Wu, Yunlong Wang, Yong Cai, Hengrui Cai

With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in prediction.

Causal Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.