TuAMOT1.A |
Tue 10:30-12:30 |
Machine Learning and Classification |
131 |
Trusheim, Felix |
Boosting Black-Box Variational Inference by Incorporating the Natural Gradient |
881 |
Fu, Xianghua; Liu, Wangwang |
Introduce More Characteristics of Samples into Cross-domain Sentiment Classification |
843 |
Jiang, Yuechi; Leung, Frank Hung Fat |
Discriminative Collaborative Representation and Its Application to Audio Signal Classification |
490 |
LI, Rui; CAO, Wenming; QIAN, Sheng; Wong, Hau-San; Wu, Si |
Cross-domain Semantic Feature Learning via Adversarial Adaptation Networks |
484 |
Bi, Yanhong; Wu, Fuchao |
Cayley-Klein Metric Learning with Shrinkage-Expansion Constraints |
1190 |
Bhaskaruni, Venkata Sai Krishna Dheeraj; Moss, Fiona; Lan, Chao |
Estimating Prediction Qualities without Ground Truth: A Revisit of the Reverse Testing Framework |
|
|
|
TuAMOT1.B |
Tue 10:30-12:10 |
Deep Learning 1 |
332 |
Ma, Jiabin; Guo, Weiyu; Wang, Wei; Wang, Liang |
RotateConv: Making Asymmetric Convolutional Kernels Rotatable |
359 |
Manessi, Franco; Rozza, Alessandro |
Learning Combinations of Activation Functions |
431 |
Zhu, Jiagang; Zou, Wei; Zheng, Zhu |
Learning Evasion Strategy in Pursuit-Evasion by Deep Q-network |
513 |
Shi, Hongjiang; Wang, Lu; Ding, Guangtai; Yang, Fenglei; Li, Xiaoqiang |
Data Augmentation with Improved Generative Adversarial Networks |
587 |
Liu, Hanwen; Navarrete Michelini, Pablo; Zhu, Dan |
ArtsyGAN: A style transfer system with improved quality, diversity and performance |
|
|
|
TuAMOT2 |
Tue 10:30-12:30 |
Learning Based Vision |
491 |
Lin, luojun; Liang, Lingyu; Jin, Lianwen |
R^2-ResNeXt: A ResNeXt-Based Regression Model with Relative Ranking for Facial Beauty Prediction |
592 |
Han, Guangyun; Xie, Xiaohua; Zheng, Wei-Shi; Lai, Jian-huang |
Learning Intrinsic Image Decomposition by Deep Neural Network with Perceptual Loss |
607 |
Roy, Anirban; Todorovic, Sinisa |
Learning to Learn Second-Order Back-Propagation for CNNs Using LSTMs |
609 |
Choo, Sungkwon; Seo, Wonkyo; Jeong, Dong-ju; Cho, Nam Ik |
Multi-scale Recurrent Encoder-Decoder Network for Dense Temporal Classification |
1160 |
Robles-Kelly, Antonio; wei, Ran |
A Convolutional Neural Network for Pixelwise Illuminant Recovery in Colour and Spectral Images |
1046 |
Li, Miaopeng; Zhou, Zimeng; li, jie; Liu, Xinguo |
Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint |
|
|
|
ThAMOT3 |
Tue 10:30-12:30 |
Image Processing |
456 |
Bolelli, Federico; Baraldi, Lorenzo; Cancilla, Michele; Grana, Costantino |
Connected Components Labeling on DRAGs |
673 |
Huang, Tao; Dong, Weisheng; Shi, Guangming; Li, Xin |
Lightweight Deep Residue Learning for Joint Color Image Demosaicking and Denoising |
800 |
Ling, zhigang; Li, xiuxin; Zou, wen; Siyu, Guo |
Joint Haze-relevant Features Selection and Transmission Estimation via Deep Belief Network for Efficient Single Image Dehazing |
923 |
Perera, Pramuditha; Mahdi, Abavisani; Patel, Vishal |
In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversial Networks |
961 |
Cheng, Xi; Li, Xiang; Yang, Jian; Tai, Ying |
SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks |
956 |
Yue, Huanjing; Zhou, Shengdi; Yang, Jingyu; Sun, Xiaoyan; Hou, Chunping |
Deep Joint Noise Estimation and Removal for High ISO JPEG Images |
|
|
|
TuPMOT1 |
Tue 17:00-18:20 |
Structural Pattern Recognition |
447 |
Hou, Jian; Pelillo, Marcello |
A Game-Theoretic Hyper-graph Matching Algorithm |
997 |
Zhang, Qi; Jin, QiZhao; Chang, Jianlong; Xiang, Shiming; PAN, Chunhong |
Kernel-Weighted Graph Convolutional Network: A Deep Learning Approach for Traffic Forecasting |
402 |
Zhang, Zhihong; ZHOU, DA; Xu, Chuanyu; Wang, Beizhan; Wang, Dong; REN, GUIJUN; Hancock, Edwin |
Depth-based Subgraph Convolutional Neural Networks |
789 |
Bai, Lu; Cui, Lixin; Rossi, Luca; Wang, Yue; Hancock, Edwin |
A Deep Hybrid Graph Kernel Through Deep Learning Networks |
|
|
|
TuPMOT2 |
Tue 17:00-18:20 |
3D Vision |
53 |
Antensteiner, Doris; tolc, Svorad; Pock, Thomas |
Multi-line Scan 3D Sensing with a Hybrid Light-Field and Photometric Stereo Approach |
889 |
Kimura, Ryosuke; Dayrit, Fabian Lorenzo; Nakashima, Yuta; Kawasaki, Hiroshi; Blanco, Ambrosio; Ikeuchi, Katsushi |
Representing a Partially Observed Non-Rigid 3D Human Using Eigen-Texture and Eigen-Deformation |
971 |
Elanattil, Shafeeq; Moghadam, Peyman; Sridha, Sridharan; Fookes, Clinton; Cox, Mark |
Non-rigid Reconstruction with a Single Moving RGB-D Camera |
1106 |
Shui, Panpan; Wang, Pengyu; Bingyang, Hu; Yan, Zhang |
3D Shape Segmentation Based on Viewpoint Entropy and Projective Fully Convolutional Networks Fusing Multi-view Features |
|
|
|
TuPMOT4 |
Tue 17:00-18:20 |
Biometric Analysis and Synthesis |
519 |
Wu, Bo; YANG, Gongping; Yang, Lu; Yin, Yilong |
Robust ECG Biometrics Using Two-Stage Model |
528 |
Zheng, Siqi; Wang, Jianzong; Xiao, Jing; Hsu, Wei-Ning; Glass, James |
A Noise-Robust Self-Adaptive Multitarget Speaker Detection System |
468 |
Li, Peipei; Hu, Yibo; Li, Qi; He, Ran; Sun, Zhenan |
Global and Local Consistent Age Generative Adversarial Networks |
1191 |
Sindagi, Vishwanath; Patel, Vishal; Di, Xing |
GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks |
|
|
|
TuPMOT5 |
Tue 17:00-18:20 |
Document Image Analysis |
653 |
Jolly, Shailza; Iwana, Brian Kenji; Kuroki, Ryohei; Uchida, Seiichi |
How do Convolutional Neural Networks Learn Design? |
980 |
Cu, Vinh Loc; burie, jean-christophe; Ogier, Jean-Marc |
Document images watermarking for security issue using fully convolutional networks |
1086 |
Baraldi, Lorenzo; Cornia, Marcella; Grana, Costantino; Cucchiara, Rita |
Aligning Text and Document Illustrations: towards Visually Explainable Digital Humanities |
364 |
Konwer, Aishik; Bhunia, Ayan Kumar; Bhowmick, Abir; Bhunia, Ankan Kumar; Banerjee, Prithaj; Roy, Partha Pratim; Pal, Umapada |
Staff line Removal using Generative Adversarial Networks |
|
|
|
WeAMOT1 |
Wed 11:10-12:30 |
Deep Learning 2 |
640 |
li, lin; Zhang, Zhaoxiang; Huang, Yan; Wang, Liang |
Deep Temporal Feature Encoding for Action Recognition |
663 |
Gupta, Nitin; Mujumdar, Shashank; Samanta, Suranjana; Mehta, Sameep |
Learning an Order Preserving Image Similarity Through Deep Ranking |
535 |
wang, chu; Zhang, Yan-Ming; Liu, Cheng-Lin |
Anomaly Detection via Minimum Likelihood Generative Adversarial Networks |
837 |
Wu, Kailun; Zhang, Changshui |
Deep Generative Adversarial Networks for the Sparse Signal Denoising |
|
|
|
WeAMOT2 |
Wed 11:10-12:30 |
Low Level Vision |
196 |
Wang, Gang; Chen, Yufei |
Spatially Coherent Matching for Robust Registration |
762 |
Yang, Guorun; Deng, Zhidong; Wang, Shiyao; Li, Zeping |
Masked Label Learning for Optical Flow Regression |
125 |
zu, yueran; Gao, Ke; bao, xiuguo; tang, wenzhong; yin, zhiyu |
Saliency guided fast interpolation for large displacement optical flow |
763 |
Haindl, Michael; Havlicek, Vojtech |
BTF Compound Texture Model with Non-Parametric Control Field |
|
|
|
WeAMOT3 |
Wed 11:00-12:30 |
Image Analysis and Segmentation |
555 |
Ngo, Phuc; Passat, Nicolas; Kenmochi, Yukiko; Debled-Rennesson, Isabelle |
Convexity invariance of voxel objects under rigid motions |
329 |
Song, Tiecheng; Luo, Lin; Xin, Liangliang; Gao, Chenqiang |
Multi-Scale Cross-Band Encoding of Sectored Local Binary Pattern for Robust Texture Classification |
884 |
Chen, Sih-Huei; Lee, Yuan-Shan; Wang, Jia-Ching |
Locality Preserving Discriminative Complex-Valued Latent Variable Model |
1091 |
Pucher, Daniel; Kropatsch, Walter |
Segmentation Edit Distance |
|
|
|
WeAMOT6 |
Wed 11:10-12:30 |
Medical Image Analysis |
562 |
Nadeem, Syed Ahmed; Hoffman, Eric A; Saha, Punam Kumar |
An automated airway segmentation algorithm for CT images using topological leakage detection and volume freezing |
615 |
Liu, Zhe; Song, Yuqing; Liu, Qingfeng; Lu, Hu; Zhu, Yan; Yuan, Deqi |
A Method for PET-CT Lung Cancer Segmentation based on Improved Random Walk |
633 |
Huang, Kuan; Cheng, Heng-Da; Huang, Jianhua; zhang, yingtao; Zhang, Boyu; Xing, Ping; Ning, Chunping |
Medical Knowledge Constrained Semantic Breast Ultrasound Image Segmentation |
975 |
Dhara, Ashis Kumar; Arvids, Erik; Fahlström, Markus; Wikström, Johan; Larsson, Elna-Marie; Strand, Robin |
Interactive Segmentation of Glioblastoma for Post-surgical Treatment Follow-up |
|
|
|
WePMOT1.A |
Wed 17:00-18:20 |
Multitask and Multilabel Learning |
927 |
Han, Tian; Xing, Xianglei; Wu, Yingnian |
Learning Multi-view Generator Network for Shared Representation |
320 |
Zhuang, Ni; Yan, Yan; Chen, Si; Wang, Hanzi |
Multi-task Learning of Cascaded CNN for Facial Attribute Classification |
1300 |
Pei, Yuanli; Fern, Xiaoli Z; Raich, Raviv |
Learning with Latent Label Hierarchy from Incomplete Multi-Label Data |
60 |
Lyu, Jie; Yuan, Zejian; Chen, Dapeng |
Learning Fixation Point Strategy for Object Detection and Classification |
|
|
|
WePMOT1.B |
Wed 17:00-18:00 |
Clustering |
1089 |
Jaberi, Maryam; Pensky, Marianna; Foroosh, Hassan |
Probabilistic Sparse Subspace Clustering |
267 |
Li, Chun-Guang; Zhang, Junjian; Guo, Jun |
Constrained Sparse Subspace Clustering with Side-Information |
269 |
Wang, Ziyin; Tsechpenakis, Gavriil |
Stream Clustering with Dynamic Estimation of Emerging Local Densities |
|
|
|
WePMOT2 |
Wed 17:00-18:20 |
Motion Analysis |
485 |
Li, Yulin; ma, Bingpeng; Chang, Hong; Chen, xilin |
A Benchmark for Full Rotation Head Tracking |
700 |
Kart, Ugur; Kamarainen, Joni-Kristian; Matas, Jiri; Fan, Lixin; Cricri, Francesco |
Depth Masked Discriminative Correlation Filter |
880 |
Jiang, Bo; Yuan, Zhang; Tang, Jin; Luo, Bin |
OWP: Objectness Weighted Patch Descriptor for Visual Tracking |
1284 |
Ma, Ding; Wu, Xiangqian |
Dual-SVM tracker via Multiple Support Instance |
|
|
|
WePMOT4 |
Wed 17:00-18:20 |
Gait and Person Re-identification |
938 |
Hosni, Nadia; Drira, Hassen; Chaieb, Faten; Ben Amor, Boulbaba |
3D Gait Recognition based on Functional PCA on Kendall's Shape Space |
748 |
Yan, Fei; Kittler, Josef; Mikolajczyk, Krystian |
Person Re-Identification with Vision and Language |
1253 |
Yuan, Baoyu; Wu, Ancong; Zheng, Wei-Shi |
Does A Body Image Tell Age? |
515 |
Xu, Qin; Sun, Yifan; Li, Yali; Wang, Shengjin |
Attend and Align: Improving Deep Representations with Feature Alignment Layer for Person Retrieval |
|
|
|
ThAMOT1 |
Thu 11:10-12:30 |
Semi-Supervised Learning |
572 |
Hailat, Zeyad; Komarichev, Artem; Chen, Xuewen |
Deep Semi-Supervised Learning |
346 |
Zhang, Huan; Zhang, Zhao; Jia, Lei; Qin, Jie; Tang, Jinhui; Wang, Meng |
Robust Adaptive Label Propagation by Double Matrix Decomposition |
666 |
zhong, min; Zeng, Gang |
Efficient Object Region Discovery for Weakly-supervised Semantic Segmentation |
1153 |
CURADO, MANUEL; Escolano, Francisco; Lozano, Miguel Angel; Hancock, Edwin |
Semi-supervised Graph Rewiring with the Dirichlet Principle |
|
|
|
ThAMOT2 |
Thu 11:10-12:30 |
Object Detection |
1258 |
Xu, Pei; Zhao, Xin; Huang, Kaiqi |
Densely Connected Single-Shot Detector |
824 |
Chen, Yuhuan; Zou, Wenbin; Li, Xia; Qiu, Guoping |
Video Salient Object Detection via Multiple Time-scale Analysis |
900 |
Yang, Wenyan; QIAN, YANLIN; Cricri, Francesco; Fan, Lixin; Kamarainen, Joni-Kristian |
Object Detection in Equirectangular Panorama |
432 |
Xie, Xiaolu; Wang, Zengfu |
Multi-scale Semantic Segmentation Enriched Features for Pedestrian Detection |
|
|
|
ThAMOT4 |
Thu 11:10-12:30 |
Face Biometrics |
29 |
Zhang, Hongwen; Li, Qi; Sun, Zhenan |
Joint Voxel and Coordinate Regression for Accurate 3D Facial Landmark Localization |
1047 |
Li, Yong; Zeng, Jiabei; Shan, Shiguang; Chen, xilin |
Patch-Gated CNN for Occlusion-aware Facial Expression Recognition |
1280 |
Gupta, Ishita; Bhalla, Ikshu; Singh, Richa; Vatsa, Mayank |
Scattering Transform for Matching Surgically Altered Face Images |
532 |
Sun, Xudong; Huang, Lei; Liu, Changping |
MULTIMODAL FACE SPOOFING DETECTION VIA RGB-D IMAGES |
|
|
|
ThAMOT5 |
Thu 11:10-12:30 |
Text Detection and Recognition |
969 |
Feng, Wei; He, Wenhao; Yin, Fei; Liu, Cheng-Lin |
Scene Text Detection with Recurrent Instance Segmentation |
482 |
Sui, Wanchen; Zhang, Qing; Yang, Jun; Chu, Wei |
A Novel Integrated Framework for Learning both Text Detection and Recognition |
795 |
Riba, Pau; Fischer, Andreas; Llados, Josep; Fornés, Alicia |
Learning Graph Distances with Message Passing Neural Networks |
719 |
Zhang, Jianshu; Du, Jun; Dai, Li-Rong |
Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition |
|
|
|
ThPMOT1.A |
Thu 14:00-15:20 |
Online and Active Learning |
818 |
Nie, Xiangli; Luo, Yongkang; Qiao, Hong; Zhang, Bo |
An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification |
1029 |
Xu, shan; Zhang, Xiao; Liao, Shizhong |
A Linear Incremental Nystrom Method for Online Kernel Learning |
1125 |
Liu, Xialei; Masana, Marc; Herranz, Luis; van de Weijer, Joost; López Peña, Antonio M.; Bagdanov, Andrew D. |
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting |
945 |
Pang, Kunkun; Dong, Mingzhi; Wu, Yang; Hospedales, Timothy |
Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice |
|
|
|
ThPMOT2.A |
Thu 14:00-15:20 |
Vision Applications |
781 |
Spera, Emiliano; Furnari, Antonino; Battiato, Sebastiano; Farinella, Giovanni Maria |
Egocentric Shopping Cart Localization |
787 |
Zhang, Jiyuan; Zeng, Gang; Zha, Hongbin |
Scalable Monocular SLAM by Fusing and Connecting Line Segments with Inverse Depth Filter |
387 |
Yang, Zhengyuan; Zhang, Yixuan; Yu, Jerry; Cai, Junjie; Luo, Jiebo |
End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perceptions |
792 |
Li, Yan; Zhang, Yinlong; Hongsheng, He; Tan, Jindong |
Spatial Calibration for Thermal-Visible Cameras and Inertial Sensor System |
|
|
|
ThPMOT6 |
Thu 14:00-15:20 |
Medical Signal Analysis and Recognition |
185 |
Abdeldayem, Sara; Bourlai, Thirimachos |
Automatically Detecting Arrhythmia-related Irregular Patterns using the Temporal and Spectro-Temporal Textures of ECG Signals |
594 |
Nguyen, Binh; Ma, Wanli; Tran, Dat |
Impact of lossy data compression techniques on EEG-based pattern recognition systems |
598 |
Zhang, Teng; Carvajal, Johanna; Smith, Daniel F.; Zhao, Kun; Wiliem, Arnold; Hobson, Peter; Jennings, Anthony; Lovell, Brian Carrington |
SlideNet: Fast and Accurate Slide Quality Assessment Based on Deep Neural Networks |
966 |
Lopez-Martinez, Daniel; Peng, Ke; Steele, Sarah; Lee, Arielle, Arielle; Borsook, David; Picard, Rosalind |
Multitask multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals |
|
|
|
ThPMOT1.B |
Thu 17:20-18:20 |
Manifold and Feature Learning |
406 |
Zhang, Zhihong; Ye, Zhiling; Bai, Zhengjian; Hu, Guosheng; Hu, Yiqun; Hancock, Edwin |
A Unified Neighbor Reconstruction Method for Embeddings |
1025 |
ZHU, Ruifeng; Dornaika, Fadi; Ruichek, Yassine |
Flexible and discriminative non-linear embedding with feature selection for image classification |
280 |
Bai, Yang; Haghighat, Mohammad; Abdel-Mottaleb, Mohamed |
Kernel Discriminant Correlation Analysis: Feature Level Fusion for Nonlinear Biometric Recognition |
|
|
|
ThPMOT2.B |
Thu 17:20-18:20 |
Behavior Recognition |
368 |
Yang, Bikun; Tong, Yuqiang; Cui, Jinshi, Jinshi; Wang, Li; Zha, Hongbin |
Recognition of Infants' Gaze Behaviors and Emotions |
523 |
Khalid, Muhammad Usman Khalid; Yu, Jie |
Multi-Modal Three Stream Network for Action Recognition |
877 |
Zhang, Wei; Cen, Jiepeng; Zheng, Huicheng |
Temporal Inception Architecture for Action Recognition with Convolutional Neural Networks |
|
|
|
ThPMOT3 |
Thu 17:20-18:20 |
Speech and Signal |
307 |
Li, Chenxing; Zhu, Lei; Xu, Shuang; Gao, Peng; Xu, Bo |
Recurrent Neural Network Based Small-footprint Wake-up-word Speech Recognition System with a Score Calibration Method |
930 |
Saitoh, Takeshi; Kubokawa, Michiko |
SSSD: Speech Scene by Smart Device for Visual Speech Recognition |
188 |
Shen, Miaomiao; Rui, WANG |
New Singular Value Decomposition Algorithm for Octonion Signals |
|
|
|
FrAMOT1 |
Fri 10:30-12:30 |
Applications of Classification and Learning |
315 |
Abdolshah, Majid; Shilton, Alistair; Rana, Santu; Gupta, Sunil Kumar; Venkatesh, Svetha |
Expected Hypervolume Improvement with Constraints |
905 |
Yang, Jianxing; Zhou, Yuan; Kung, Sun-Yuan |
Multi-scale Generative Adversarial Networks for Crowd Counting |
1187 |
Sinha, Sayan; Nirala, Mehul Kumar; Ghosh, Shreya; Ghosh, Soumya K. |
Hybrid Path Planner for Efficient Navigation in Urban Road Networks through Analysis of Trajectory Traces |
1197 |
Zhang, Ting; Zhou, Tian; Duerstock, Bradley S.; Wachs, Juan |
Image Exploration Procedure Classification with Spike-timing Neural Network for the Blind |
1008 |
Savchenko, Andrey |
Efficient Statistical Face Recognition Using Trigonometric Series and CNN Features |
530 |
Lei, Haijun; Zhao, Yujia; Huang, Zhongwei; Zhou, Feng; Lei, Baiying |
Multi-classification of Parkinsons Disease via Sparse Low-Rank Learning |
|
|
|
FrAMOT2 |
Fri 10:30-12:30 |
Object Recognition and Scene Understanding |
337 |
Chan, Jacob; Lee, Jimmy Addison; Qian, Kemao |
Real-Time Texture-less Object Recognition on Mobile Devices |
723 |
Tian, Yanling; Zhang, Weitong; Zhang, Qieshi; Lu, Gang; Wu, Xiaojun |
Selective Multi-Convolutional Region Feature Extraction based Iterative Discrimination CNN for Fine-Grained Vehicle Model Recognition |
261 |
Zhu, Jianqing; Huanqiang, Zeng; Lei, Zhen; Liao, Shengcai; Lixin, Zheng; Cai, Canhui |
A Shortly and Densely Connected Convolutional Neural Network for Vehicle Re-identification |
287 |
Li, Binglin; Wang, Yang |
Visual Relationship Detection Using Joint Visual-Semantic Embedding |
588 |
Wang, Fuwei; Gong, Xiaolong; Huang, Linpeng |
Time-Dependent Pre-attention Model for Image Captioning |
755 |
Cheng, Wenlong; Huang, Yan; Wang, Liang |
Towards Unconstrained Pointing Problem of Visual Question Answering: A Retrieval-based Method |
|
|
|
FrAMOT3 |
Fri 10:30-12:30 |
Image and Video Retrieval |
152 |
Yang, Zhengyuan; Li, Yuncheng; Yang, Jianchao; Luo, Jiebo |
Action Recognition with Visual Attention on Skeleton Images |
1147 |
Dehzangi, Omid; Anantapur Bache, Bhavani; Iftikhar, Omar |
Human Activity Recognition via Discriminative Fusion of Insole embedded Multi-Pressure Sensors |
74 |
Ueki, Kazuya; Hirakawa, Koji; Kikuchi, Kotaro; Kobayashi, Tetsunori |
Fine-grained Video Retrieval using Query Phrases - Waseda_Meisei TRECVID 2017 AVS System - |
284 |
sun, peng; Yan, Cheng; Bai, Xiao; wang, shuai |
Discriminate Cross-modal Quantization for Efficient Retrieval |
660 |
Hao, Jiedong; Dong, Jing; Wang, Wei; Tan, Tieniu |
DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval |
782 |
Zhang, Yonghui; Shao, Jie; Ouyang, Deqiang; Shen, Heng Tao |
Person Re-identification Using Two-Stage Convolutional Neural Network |