Search Results - "Lin, Xiangru"

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up by Ge, Weifeng, Lin, Xiangru, Yu, Yizhou

“…Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining…”
Get full text

I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation by Ma, Haoyu, Lin, Xiangru, Yu, Yizhou

“…Unsupervised domain adaptation (UDA) for semantic segmentation is a promising task freeing people from heavy annotation work. However, domain discrepancies in…”
Get full text

Design and Analysis of a Novel Flux Modulated Dual-Rotor Permanent Magnet Machine by Lin, Xiangru, Zhou, Li, Fang, Shuhua

“…The transmission and conversion of torque is an important link in hybrid electric vehicles (HEV), which is related to the quality and driving experience of…”
Get full text

Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization by Ma, Haoyu, Lin, Xiangru, Wu, Zifeng, Yu, Yizhou

“…Unsupervised domain adaptation (UDA) in semantic segmentation is a fundamental yet promising task relieving the need for laborious annotation works. However,…”
Get full text

Scene-Intuitive Agent for Remote Embodied Visual Grounding by Lin, Xiangru, Li, Guanbin, Yu, Yizhou

“…Humans learn from life events to form intuitions towards the understanding of visual environments and languages. Envision that you are instructed by a…”
Get full text

Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection by Liu, Chang, Zhang, Weiming, Lin, Xiangru, Zhang, Wei, Tan, Xiao, Han, Junyu, Li, Xiaomao, Ding, Errui, Wang, Jingdong

“…With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We…”
Get full text

Semi-DETR: Semi-Supervised Object Detection with Detection Transformers by Zhang, Jiacheng, Lin, Xiangru, Zhang, Wei, Wang, Kuo, Tan, Xiao, Han, Junyu, Ding, Errui, Wang, Jingdong, Li, Guanbin

“…We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect…”
Get full text

Comparative Analysis of a Novel Flux-Switching Arc Permanent Magnet Machine with Flux-Reversal Effect by Lin, Xiangru, Fang, Shuhua

“…This paper proposes a novel flux-switching arc permanent magnet (PM) machine (FSAPMM) with flux-reversal effect to improve the electromagnetic performances of…”
Get full text

I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation by Ma, Haoyu, Lin, Xiangru, Yu, Yizhou

“…Unsupervised domain adaptation (UDA) for semantic segmentation is a promising task freeing people from heavy annotation work. However, domain discrepancies in…”
Get full text

Sal-Guide Diffusion: Saliency Maps Guide Emotional Image Generation through Adapter by Lin, Xiangru, Zhong, Shenghua, Liu, Yan, Chen, Gong

“…The existing text-to-image generation methods based on stable diffusion yield better results in low-semantic prompt but often neglect the generation quality of…”
Get full text

Scene-Intuitive Agent for Remote Embodied Visual Grounding by Lin, Xiangru, Li, Guanbin, Yu, Yizhou

“…Humans learn from life events to form intuitions towards the understanding of visual environments and languages. Envision that you are instructed by a…”
Get full text

Semi-Stereo: A Universal Stereo Matching Framework for Imperfect Data via Semi-supervised Learning by Yue, Xin, Lu, Zongqing, Lin, Xiangru, Ren, Wenjia, Shao, Zhijing, Hu, Haonan, Zhang, Yu, Liao, Qingmin

“…Data matters in deep-learning-based binocular stereo matching. Obtaining a perfect dataset for stereo matching is hard and thus imperfect data is common in…”
Get full text

SplattingAvatar: Realistic Real-Time Human Avatars With Mesh-Embedded Gaussian Splatting by Shao, Zhijing, Wang, Zhaolong, Li, Zhuang, Wang, Duotun, Lin, Xiangru, Zhang, Yu, Fan, Mingming, Wang, Zeyu

“…We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting em-bedded on a triangle mesh, which renders over…”
Get full text

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting by Shao, Zhijing, Wang, Zhaolong, Li, Zhuang, Wang, Duotun, Lin, Xiangru, Zhang, Yu, Fan, Mingming, Wang, Zeyu

“…We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over…”
Get full text

SMPLX-Lite: A Realistic and Drivable Avatar Benchmark with Rich Geometry and Texture Annotations by Jiang, Yujiao, Liao, Qingmin, Wang, Zhaolong, Lin, Xiangru, Lu, Zongqing, Zhao, Yuxi, Wei, Hanqing, Ye, Jingrui, Zhang, Yu, Shao, Zhijing

“…Recovering photorealistic and drivable full-body avatars is crucial for numerous applications, including virtual reality, 3D games, and tele-presence. Most…”
Get full text

Decoupled Pseudo-Labeling for Semi-Supervised Monocular 3D Object Detection by Zhang, Jiacheng, Li, Jiaming, Lin, Xiangru, Zhang, Wei, Tan, Xiao, Han, Junyu, Ding, Errui, Wang, Jingdong, Li, Guanbin

“…We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM30D) and discover two primary issues: a misalignment between the prediction…”
Get full text

SMPLX-Lite: A Realistic and Drivable Avatar Benchmark with Rich Geometry and Texture Annotations by Jiang, Yujiao, Liao, Qingmin, Wang, Zhaolong, Lin, Xiangru, Lu, Zongqing, Zhao, Yuxi, Wei, Hanqing, Ye, Jingrui, Zhang, Yu, Shao, Zhijing

“…Recovering photorealistic and drivable full-body avatars is crucial for numerous applications, including virtual reality, 3D games, and tele-presence. Most…”
Get full text

Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection by Zhang, Jiacheng, Li, Jiaming, Lin, Xiangru, Zhang, Wei, Tan, Xiao, Han, Junyu, Ding, Errui, Wang, Jingdong, Li, Guanbin

“…We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction…”
Get full text

Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection by Li, Jiaming, Lin, Xiangru, Zhang, Wei, Tan, Xiao, Li, Yingying, Han, Junyu, Ding, Errui, Wang, Jingdong, Li, Guanbin

“…Current semi-supervised object detection (SSOD) algorithms typically assume class balanced datasets (PASCAL VOC etc.) or slightly class imbalanced datasets…”
Get full text

Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization by Ma, Haoyu, Lin, Xiangru, Wu, Zifeng, Yu, Yizhou

“…Unsupervised domain adaptation (UDA) in semantic segmentation is a fundamental yet promising task relieving the need for laborious annotation works. However,…”
Get full text