Search Results for author: Yifu Zhang

Found 13 papers, 3 papers with code

Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation

no code implementations28 Oct 2023 Haoran Shen, Yifu Zhang, Wenxuan Wang, Chen Chen, Jing Liu, Shanshan Song, Jiangyun Li

As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i. e. Med-DANet) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices.

MRI segmentation Quantization +1

DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model

no code implementations11 Oct 2023 Xiaofan Li, Yifu Zhang, Xiaoqing Ye

To alleviate the problem, we propose a spatial-temporal consistent diffusion framework DrivingDiffusion, to generate realistic multi-view videos controlled by 3D layout.

Autonomous Driving Image Generation +1

CityTrack: Improving City-Scale Multi-Camera Multi-Target Tracking by Location-Aware Tracking and Box-Grained Matching

no code implementations6 Jul 2023 Jincheng Lu, Xipeng Yang, Jin Ye, Yifu Zhang, Zhikang Zou, Wei zhang, Xiao Tan

Targets in urban traffic scenes often undergo occlusion, illumination changes, and perspective changes, making it difficult to associate targets across different cameras accurately.

Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity

no code implementations30 May 2023 Yifu Zhang, Hongru Li, Tao Yang, Rui Tao, Zhengyuan Liu, Shimeng Shi, Jiansong Zhang, Ning Ma, Wujin Feng, Zhanhu Zhang, Xinyu Zhang

Transfer learning provides the possibility to solve this problem, but there are too many features in natural images that are not related to the target domain.

Image Segmentation Lesion Segmentation +2

Multi-source adversarial transfer learning based on similar source domains with local features

no code implementations30 May 2023 Yifu Zhang, Hongru Li, Shimeng Shi, Youqi Li, Jiansong Zhang

In order to ensure that the data from the target domain in different sub-networks in the same batch is exactly the same, we designed a multi-source domain independent strategy to provide the possibility for later local feature fusion to complete the key features required.

Image Segmentation Semantic Segmentation +1

ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box

no code implementations27 Mar 2023 Yifu Zhang, Xinggang Wang, Xiaoqing Ye, Wei zhang, Jincheng Lu, Xiao Tan, Errui Ding, Peize Sun, Jingdong Wang

We propose a hierarchical data association strategy to mine the true objects in low-score detection boxes, which alleviates the problems of object missing and fragmented trajectories.

3D Multi-Object Tracking motion prediction

Robust Multi-Object Tracking by Marginal Inference

no code implementations7 Aug 2022 Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, Wenyu Liu

To address the problem, we present an efficient approach to compute a marginal probability for each pair of objects in real time.

Multi-Object Tracking

PlaneSDF-based Change Detection for Long-term Dense Mapping

no code implementations18 Jul 2022 Jiahui Fu, Chengyuan Lin, Yuichi Taguchi, Andrea Cohen, Yifu Zhang, Stephen Mylabathula, John J. Leonard

Given point clouds of the source and target scenes, we propose a three-step PlaneSDF-based change detection approach: (1) PlaneSDF volumes are instantiated within each scene and registered across scenes using plane poses; 2D height maps and object maps are extracted per volume via height projection and connected component analysis.

Change Detection object-detection +1

VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild

no code implementations5 Aug 2021 Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenyu Liu, Wenjun Zeng

We estimate 3D poses from the voxel representation by predicting whether each voxel contains a particular body joint.

Ranked #7 on 3D Multi-Person Pose Estimation on Panoptic (using extra training data)

3D Multi-Person Pose Estimation 3D Pose Estimation

FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking

30 code implementations4 Apr 2020 Yifu Zhang, Chunyu Wang, Xinggang Wang, Wen-Jun Zeng, Wenyu Liu

Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency.

 Ranked #1 on Multi-Object Tracking on 2DMOT15 (using extra training data)

Fairness Multi-Object Tracking +3

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