Search Results for author: Hua Yang

Found 20 papers, 4 papers with code

MCSD: An Efficient Language Model with Diverse Fusion

no code implementations18 Jun 2024 Hua Yang, Duohai Li, Shiman Li

MCSD model leverages diverse feature fusion, primarily through the multi-channel slope and decay (MCSD) block, to robustly represent features.

Language Modelling

FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences

no code implementations CVPR 2024 Haobo Xu, Jun Zhou, Hua Yang, Renjie Pan, Cunyan Li

Finding correspondences between images is essential for many computer vision tasks and sparse matching pipelines have been popular for decades.

Graph Neural Network Keypoint Detection

GelFlow: Self-supervised Learning of Optical Flow for Vision-Based Tactile Sensor Displacement Measurement

no code implementations13 Sep 2023 Zhiyuan Zhang, Hua Yang, Zhouping Yin

However, these methods need to be more precise for accurately measuring the displacement of markers during large elastic deformation of the gel, as this can significantly impact the accuracy of downstream tasks.

Optical Flow Estimation Self-Supervised Learning

Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

1 code implementation11 Jan 2023 Zhiqiang Shen, Peng Cao, Hua Yang, Xiaoli Liu, Jinzhu Yang, Osmar R. Zaiane

Combining the strengths of UMIX with CMT, UCMT can retain model disagreement and enhance the quality of pseudo labels for the co-training segmentation.

Image Segmentation Segmentation +2

Dynamic Spatial Propagation Network for Depth Completion

1 code implementation20 Feb 2022 Yuankai Lin, Tao Cheng, Qi Zhong, Wending Zhou, Hua Yang

Our solution is to estimate independent affinity matrices in each SPN iteration, but it is over-parameterized and heavy calculation.

Depth Completion

Subtask-dominated Transfer Learning for Long-tail Person Search

no code implementations1 Dec 2021 Chuang Liu, Hua Yang, Qin Zhou, Shibao Zheng

One major challenge comes from the imbalanced long-tail person identity distributions, which prevents the one-step person search model from learning discriminative person features for the final re-identification.

Human Detection Person Re-Identification +2

Efficient Context-Aware Network for Abdominal Multi-organ Segmentation

1 code implementation22 Sep 2021 Fan Zhang, Yu Wang, Hua Yang

For the context block, we propose strip pooling module to capture anisotropic and long-range contextual information, which exists in abdominal scene.

Decoder Organ Segmentation

Making Person Search Enjoy the Merits of Person Re-identification

no code implementations24 Aug 2021 Chuang Liu, Hua Yang, Qin Zhou, Shibao Zheng

In the proposed TDN, for better knowledge transfer from the Re-ID teacher model to the one-step person search model, we design a strong one-step person search base framework by partially disentangling the two subtasks.

Human Detection Person Re-Identification +3

MPASNET: Motion Prior-Aware Siamese Network for Unsupervised Deep Crowd Segmentation in Video Scenes

no code implementations21 Jan 2021 Jinhai Yang, Hua Yang

Crowd segmentation is a fundamental task serving as the basis of crowded scene analysis, and it is highly desirable to obtain refined pixel-level segmentation maps.

Segmentation Semantic Segmentation

Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding

no code implementations11 Jul 2020 Jinhai Yang, Hua Yang, Lin Chen

Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning.

Classification Few-Shot Learning +1

Attentive Semantic Exploring for Manipulated Face Detection

no code implementations6 May 2020 Zehao Chen, Hua Yang

Face manipulation methods develop rapidly in recent years, whose potential risk to society accounts for the emerging of researches on detection methods.

Face Detection Semantic Segmentation

Distribution Context Aware Loss for Person Re-identification

no code implementations17 Nov 2019 Zhigang Chang, Qin Zhou, Mingyang Yu, Shibao Zheng, Hua Yang, Tai-Pang Wu

To learn the optimal similarity function between probe and gallery images in Person re-identification, effective deep metric learning methods have been extensively explored to obtain discriminative feature embedding.

Clustering Metric Learning +1

Online Multi-Object Tracking with Dual Matching Attention Networks

1 code implementation ECCV 2018 Ji Zhu, Hua Yang, Nian Liu, Minyoung Kim, Wenjun Zhang, Ming-Hsuan Yang

In this paper, we propose an online Multi-Object Tracking (MOT) approach which integrates the merits of single object tracking and data association methods in a unified framework to handle noisy detections and frequent interactions between targets.

Multi-Object Tracking Object +1

Robust and Efficient Graph Correspondence Transfer for Person Re-identification

no code implementations15 May 2018 Qin Zhou, Heng Fan, Hua Yang, Hang Su, Shibao Zheng, Shuang Wu, Haibin Ling

To address this problem, in this paper, we present a robust and efficient graph correspondence transfer (REGCT) approach for explicit spatial alignment in Re-ID.

Graph Matching Person Re-Identification

Weighted Bilinear Coding over Salient Body Parts for Person Re-identification

no code implementations22 Mar 2018 Zhigang Chang, Qin Zhou, Heng Fan, Hang Su, Hua Yang, Shibao Zheng, Haibin Ling

Meanwhile, a weighting scheme is applied on the bilinear coding to adaptively adjust the weights of local features at different locations based on their importance in recognition, further improving the discriminability of feature aggregation.

Person Re-Identification

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