Search Results for author: Bin Fan

Found 21 papers, 7 papers with code

SUNet: Symmetric Undistortion Network for Rolling Shutter Correction

no code implementations10 Aug 2021 Bin Fan, Yuchao Dai, Mingyi He

The vast majority of modern consumer-grade cameras employ a rolling shutter mechanism, leading to image distortions if the camera moves during image acquisition.

Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization

no code implementations ECCV 2020 Haibao Yu, Qi Han, Jianbo Li, Jianping Shi, Guangliang Cheng, Bin Fan

Learning to find an optimal mixed precision model that can preserve accuracy and satisfy the specific constraints on model size and computation is extremely challenge due to the difficult in training a mixed precision model and the huge space of all possible bit quantizations.


Relative Pose Estimation for Stereo Rolling Shutter Cameras

no code implementations14 Jun 2020 Ke Wang, Bin Fan, Yuchao Dai

In this paper, we present a novel linear algorithm to estimate the 6 DoF relative pose from consecutive frames of stereo rolling shutter (RS) cameras.

Pose Estimation

Deep Attention Aware Feature Learning for Person Re-Identification

1 code implementation1 Mar 2020 Yifan Chen, Han Wang, Xiaolu Sun, Bin Fan, Chu Tang

Visual attention has proven to be effective in improving the performance of person re-identification.

Deep Attention Person Re-Identification

AugFPN: Improving Multi-scale Feature Learning for Object Detection

2 code implementations CVPR 2020 Chaoxu Guo, Bin Fan, Qian Zhang, Shiming Xiang, Chunhong Pan

In this paper, we begin by first analyzing the design defects of feature pyramid in FPN, and then introduce a new feature pyramid architecture named AugFPN to address these problems.

Object Detection

Guiding the Flowing of Semantics: Interpretable Video Captioning via POS Tag

no code implementations IJCNLP 2019 Xinyu Xiao, Lingfeng Wang, Bin Fan, Shinming Xiang, Chunhong Pan

To address these problems, we propose an Adaptive Semantic Guidance Network (ASGN), which instantiates the whole video semantics to different POS-aware semantics with the supervision of part of speech (POS) tag.

POS Video Captioning

Relation-Shape Convolutional Neural Network for Point Cloud Analysis

4 code implementations CVPR 2019 Yongcheng Liu, Bin Fan, Shiming Xiang, Chunhong Pan

Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others.

Ranked #14 on 3D Part Segmentation on ShapeNet-Part (Instance Average IoU metric)

3D Part Segmentation 3D Point Cloud Classification

SOSNet: Second Order Similarity Regularization for Local Descriptor Learning

1 code implementation CVPR 2019 Yurun Tian, Xin Yu, Bin Fan, Fuchao Wu, Huub Heijnen, Vassileios Balntas

Despite the fact that Second Order Similarity (SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors.

Graph Matching Structure from Motion

Progressive Sparse Local Attention for Video object detection

no code implementations ICCV 2019 Chaoxu Guo, Bin Fan, Jie Gu, Qian Zhang, Shiming Xiang, Veronique Prinet, Chunhong Pan

Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features.

Optical Flow Estimation Video Object Detection

Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network

1 code implementation30 Jul 2018 Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan

Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation.

L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space

1 code implementation CVPR 2017 Yurun Tian, Bin Fan, Fuchao Wu

In this paper, we propose to learn high per- formance descriptor in Euclidean space via the Convolu- tional Neural Network (CNN).

Patch Matching

Do We Need Binary Features for 3D Reconstruction?

no code implementations14 Feb 2016 Bin Fan, Qingqun Kong, Wei Sui, Zhiheng Wang, Xinchao Wang, Shiming Xiang, Chunhong Pan, Pascal Fua

Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors.

3D Reconstruction

kNN Hashing With Factorized Neighborhood Representation

no code implementations ICCV 2015 Kun Ding, Chunlei Huo, Bin Fan, Chunhong Pan

Hashing is very effective for many tasks in reducing the processing time and in compressing massive databases.

Beyond Mahalanobis Metric: Cayley-Klein Metric Learning

no code implementations CVPR 2015 Yanhong Bi, Bin Fan, Fuchao Wu

Experiments have shown the superiority of Cayley-Klein metric over Mahalanobis ones and the effectiveness of our Cayley-Klein metric learning methods.

Metric Learning

10,000+ Times Accelerated Robust Subset Selection (ARSS)

no code implementations12 Sep 2014 Feiyun Zhu, Bin Fan, Xinliang Zhu, Ying Wang, Shiming Xiang, Chunhong Pan

Subset selection from massive data with noised information is increasingly popular for various applications.

Ranked #6 on Named Entity Recognition on SciERC (using extra training data)

Action Recognition Fine-Grained Image Classification +15

Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity

no code implementations2 Sep 2014 Feiyun Zhu, Ying Wang, Bin Fan, Gaofeng Meng, Chunhong Pan

Based on this observation, we exploit a learning-based sparsity method to simultaneously learn the HU results and a sparse guidance map.

Hyperspectral Unmixing

Affine Subspace Representation for Feature Description

no code implementations18 Jul 2014 Zhenhua Wang, Bin Fan, Fuchao Wu

This paper proposes a novel Affine Subspace Representation (ASR) descriptor to deal with affine distortions induced by viewpoint changes.

Structured Sparse Method for Hyperspectral Unmixing

no code implementations19 Mar 2014 Feiyun Zhu, Ying Wang, Shiming Xiang, Bin Fan, Chunhong Pan

With this constraint, our method can learn a compact space, where highly similar pixels are grouped to share correlated sparse representations.

Hyperspectral Unmixing

Spectral Unmixing via Data-guided Sparsity

no code implementations13 Mar 2014 Feiyun Zhu, Ying Wang, Bin Fan, Gaofeng Meng, Shiming Xiang, Chunhong Pan

Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding.

Hyperspectral Unmixing

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