Publications on computer graphics and computer vision - SCIENCE CHINA Information Sciences

Special Focus on Deep Learning for Computer Vision
Highly Cited in 202401 RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 79

TransCrowd: weakly-supervised crowd counting with transformers
Liang, Dingkang; Chen, Xiwu; Xu, Wei; Zhou, Yu; Bai, Xiang
Sci China Inf Sci, 2022, 65(6): 160104

Keywords: crowd counting; visual transformer; weakly supervised; crowd analysis; transformer

Cite as: Liang D K, Chen X W, Xu W, et al. TransCrowd: weakly-supervised crowd counting with transformers. Sci China Inf Sci, 2022, 65(6): 160104, doi: 10.1007/s11432-021-3445-y

Special Focus on Deep Learning for Computer Vision
Highly Cited in 202401 RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 51

Progressive learning with multi-scale attention network for cross-domain vehicle re-identification
Wang, Yang; Peng, Jinjia; Wang, Huibing; Wang, Meng
Sci China Inf Sci, 2022, 65(6): 160103

Keywords: data adaptation module; weighted label smoothing loss; multi-scale attention network; vehicle re-identification

Cite as: Wang Y, Peng J J, Wang H B, et al. Progressive learning with multi-scale attention network for cross-domain vehicle re-identification. Sci China Inf Sci, 2022, 65(6): 160103, doi: 10.1007/s11432-021-3383-y

Highly Cited in 202311 RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 48

Learning practically feasible policies for online 3D bin packing
Zhao, Hang; Zhu, Chenyang; Xu, Xin; Huang, Hui; Xu, Kai
Sci China Inf Sci, 2022, 65(1): 112105

Keywords: bin packing problem; online 3d-bpp; reinforcement learning

Cite as: Zhao H, Zhu C Y, Xu X, et al. Learning practically feasible policies for online 3D bin packing. Sci China Inf Sci, 2022, 65(1): 112105, doi: 10.1007/s11432-021-3348-6

Highly Cited in 202303 RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 42

Learning hyperspectral images from RGB images via a coarse-to-fine CNN
Mei, Shaohui; Geng, Yunhao; Hou, Junhui; Du, Qian
Sci China Inf Sci, 2022, 65(5): 152102

Keywords: hyperspectral; reconstruction; convolutional neural network; deep learning

Cite as: Mei S H, Geng Y H, Hou J H, et al. Learning hyperspectral images from RGB images via a coarse-to-fine CNN. Sci China Inf Sci, 2022, 65(5): 152102, doi: 10.1007/s11432-020-3102-9

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 34

Densely nested top-down flows for salient object detection
Fang, Chaowei; Tian, Haibin; Zhang, Dingwen; Zhang, Qiang; Han, Jungong; Han, Junwei
Sci China Inf Sci, 2022, 65(8): 182103

Keywords: salient object detection; top-down flow; densely nested framework; convolutional neural networks

Cite as: Fang C W, Tian H B, Zhang D W, et al. Densely nested top-down flows for salient object detection. Sci China Inf Sci, 2022, 65(8): 182103, doi: 10.1007/s11432-021-3384-y

Special Focus on Deep Learning for Computer Vision
LETTER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 34

RLLNet: a lightweight remaking learning network for saliency redetection on RGB-D images
Zhou, Wujie; Liu, Chang; Lei, Jingsheng; Yu, Lu
Sci China Inf Sci, 2022, 65(6): 160107

Keywords: deep learning; rgb-d image; saliency detection; remaking learning; lightweight network

Cite as: Zhou W J, Liu C, Lei J S, et al. RLLNet: a lightweight remaking learning network for saliency redetection on RGB-D images. Sci China Inf Sci, 2022, 65(6): 160107, doi: 10.1007/s11432-020-3337-9

Highly Cited in 202401 RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 29

Class attention network for image recognition
Cheng, Gong; Lai, Pujian; Gao, Decheng; Han, Junwei
Sci China Inf Sci, 2023, 66(3): 132105

Keywords: visual attention; class-specific attention encoding; class attention network; dictionary learning

Cite as: Cheng G, Lai P J, Gao D C, et al. Class attention network for image recognition. Sci China Inf Sci, 2023, 66(3): 132105, doi: 10.1007/s11432-021-3493-7

Highly Cited in 202401 RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 19

Fewer is more: efficient object detection in large aerial images
Xie, Xingxing; Cheng, Gong; Li, Qingyang; Miao, Shicheng; Li, Ke; Han, Junwei
Sci China Inf Sci, 2024, 67(1): 112106

Keywords: efficient object detection; large aerial images; objectness activation network

Cite as: Xie X X, Cheng G, Li Q Y, et al. Fewer is more: efficient object detection in large aerial images. Sci China Inf Sci, 2024, 67(1): 112106, doi: 10.1007/s11432-022-3718-5

LETTER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 15

Human motion segmentation based on structure constraint matrix factorization
Gao, Hongbo; Guo, Fang; Zhu, Juping; Kan, Zhen; Zhang, Xinyu
Sci China Inf Sci, 2022, 65(1): 119103

Keywords: computer vision; human motion segmentation; spectral clustering; structure constraint; matrix factorization

Cite as: Gao H B, Guo F, Zhu J P, et al. Human motion segmentation based on structure constraint matrix factorization. Sci China Inf Sci, 2022, 65(1): 119103, doi: 10.1007/s11432-020-2967-3

REVIEW Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 14

Survey on rain removal from videos or a single image
Wang, Hong; Wu, Yichen; Li, Minghan; Zhao, Qian; Meng, Deyu
Sci China Inf Sci, 2022, 65(1): 111101

Keywords: rain removal; maximum a posterior estimation; deep learning; generalization performance; comprehensive repository

Cite as: Wang H, Wu Y C, Li M H, et al. Survey on rain removal from videos or a single image. Sci China Inf Sci, 2022, 65(1): 111101, doi: 10.1007/s11432-020-3225-9

RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 12

Fast target-aware learning for few-shot video object segmentation
Chen, Yadang; Hao, Chuanyan; Yang, Zhi-Xin; Wu, Enhua
Sci China Inf Sci, 2022, 65(8): 182104

Keywords: video object segmentation; few-shot; target-aware; meta knowledge; bilevel-optimization

Cite as: Chen Y D, Hao C Y, Yang Z-X, et al. Fast target-aware learning for few-shot video object segmentation. Sci China Inf Sci, 2022, 65(8): 182104, doi: 10.1007/s11432-021-3396-7

NEWS & VIEWS Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 10

RPC: a large-scale and fine-grained retail product checkout dataset
WEI, Xiu-Shen; CUI, Quan; YANG, Lei; WANG, Peng; LIU, Lingqiao; YANG, Jian
Sci China Inf Sci, 2022, 65(9): 197101

Keywords: Automatic Check-Out; Benchmark Datasets; Retail Product Recognition; Fine-Grained Recognition; Deep Learning

Cite as: Wei X-S, Cui Q, Yang L, et al. RPC: a large-scale and fine-grained retail product checkout dataset. Sci China Inf Sci, 2022, 65(9): 197101, doi: 10.1007/s11432-022-3513-y

Special Focus on Deep Learning for Computer Vision
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 9

Onfocus detection: identifying individual-camera eye contact from unconstrained images
Zhang, Dingwen; Wang, Bo; Wang, Gerong; Zhang, Qiang; Zhang, Jiajia; Han, Jungong; You, Zheng
Sci China Inf Sci, 2022, 65(6): 160101

Keywords: onfocus detection; deep neural network; capsule routing; computer vision; deep learning

Cite as: Zhang D W, Wang B, Wang G R, et al. Onfocus detection: identifying individual-camera eye contact from unconstrained images. Sci China Inf Sci, 2022, 65(6): 160101, doi: 10.1007/s11432-020-3181-9

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 8

RGBT tracking via reliable feature configuration
Tu, Zhengzheng; Pan, Wenli; Duan, Yunsheng; Tang, Jin; Li, Chenglong
Sci China Inf Sci, 2022, 65(4): 142101

Keywords: rgbt tracking; multi-modal; reliability guideline; feature configuration; correlation filter

Cite as: Tu Z Z, Pan W L, Duan Y S, et al. RGBT tracking via reliable feature configuration. Sci China Inf Sci, 2022, 65(4): 142101, doi: 10.1007/s11432-020-3160-5

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 6

Contextual and selective attention networks for image captioning
Wang, Jing; Li, Yehao; Pan, Yingwei; Yao, Ting; Tang, Jinhui; Mei, Tao
Sci China Inf Sci, 2022, 65(12): 222103

Keywords: image captioning; hybrid attention; contextual attention

Cite as: Wang J, Li Y H, Pan Y W, et al. Contextual and selective attention networks for image captioning. Sci China Inf Sci, 2022, 65(12): 222103, doi: 10.1007/s11432-020-3523-6

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 6

Quantized and adaptive memristor based CNN (QA-mCNN) for image processing
Hu, Xiaofang; Shi, Wenqiang; Zhou, Yue; Tang, Hongan; Duan, Shukai
Sci China Inf Sci, 2022, 65(1): 119104

Keywords: adaptive template; incremental network quantization; optimization; cnn; memristor

Cite as: Hu X F, Shi W Q, Zhou Y, et al. Quantized and adaptive memristor based CNN (QA-mCNN) for image processing. Sci China Inf Sci, 2022, 65(1): 119104, doi: 10.1007/s11432-020-3031-9

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 5

A unified pruning framework for vision transformers
Yu, Hao; Wu, Jianxin
Sci China Inf Sci, 2023, 66(7): 179101

Keywords: vision transformer; structural pruning; image classification; object detection; language modeling

Cite as: Yu H, Wu J X. A unified pruning framework for vision transformers. Sci China Inf Sci, 2023, 66(7): 179101, doi: 10.1007/s11432-022-3646-6

REVIEW Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 5

Survey on leveraging pre-trained generative adversarial networks for image editing and restoration
Liu, Ming; Wei, Yuxiang; Wu, Xiaohe; Zuo, Wangmeng; Zhang, Lei
Sci China Inf Sci, 2023, 66(5): 151101

Keywords: survey; generative adversarial networks; pre-trained models; image editing; image restoration

Cite as: Liu M, Wei Y X, Wu X H, et al. Survey on leveraging pre-trained generative adversarial networks for image editing and restoration. Sci China Inf Sci, 2023, 66(5): 151101, doi: 10.1007/s11432-022-3679-0

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 5

Unpaired remote sensing image super-resolution with content-preserving weak supervision neural network
Wu, Jie; Cong, Runmin; Fang, Leyuan; Guo, Chunle; Zhang, Bob; Ghamisi, Pedram
Sci China Inf Sci, 2023, 66(1): 119105

Keywords: deep learning; remote sensing images; super-resolution; unpaired training; weak supervision

Cite as: Wu J, Cong R M, Fang L Y, et al. Unpaired remote sensing image super-resolution with content-preserving weak supervision neural network. Sci China Inf Sci, 2023, 66(1): 119105, doi: 10.1007/s11432-021-3575-1

RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 5

On learning the right attention point for feature enhancement
Lin, Liqiang; Huang, Pengdi; Fu, Chi-Wing; Xu, Kai; Zhang, Hao; Huang, Hui
Sci China Inf Sci, 2023, 66(1): 112107

Keywords: point convolution; feature enhancement; attention point; deep neural network

Cite as: Lin L Q, Huang P D, Fu C-W, et al. On learning the right attention point for feature enhancement. Sci China Inf Sci, 2023, 66(1): 112107, doi: 10.1007/s11432-021-3431-9

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 5

Evolution of AVS video coding standards: twenty years of innovation and development
Ma, Siwei; Zhang, Li; Wang, Shiqi; Jia, Chuanmin; Wang, Shanshe; Huang, Tiejun; Wu, Feng; Gao, Wen
Sci China Inf Sci, 2022, 65(9): 192101

Keywords: video coding; AVS standards; video applications; intelligent coding

Cite as: Ma S W, Zhang L, Wang S Q, et al. Evolution of AVS video coding standards: twenty years of innovation and development. Sci China Inf Sci, 2022, 65(9): 192101, doi: 10.1007/s11432-021-3461-9

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 5

Heterogeneous memory enhanced graph reasoning network for cross-modal retrieval
Ji, Zhong; Chen, Kexin; He, Yuqing; Pang, Yanwei; Li, Xuelong
Sci China Inf Sci, 2022, 65(7): 172104

Keywords: cross-modal retrieval; graph reasoning; memory network; visual semantic embedding; image-text retrieval; video-text retrieval

Cite as: Ji Z, Chen K X, He Y Q, et al. Heterogeneous memory enhanced graph reasoning network for cross-modal retrieval. Sci China Inf Sci, 2022, 65(7): 172104, doi: 10.1007/s11432-021-3367-y

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 4

Siamese transformer with hierarchical concept embedding for fine-grained image recognition
Lyu, Yilin; Jing, Liping; Wang, Jiaqi; Guo, Mingzhe; Wang, Xinyue; Yu, Jian
Sci China Inf Sci, 2023, 66(3): 132107

Keywords: fine-grained image recognition; transformer; hierarchical concept embedding; adaptive sampling; Siamese network

Cite as: Lyu Y L, Jing L P, Wang J Q, et al. Siamese transformer with hierarchical concept embedding for fine-grained image recognition. Sci China Inf Sci, 2023, 66(3): 132107, doi: 10.1007/s11432-022-3586-y

Special Focus on Deep Learning for Computer Vision
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 4

Prototype-based classifier learning for long-tailed visual recognition
Wei, Xiu-Shen; Xu, Shu-Lin; Chen, Hao; Xiao, Liang; Peng, Yuxin
Sci China Inf Sci, 2022, 65(6): 160105

Keywords: long-tailed distribution; categorical prototype; classifier generation; classifier calibration; class imbalance

Cite as: Wei X-S, Xu S-L, Chen H, et al. Prototype-based classifier learning for long-tailed visual recognition. Sci China Inf Sci, 2022, 65(6): 160105, doi: 10.1007/s11432-021-3489-1

PERSPECTIVE Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

SAM struggles in concealed scenes - empirical study on "Segment Anything"
Ji, Ge-Peng; Fan, Deng-Ping; Xu, Peng; Zhou, Bowen; Cheng, Ming-Ming; Van Gool, Luc
Sci China Inf Sci, 2023, 66(12): 226101

Keywords: Segment Anything; SAM; Camouflaged; Concealed Scene Understanding; Concealed Object Segmentation

Cite as: Ji G-P, Fan D-P, Xu P, et al. SAM struggles in concealed scenes - empirical study on "Segment Anything". Sci China Inf Sci, 2023, 66(12): 226101, doi: 10.1007/s11432-023-3881-x

Special Topic: Deep Learning for Computer Vision
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

Sparse spatial transformers for few-shot learning
Chen, Haoxing; Li, Huaxiong; Li, Yaohui; Chen, Chunlin
Sci China Inf Sci, 2023, 66(11): 210102

Keywords: few-shot learning; transformer; metric-learning; cross-attention

Cite as: Chen H X, Li H X, Li Y H, et al. Sparse spatial transformers for few-shot learning. Sci China Inf Sci, 2023, 66(11): 210102, doi: 10.1007/s11432-022-3700-8

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

ViGT: proposal-free video grounding with a learnable token in the transformer
Li, Kun; Guo, Dan; Wang, Meng
Sci China Inf Sci, 2023, 66(10): 202102

Keywords: video grounding; temporal sentence grounding; boundary regression; token learning; proposal-free

Cite as: Li K, Guo D, Wang M. ViGT: proposal-free video grounding with a learnable token in the transformer. Sci China Inf Sci, 2023, 66(10): 202102, doi: 10.1007/s11432-022-3783-3

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

Augmented FCN: rethinking context modeling for semantic segmentation
Zhang, Dong; Zhang, Liyan; Tang, Jinhui
Sci China Inf Sci, 2023, 66(4): 142105

Keywords: semantic segmentation; context modeling; long-range dependencies; attention mechanism

Cite as: Zhang D, Zhang L Y, Tang J H. Augmented FCN: rethinking context modeling for semantic segmentation. Sci China Inf Sci, 2023, 66(4): 142105, doi: 10.1007/s11432-021-3590-1

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

TinyDet: accurately detecting small objects within 1 GFLOPs
Chen, Shaoyu; Cheng, Tianheng; Fang, Jiemin; Zhang, Qian; Li, Yuan; Liu, Wenyu; Wang, Xinggang
Sci China Inf Sci, 2023, 66(1): 119102

Keywords: small object detection; lightweight networ; generic object detection; Tiny AI; high resolution

Cite as: Chen S Y, Cheng T H, Fang J M, et al. TinyDet: accurately detecting small objects within 1 GFLOPs. Sci China Inf Sci, 2023, 66(1): 119102, doi: 10.1007/s11432-021-3504-4

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

Point attention network for point cloud semantic segmentation
Ren, Dayong; Wu, Zhengyi; Li, Jiawei; Yu, Piaopiao; Guo, Jie; Wei, Mingqiang; Guo, Yanwen
Sci China Inf Sci, 2022, 65(9): 192104

Keywords: point cloud; semantic segmentation; self-attention mechanism; deep learning; long-range dependencies

Cite as: Ren D Y, Wu Z Y, Li J W, et al. Point attention network for point cloud semantic segmentation. Sci China Inf Sci, 2022, 65(9): 192104, doi: 10.1007/s11432-021-3387-7

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

Difficulty-aware bi-network with spatial attention constrained graph for axillary lymph node segmentation
Xu, Qing; Xi, Xiaoming; Meng, Xianjing; Qin, Zheyun; Nie, Xiushan; Wu, Yongjian; Zhou, Dongsheng; Qu, Yi; Li, Chenglong; Yin, Yilong
Sci China Inf Sci, 2022, 65(9): 192102

Keywords: ultrasound image; axillary lymph nodes segmentation; difficulty-aware segmentation; graph with spatial attention

Cite as: Xu Q, Xi X M, Meng X J, et al. Difficulty-aware bi-network with spatial attention constrained graph for axillary lymph node segmentation. Sci China Inf Sci, 2022, 65(9): 192102, doi: 10.1007/s11432-020-3079-8

Special Focus on Deep Learning for Computer Vision
LETTER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

Human-object interaction detection via interactive visual-semantic graph learning
Wu, Tongtong; Duan, Fuqing; Chang, Liang; Lu, Ke
Sci China Inf Sci, 2022, 65(6): 160108

Keywords: human-object interaction; context modeling; graph learning; interactive graph; visual-semantic graph

Cite as: Wu T T, Duan F Q, Chang L, et al. Human-object interaction detection via interactive visual-semantic graph learning. Sci China Inf Sci, 2022, 65(6): 160108, doi: 10.1007/s11432-021-3427-2

Special Focus on Deep Learning for Computer Vision
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 3

HAPNet: a head-aware pedestrian detection network associated with the affinity field
Ding, Jiali; Liu, Tie; Zhao, Yun; Yuan, Zejian; Shang, Yuanyuan
Sci China Inf Sci, 2022, 65(6): 160102

Keywords: pedestrian detection; head detection; head-aware pedestrian network; affinity module; occlusion

Cite as: Ding J L, Liu T, Zhao Y, et al. HAPNet: a head-aware pedestrian detection network associated with the affinity field. Sci China Inf Sci, 2022, 65(6): 160102, doi: 10.1007/s11432-021-3300-2

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

RGB oralscan video-based orthodontic treatment monitoring
Tian, Yan; Fu, Hanshi; Wang, Hao; Liu, Yuqi; Xu, Zhaocheng; Chen, Hong; Li, Jianyuan; Wang, Ruili
Sci China Inf Sci, 2024, 67(1): 112107

Keywords: digital dentistry; object 6D pose estimation; deep learning; computer vision

Cite as: Tian Y, Fu H S, Wang H, et al. RGB oralscan video-based orthodontic treatment monitoring. Sci China Inf Sci, 2024, 67(1): 112107, doi: 10.1007/s11432-023-3847-x

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

Improving pseudo-labeling with reliable inter-camera distance encouragement for unsupervised person re-identification
Chen, Yiyu; Fan, Zheyi; Chen, Shuni; Zhu, Yixuan
Sci China Inf Sci, 2023, 66(5): 152103

Keywords: person re-identification; noise label; camera variation; clustering; deep learning

Cite as: Chen Y Y, Fan Z Y, Chen S N, et al. Improving pseudo-labeling with reliable inter-camera distance encouragement for unsupervised person re-identification. Sci China Inf Sci, 2023, 66(5): 152103, doi: 10.1007/s11432-022-3628-y

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

Adaptive structured sparse multiview canonical correlation analysis for multimodal brain imaging association identification
Du, Lei; Wang, Huiai; Zhang, Jin; Zhang, Shu; Guo, Lei; Han, Junwei
Sci China Inf Sci, 2023, 66(4): 142106

Keywords: multimodal brain imaging correlation; sparse multiview canonical correlation analysis; task imbalance; adaptive loss balancing; graph-group penalty

Cite as: Du L, Wang H A, Zhang J, et al. Adaptive structured sparse multiview canonical correlation analysis for multimodal brain imaging association identification. Sci China Inf Sci, 2023, 66(4): 142106, doi: 10.1007/s11432-021-3589-5

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

Deep graph learning for spatially-varying indoor lighting prediction
Bai, Jiayang; Guo, Jie; Wang, Chenchen; Chen, Zhenyu; He, Zhen; Yang, Shan; Yu, Piaopiao; Zhang, Yan; Guo, Yanwen
Sci China Inf Sci, 2023, 66(3): 132106

Keywords: lighting; graph learning; augmented reality; spherical Gaussians; rendering

Cite as: Bai J Y, Guo J, Wang C C, et al. Deep graph learning for spatially-varying indoor lighting prediction. Sci China Inf Sci, 2023, 66(3): 132106, doi: 10.1007/s11432-022-3576-9

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

Repeatable adaptive keypoint detection via self-supervised learning
Yan, Pei; Tan, Yihua; Tai, Yuan
Sci China Inf Sci, 2022, 65(11): 212103

Keywords: keypoint detection; convolutional neural network; image matching; self-supervised learning; repeatable

Cite as: Yan P, Tan Y H, Tai Y. Repeatable adaptive keypoint detection via self-supervised learning. Sci China Inf Sci, 2022, 65(11): 212103, doi: 10.1007/s11432-021-3364-5

MOOP Supplementary Video Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

Reverse erasure guided spatio-temporal autoencoder with compact feature representation for video anomaly detection
Zhong, Yuanhong; Chen, Xia; Jiang, Jinyang; Ren, Fan
Sci China Inf Sci, 2022, 65(9): 194101

Keywords: anomaly detection; dual-encoder single-decoder network; reverse erasure; compact feature representation; deep support vector data description

Cite as: Zhong Y H, Chen X, Jiang J Y, et al. Reverse erasure guided spatio-temporal autoencoder with compact feature representation for video anomaly detection. Sci China Inf Sci, 2022, 65(9): 194101, doi: 10.1007/s11432-021-3444-9

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

Indoor layout programming via virtual navigation detectors
Fu, Qiang; Fu, Hongbo; Deng, Zhigang; Li, Xueming
Sci China Inf Sci, 2022, 65(8): 189101

Keywords: 3d modeling; indoor scene synthesis; layout programming; indoor navigation; deep reinforcement learning

Cite as: Fu Q, Fu H B, Deng Z G, et al. Indoor layout programming via virtual navigation detectors. Sci China Inf Sci, 2022, 65(8): 189101, doi: 10.1007/s11432-019-2930-x

LETTER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

VNet: a versatile network to train real-time semantic segmentation models on a single GPU
Li, Wenxing; Lin, Ning; Zhang, Mingzhe; Lu, Hang; Chen, Xiaoming; Li, Xiaowei
Sci China Inf Sci, 2022, 65(3): 139105

Keywords: efficiency; machine learning; real-time systems; segmentation; light-weight

Cite as: Li W X, Lin N, Zhang M Z, et al. VNet: a versatile network to train real-time semantic segmentation models on a single GPU. Sci China Inf Sci, 2022, 65(3): 139105, doi: 10.1007/s11432-020-2971-8

MOOP Video Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 2

Automatic image matting and fusing for portrait synthesis
Yi, Zhike; Song, Wenfeng; Li, Shuai; Hao, Aimin
Sci China Inf Sci, 2022, 65(2): 124101

Keywords: neural network; automatic image matting; image fusion; deep learning; gradient domain

Cite as: Yi Z K, Song W F, Li S, et al. Automatic image matting and fusing for portrait synthesis. Sci China Inf Sci, 2022, 65(2): 124101, doi: 10.1007/s11432-021-3279-y

MOOP Supplementary Video Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

ASPPR: active single-image piecewise planar 3D reconstruction based on geometric priors
Wang, Wei; Dong, Qiulei; Hu, Zhanyi
Sci China Inf Sci, 2023, 66(7): 174101

Keywords: single-image reconstruction; geometric prior; user interaction; multi-plane optimization; convolutional neural network

Cite as: Wang W, Dong Q L, Hu Z Y. ASPPR: active single-image piecewise planar 3D reconstruction based on geometric priors. Sci China Inf Sci, 2023, 66(7): 174101, doi: 10.1007/s11432-022-3631-6

RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

Reflectance edge guided networks for detail-preserving intrinsic image decomposition
Li, Quewei; Guo, Jie; Wu, Zhengyi; Fei, Yang; Guo, Yanwen
Sci China Inf Sci, 2023, 66(2): 122105

Keywords: intrinsic image decomposition; detail-preserving; reflectance edges

Cite as: Li Q W, Guo J, Wu Z Y, et al. Reflectance edge guided networks for detail-preserving intrinsic image decomposition. Sci China Inf Sci, 2023, 66(2): 122105, doi: 10.1007/s11432-021-3481-3

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

Difficulty-aware prior-guided hierarchical network for adaptive segmentation of breast tumors
Hussain, Sumaira; Xi, Xiaoming; Ullah, Inam; Naim, Syeda Wajiha; Shaheed, Kashif; Tian, Cuihuan; Yin, Yilong
Sci China Inf Sci, 2023, 66(2): 122104

Keywords: breast tumor; ultrasound image segmentation; deep neural network; difficulty-awareness

Cite as: Hussain S, Xi X M, Ullah I, et al. Difficulty-aware prior-guided hierarchical network for adaptive segmentation of breast tumors. Sci China Inf Sci, 2023, 66(2): 122104, doi: 10.1007/s11432-021-3340-y

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

BiTGAN: bilateral generative adversarial networks for Chinese ink wash painting style transfer
He, Xiao; Zhu, Mingrui; Wang, Nannan; Wang, Xiaoyu; Gao, Xinbo
Sci China Inf Sci, 2023, 66(1): 119104

Keywords: Chinese ink wash painting; image style transfer; image-to-image translation; generative adversarial networks; GAN; bilateral-generator

Cite as: He X, Zhu M R, Wang N N, et al. BiTGAN: bilateral generative adversarial networks for Chinese ink wash painting style transfer. Sci China Inf Sci, 2023, 66(1): 119104, doi: 10.1007/s11432-022-3541-x

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

Learning cross-modal interaction for RGB-T tracking
Xu, Chunyan; Cui, Zhen; Wang, Chaoqun; Zhou, Chuanwei; Yang, Jian
Sci China Inf Sci, 2023, 66(1): 119103

Keywords: RGB-T tracking; cross-modal interaction; pixel-level correlation; relation-level correlation; visual object tracking

Cite as: Xu C Y, Cui Z, Wang C Q, et al. Learning cross-modal interaction for RGB-T tracking. Sci China Inf Sci, 2023, 66(1): 119103, doi: 10.1007/s11432-021-3518-y

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

Image co-segmentation based on pyramid features cross-correlation network
Chen, Jia; Chen, Yasong; Li, Weihao; Liu, Zhi; Liu, Sannyuya; Yang, Zongkai
Sci China Inf Sci, 2023, 66(1): 119101

Keywords: image co-segmentation; pyramid features; deep learning; pair-wise manner; VGG16

Cite as: Chen J, Chen Y S, Li W H, et al. Image co-segmentation based on pyramid features cross-correlation network. Sci China Inf Sci, 2023, 66(1): 119101, doi: 10.1007/s11432-021-3515-6

RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

Model-guided 3D stitching for augmented virtual environment
Zhou, Zhong; Meng, Ming; Zhou, Yi; Zhu, Zhe; You, Jingdi
Sci China Inf Sci, 2023, 66(1): 112106

Keywords: 3D stitching; video model; multiple video visualization; augmented virtual environment

Cite as: Zhou Z, Meng M, Zhou Y, et al. Model-guided 3D stitching for augmented virtual environment. Sci China Inf Sci, 2023, 66(1): 112106, doi: 10.1007/s11432-021-3323-2

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

A novel vision-based multi-task robotic grasp detection method for multi-object scenes
Song, Yanan; Gao, Liang; Li, Xinyu; Shen, Weiming; Peng, Kunkun
Sci China Inf Sci, 2022, 65(12): 222104

Keywords: robotic grasp detection; multi-object scene; object detection; grasp matching strategy; deep learning

Cite as: Song Y N, Gao L, Li X Y, et al. A novel vision-based multi-task robotic grasp detection method for multi-object scenes. Sci China Inf Sci, 2022, 65(12): 222104, doi: 10.1007/s11432-021-3558-y

Special Focus on Deep Learning for Computer Vision
NEWS & VIEWS Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

Comprehensive benchmark datasets for Amharic scene text detection and recognition
DIKUBAB, Wondimu; LIANG, Dingkang; LIAO, Minghui; BAI, Xiang
Sci China Inf Sci, 2022, 65(6): 160106

Keywords: Amharic script; scene text; text detection; text recognition; Amharic text

Cite as: Dikubab W, Liang D K, Liao M H, et al. Comprehensive benchmark datasets for Amharic scene text detection and recognition. Sci China Inf Sci, 2022, 65(6): 160106, doi: 10.1007/s11432-021-3447-9

LETTER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

Self-adjustable hyper-graphs for video pose estimation based on spatial-temporal subspace construction
Ma, Jizhou; Li, Shuai; Qin, Hong; Hao, Aimin; Zhao, Qinping
Sci China Inf Sci, 2022, 65(3): 139101

Keywords: video pose estimation; self-adjustable hyper-graph; spatial-temporal subspace exploration; maximum matching subspace operator; action pattern

Cite as: Ma J Z, Li S, Qin H, et al. Self-adjustable hyper-graphs for video pose estimation based on spatial-temporal subspace construction. Sci China Inf Sci, 2022, 65(3): 139101, doi: 10.1007/s11432-019-2869-x

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 1

AR-CNN: an attention ranking network for learning urban perception
Li, Zhetao; Chen, Ziwen; Zheng, Wei-Shi; Oh, Sangyoon; Nguyen, Kien
Sci China Inf Sci, 2022, 65(1): 112104

Keywords: ranking network; urban perception; attribute learning; attention network; colour and texture

Cite as: Li Z T, Chen Z W, Zheng W-S, et al. AR-CNN: an attention ranking network for learning urban perception. Sci China Inf Sci, 2022, 65(1): 112104, doi: 10.1007/s11432-019-2899-9

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Pyramid-resolution person restoration for cross-resolution person re-identification
Peng, Chunlei; Wang, Bo; Liu, Decheng; Wang, Nannan; Gao, Xinbo
Sci China Inf Sci, 2024, 67(6): 169101

Keywords: pyramid-resolution; cross-resolution person ReID; image restoration; feature distance fusion; multi-resolution person ReID

Cite as: Peng C L, Wang B, Liu D C, et al. Pyramid-resolution person restoration for cross-resolution person re-identification. Sci China Inf Sci, 2024, 67(6): 169101, doi: 10.1007/s11432-023-4023-y

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Meta label associated loss for fine-grained visual recognition
Li, Yanchao; Xiao, Fu; Li, Hao; Li, Qun; Yu, Shui
Sci China Inf Sci, 2024, 67(6): 162102

Keywords: label associated loss; weighting noisy samples; fine-grained visual recognition; noise-tolerant learning; meta-learning

Cite as: Li Y C, Xiao F, Li H, et al. Meta label associated loss for fine-grained visual recognition. Sci China Inf Sci, 2024, 67(6): 162102, doi: 10.1007/s11432-023-3922-2

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

SAM3D: zero-shot 3D object detection via the segment anything model
Zhang, Dingyuan; Liang, Dingkang; Yang, Hongcheng; Zou, Zhikang; Ye, Xiaoqing; Liu, Zhe; Bai, Xiang
Sci China Inf Sci, 2024, 67(4): 149101

Keywords: Zero-shot 3D Object Detection; Foundation Model; Segment Anything Model; BEV Perception; Segmentation

Cite as: Zhang D Y, Liang D K, Yang H C, et al. SAM3D: zero-shot 3D object detection via the segment anything model. Sci China Inf Sci, 2024, 67(4): 149101, doi: 10.1007/s11432-023-3943-6

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Retrieval-and-alignment based large-scale indoor point cloud semantic segmentation
Xu, Zongyi; Huang, Xiaoshui; Yuan, Bo; Wang, Yangfu; Zhang, Qianni; Li, Weisheng; Gao, Xinbo
Sci China Inf Sci, 2024, 67(4): 142104

Keywords: point cloud semantic segmentation; large-scale indoor point clouds; point cloud alignment; overlap estimation; label transfer

Cite as: Xu Z Y, Huang X S, Yuan B, et al. Retrieval-and-alignment based large-scale indoor point cloud semantic segmentation. Sci China Inf Sci, 2024, 67(4): 142104, doi: 10.1007/s11432-022-3928-x

LETTER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Scene text recognition via dual character counting-aware visual and semantic modeling network
Xiao, Ke; Zhu, Anna; Iwana, Brian Kenji; Liu, Cheng-Lin
Sci China Inf Sci, 2024, 67(3): 139101

Keywords: scene text recognition; language model; document analysis; deep learning; attention mechanism

Cite as: Xiao K, Zhu A N, K Iwana B K, et al. Scene text recognition via dual character counting-aware visual and semantic modeling network. Sci China Inf Sci, 2024, 67(3): 139101, doi: 10.1007/s11432-023-3935-8

Special Topic: Deep Learning for Computer Vision
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Confidence-weighted mutual supervision on dual networks for unsupervised cross-modality image segmentation
Chen, Yajie; Yang, Xin; Bai, Xiang
Sci China Inf Sci, 2023, 66(11): 210104

Keywords: domain adaptation; pseudo label; mutual supervision; cross-modality; image segmentation

Cite as: Chen Y J, Yang X, Bai X. Confidence-weighted mutual supervision on dual networks for unsupervised cross-modality image segmentation. Sci China Inf Sci, 2023, 66(11): 210104, doi: 10.1007/s11432-022-3871-0

Special Topic: Deep Learning for Computer Vision
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

A meaningful learning method for zero-shot semantic segmentation
Liu, Xianglong; Bai, Shihao; An, Shan; Wang, Shuo; Liu, Wei; Zhao, Xiaowei; Ma, Yuqing
Sci China Inf Sci, 2023, 66(11): 210103

Keywords: meaningful learning; zero-shot learning; semantic segmentation; conjugate conceptual correlation; fast-slow conceptual modulator

Cite as: Liu X L, Bai S H, An S, et al. A meaningful learning method for zero-shot semantic segmentation. Sci China Inf Sci, 2023, 66(11): 210103, doi: 10.1007/s11432-022-3748-5

Special Topic: Deep Learning for Computer Vision
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

An end-to-end network for co-saliency detection in one single image
Yue, Yuanhao; Zou, Qin; Yu, Hongkai; Wang, Qian; Wang, Zhongyuan; Wang, Song
Sci China Inf Sci, 2023, 66(11): 210101

Keywords: saliency detection; convolutional neural network; regional feature mapping; co-saliency detection; deep learning

Cite as: Yue Y H, Zou Q, Yu H K, et al. An end-to-end network for co-saliency detection in one single image. Sci China Inf Sci, 2023, 66(11): 210101, doi: 10.1007/s11432-022-3686-1

MOOP Supplementary Video Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

A unified user behavior model for trajectory-based tasks with different types of path constraints
Zhang, Hao; Huang, Jin; Tu, Huawei; Tian, Feng; Dai, Guozhong; Wang, Hongan
Sci China Inf Sci, 2023, 66(10): 204101

Keywords: human-computer interaction; user behavior modeling; artificial potential field; trajectory-based task; trajectory predicting

Cite as: Zhang H, Huang J, Tu H W, et al. A unified user behavior model for trajectory-based tasks with different types of path constraints. Sci China Inf Sci, 2023, 66(10): 204101, doi: 10.1007/s11432-023-3779-5

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

NeuralReshaper: single-image human-body retouching with deep neural networks
Chen, Beijia; Shen, Yuefan; Fu, Hongbo; Chen, Xiang; Zhou, Kun; Zheng, Youyi
Sci China Inf Sci, 2023, 66(9): 199101

Keywords: image manipulation; human-body reshaping; deep neural networks; generative adversarial network; self-supervised learning

Cite as: Chen B J, Shen Y F, Fu H B, et al. NeuralReshaper: single-image human-body retouching with deep neural networks. Sci China Inf Sci, 2023, 66(9): 199101, doi: 10.1007/s11432-022-3675-1

RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Hybrid3D: learning 3D hybrid features with point clouds and multi-view images for point cloud registration
Yang, Bangbang; Huang, Zhaoyang; Li, Yijin; Zhou, Han; Li, Hongsheng; Zhang, Guofeng; Bao, Hujun
Sci China Inf Sci, 2023, 66(7): 172101

Keywords: point cloud registration; cross-modal feature fusion; multi-view feature fusion; computer vision; deep learning

Cite as: Yang B B, Huang Z Y, Li Y J, et al. Hybrid3D: learning 3D hybrid features with point clouds and multi-view images for point cloud registration. Sci China Inf Sci, 2023, 66(7): 172101, doi: 10.1007/s11432-022-3604-6

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

An energy constraint position-based dynamics with corrected SPH kernel
Cao, Wei; Lyu, Luan; Yang, Zhixin; Wu, Enhua
Sci China Inf Sci, 2023, 66(1): 112108

Keywords: position-based dynamics; deformable solids; continuum mechanics

Cite as: Cao W, Lyu L, Yang Z X, et al. An energy constraint position-based dynamics with corrected SPH kernel. Sci China Inf Sci, 2023, 66(1): 112108, doi: 10.1007/s11432-021-3464-2

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Reconstructing and editing fluids using the adaptive multilayer external force guiding model
Nie, Xiaoying; Hu, Yong; Shen, Xukun; Su, Zhiyuan
Sci China Inf Sci, 2022, 65(11): 212102

Keywords: reconstructing fluids; editing fluids; monocular videos; adaptive multilayer external force guiding model; generation and extinction model

Cite as: Nie X Y, Hu Y, Shen X K, et al. Reconstructing and editing fluids using the adaptive multilayer external force guiding model. Sci China Inf Sci, 2022, 65(11): 212102, doi: 10.1007/s11432-020-3322-x

RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Ensemble of half-space trees for hyperspectral anomaly detection
Huang, Ju; Li, Xuelong
Sci China Inf Sci, 2022, 65(9): 192103

Keywords: hyperspectral image; anomaly detection; extended morphological attribute profile; mass esti- mation; half-space tree

Cite as: Huang J, Li X L. Ensemble of half-space trees for hyperspectral anomaly detection. Sci China Inf Sci, 2022, 65(9): 192103, doi: 10.1007/s11432-021-3310-x

LETTER Supplementary Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

3DPF-FBN: video inpainting by jointly 3D-patch filling and neural network refinement
Huang, Yan; Yang, Chuanchuan; Chen, Zhangyuan
Sci China Inf Sci, 2022, 65(7): 179103

Keywords: video inpainting; patch-based searching; optical flow; neural network; refinement

Cite as: Huang Y, Yang C C, Chen Z Y. 3DPF-FBN: video inpainting by jointly 3D-patch filling and neural network refinement. Sci China Inf Sci, 2022, 65(7): 179103, doi: 10.1007/s11432-019-2956-6

Special Focus on Deep Learning for Computer Vision
LETTER Webpage Webpage-cn SpringerLink Google Scholar Cited in SCI: 0

Few-shot font style transfer with multiple style encoders
Zhang, Kejun; Zhang, Rui; Wu, Yonglin; Li, Yifei; Ling, Yonggen; Wang, Bolin; Sun, Lingyun; Li, Yingming
Sci China Inf Sci, 2022, 65(6): 160109

Keywords: font generation; image-to-image translation; generative adversarial network; multi-task learning; font fusion; style transfer

Cite as: Zhang K J, Zhang R, Wu Y L, et al. Few-shot font style transfer with multiple style encoders. Sci China Inf Sci, 2022, 65(6): 160109, doi: 10.1007/s11432-021-3435-8