Search Results for author: Yunde Jia

Found 16 papers, 1 papers with code

A Decomposition Model for Stereo Matching

no code implementations CVPR 2021 Chengtang Yao, Yunde Jia, Huijun Di, Pengxiang Li, Yuwei Wu

In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases.

Disparity Estimation Stereo Matching

A Hyperbolic-to-Hyperbolic Graph Convolutional Network

no code implementations CVPR 2021 Jindou Dai, Yuwei Wu, Zhi Gao, Yunde Jia

Specifically, we developed a manifold-preserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic neighborhood aggregation.

General Classification Graph Classification +2

Curvature Generation in Curved Spaces for Few-Shot Learning

no code implementations ICCV 2021 Zhi Gao, Yuwei Wu, Yunde Jia, Mehrtash Harandi

Few-shot learning describes the challenging problem of recognizing samples from unseen classes given very few labeled examples.

Few-Shot Learning

Video Captioning Using Weak Annotation

no code implementations2 Sep 2020 Jingyi Hou, Yunde Jia, Xinxiao wu, Yayun Qi

Through traversing the dependency trees, the sentences are generated to train the captioning model.

Video Captioning Visual Reasoning

Content-Aware Inter-Scale Cost Aggregation for Stereo Matching

no code implementations5 Jun 2020 Chengtang Yao, Yunde Jia, Huijun Di, Yuwei Wu, Lidong Yu

In this paper, we present a content-aware inter-scale cost aggregation method that adaptively aggregates and upsamples the cost volume from coarse-scale to fine-scale by learning dynamic filter weights according to the content of the left and right views on the two scales.

Depth Estimation Stereo Matching

Relational Reasoning using Prior Knowledge for Visual Captioning

no code implementations4 Jun 2019 Jingyi Hou, Xinxiao Wu, Yayun Qi, Wentian Zhao, Jiebo Luo, Yunde Jia

Extensive experiments on the MS-COCO image captioning benchmark and the MSVD video captioning benchmark validate the superiority of our method on leveraging prior commonsense knowledge to enhance relational reasoning for visual captioning.

Image Captioning Object Detection +2

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set

1 code implementation20 Mar 2019 Yu Deng, Jiaolong Yang, Sicheng Xu, Dong Chen, Yunde Jia, Xin Tong

Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency. However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce.

3D Face Reconstruction

Stitching Videos from a Fisheye Lens Camera and a Wide-Angle Lens Camera for Telepresence Robots

no code implementations15 Mar 2019 Yanmei Dong, Mingtao Pei, Lijia Zhang, Bin Xu, Yuwei Wu, Yunde Jia

In this paper, we propose to stitch videos from the FF-camera with a wide-angle lens and the DF-camera with a fisheye lens for telepresence robots.

Deep Stereo Matching with Explicit Cost Aggregation Sub-Architecture

no code implementations12 Jan 2018 Lidong Yu, Yucheng Wang, Yuwei Wu, Yunde Jia

The cost aggregation sub-architecture is realized by a two-stream network: one for the generation of cost aggregation proposals, the other for the selection of the proposals.

Stereo Matching Stereo Matching Hand

Learning a Robust Representation via a Deep Network on Symmetric Positive Definite Manifolds

no code implementations17 Nov 2017 Zhi Gao, Yuwei Wu, Xingyuan Bu, Yunde Jia

To this end, several new layers are introduced in our network, including a nonlinear kernel aggregation layer, an SPD matrix transformation layer, and a vectorization layer.

Anisotropic Diffusion-based Kernel Matrix Model for Face Liveness Detection

no code implementations10 Jul 2017 Changyong Yu, Yunde Jia

We use the anisotropic diffusion to enhance the edges and boundary locations of a face image, and the kernel matrix model to extract face image features which we call the diffusion-kernel (D-K) features.

A Hybrid Data Association Framework for Robust Online Multi-Object Tracking

no code implementations31 Mar 2017 Min Yang, Yuwei Wu, Yunde Jia

In this paper, we present a hybrid data association framework with a min-cost multi-commodity network flow for robust online multi-object tracking.

Multi-Object Tracking Online Multi-Object Tracking

Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration

no code implementations11 May 2016 Jiaolong Yang, Hongdong Li, Dylan Campbell, Yunde Jia

The evaluation demonstrates that the proposed method is able to produce reliable registration results regardless of the initialization.

Temporal Dynamic Appearance Modeling for Online Multi-Person Tracking

no code implementations10 Oct 2015 Min Yang, Yunde Jia

The temporal dynamic makes a sufficient complement to the spatial structure of varying appearances in the feature space, which significantly improves the affinity measurement between trajectories and detections.

Discriminatively Trained And-Or Tree Models for Object Detection

no code implementations CVPR 2013 Xi Song, Tianfu Wu, Yunde Jia, Song-Chun Zhu

This paper presents a method of learning reconfigurable And-Or Tree (AOT) models discriminatively from weakly annotated data for object detection.

Object Detection

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