歡迎關注微信公衆號【計算機視覺聯盟】 獲取更多前沿AI、CV資訊
CVPR2019最新論文,論文列表(附論文地址和代碼),更新於6月11日(arXiv最新日期),持續更新中
總結論文下載方式:關注公衆號【計算機視覺聯盟】回覆關鍵詞【CVPR2019】即可獲取全部論文下載!
【1】Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos(Romero Morais; Vuong Le; Truyen Tran; Budhaditya Saha; Moussa Mansour; Svetha Venkatesh )
論文地址:https://arxiv.org/abs/1903.03295
【2】Learning from Synthetic Data for Crowd Counting in the Wild(Qi Wang, Junyu Gao, Wei Lin, Yuan Yuan)
論文地址:https://arxiv.org/abs/1903.03303
【3】Knowledge-Embedded Routing Network for Scene Graph Generation(Tianshui Chen, Weihao Yu, Riquan Chen, Liang Lin)
論文地址:https://arxiv.org/abs/1903.03326
【4】Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval(Anjan Dutta, Zeynep Akata)
論文地址:https://arxiv.org/abs/1903.03372
【5】Structured Knowledge Distillation for Semantic Segmentation
https://arxiv.org/pdf/1903.04197.pdf
【5】Strong-Weak Distribution Alignment for Adaptive Object Detection(Kuniaki Saito1、Yoshitaka Ushiku2、Tatsuya Harada2,3、Kate Saenko1,波士頓大、學東京大學)
論文地址:https://arxiv.org/pdf/1812.04798.pdf
【7】PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation(Fenggen Yu、Kun Liu1、Yan Zhang1、Chenyang Zhu、Kai Xu,南京大學、國防科技大學)
論文地址:https://arxiv.org/pdf/1903.00709.pdf
【9】Understanding and Visualizing Deep Visual Saliency Models(Sen He、Hamed R. Tavakoli、Ali Borji、Yang Mi、Nicolas Pugeault,埃克塞特大學、阿爾託大學)
論文地址:https://arxiv.org/pdf/1903.02501.pdf
【9】Depth Coefficients for Depth Completion(Saif Imran、Yunfei Long、Xiaoming Liu、Daniel Morris,密歇根州立大學)
論文地址:https://arxiv.org/pdf/1903.05421.pdf
【10】RVOS: End-to-End Recurrent Network for Video Object Segmentation
論文地址:https://arxiv.org/pdf/1903.05612.pdf
【11】Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis(北京大學、加利福尼亞大學)
論文地址:https://arxiv.org/pdf/1903.05628.pdf
【12】MirrorGAN: Learning Text-to-image Generation by Redescription
論文地址:https://arxiv.org/pdf/1903.05854.pdf
【13】Deep Transfer Learning for Multiple Class Novelty Detection
論文地址:https://arxiv.org/abs/1903.02196
【14】AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data
https://arxiv.org/pdf/1901.04596.pdf
【15】ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding
https://arxiv.org/pdf/1811.11968.pdf
【16】Fast Online Object Tracking and Segmentation: A Unifying Approach
開源:https://github.com/foolwood/SiamMask
【17】Dual Encoding for Zero-Example Video Retrieval
論文地址:https://arxiv.org/abs/1809.06181
開源地址:https://github.com/danieljf24/dual_encoding
【18】Supervised Fitting of Geometric Primitives to 3D Point Clouds
https://arxiv.org/abs/1811.08988
【19】Learning 3D Human Dynamics from Video
https://arxiv.org/abs/1812.01601
【20】Explainable and Explicit Visual Reasoning over Scene Graphs
https://arxiv.org/abs/1812.01855
【21】Learning Parallax Attention for Stereo Image Super-Resolution
https://arxiv.org/abs/1903.05784
【22】AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs
https://arxiv.org/abs/1903.07062
【23】QATM: Quality-Aware Template Matching For Deep Learning
https://arxiv.org/abs/1903.07254
【24】Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection
https://arxiv.org/abs/1903.07256
【25】Self-calibrating Deep Photometric Stereo Networks(oral)
https://arxiv.org/abs/1903.07366
【26】Understanding the Limitations of CNN-based Absolute Camera Pose Regression
https://arxiv.org/abs/1903.07504
【27】Learning Correspondence from the Cycle-Consistency of Time
https://arxiv.org/abs/1903.07593
http://ajabri.github.io/timecycle
【28】Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
https://arxiv.org/abs/1812.07179
【29】SimulCap : Single-View Human Performance Capture with Cloth Simulation
https://arxiv.org/abs/1903.06323
【30】Neural Sequential Phrase Grounding (SeqGROUND)
https://arxiv.org/abs/1903.07669
【31】Direct Object Recognition Without Line-of-Sight Using Optical Coherence
https://arxiv.org/abs/1903.07705
【32】SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations
https://arxiv.org/abs/1903.06482
【33】Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
https://arxiv.org/abs/1903.07788
【34】Semantic Image Synthesis with Spatially-Adaptive Normalization(oral)
https://arxiv.org/abs/1903.07291
【35】Inverse Path Tracing for Joint Material and Lighting Estimation(oral)
https://arxiv.org/abs/1903.07145
【36】Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
https://arxiv.org/abs/1903.05628
https://github.com/HelenMao/MSGAN
【37】Selective Kernel Networks
https://arxiv.org/abs/1903.06586
【38】A Cross-Season Correspondence Dataset for Robust Semantic Segmentation
https://arxiv.org/abs/1903.06916
【39】Unsupervised Part-Based Disentangling of Object Shape and Appearance
https://arxiv.org/abs/1903.06946
【40】Inserting Videos into Videos
https://arxiv.org/abs/1903.06571
【41】Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
https://arxiv.org/abs/1812.09502
【42】Domain Generalization by Solving Jigsaw Puzzles
https://arxiv.org/abs/1903.06864
【43】Fast Interactive Object Annotation with Curve-GCN
https://arxiv.org/abs/1903.06874
【44】MFAS: Multimodal Fusion Architecture Search
https://arxiv.org/abs/1903.06496
【45】OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
https://arxiv.org/abs/1903.08550
【46】An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM
https://arxiv.org/abs/1903.08636
【47】Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
https://arxiv.org/abs/1903.08642
code: https://chenhsuanlin.bitbucket.io/photometric-mesh-optim/
【48】Towards Robust Curve Text Detection with Conditional Spatial Expansion
https://arxiv.org/abs/1903.08836
【49】Learning with Batch-wise Optimal Transport Loss for 3D Shape Recognition
https://arxiv.org/abs/1903.08923
【50】Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
https://arxiv.org/pdf/1903.08839.pdf
【51】Patch-based Progressive 3D Point Set Upsampling
https://arxiv.org/abs/1811.11286
【52】Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos(Romero Morais; Vuong Le; Truyen Tran; Budhaditya Saha; Moussa Mansour; Svetha Venkatesh )
論文地址:https://arxiv.org/abs/1903.03295
【53】Learning from Synthetic Data for Crowd Counting in the Wild(Qi Wang, Junyu Gao, Wei Lin, Yuan Yuan)
論文地址:https://arxiv.org/abs/1903.03303
【54】Knowledge-Embedded Routing Network for Scene Graph Generation(Tianshui Chen, Weihao Yu, Riquan Chen, Liang Lin)
論文地址:https://arxiv.org/abs/1903.03326
【55】Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval(Anjan Dutta, Zeynep Akata)
論文地址:https://arxiv.org/abs/1903.03372
【56】Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
作者:Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata
論文鏈接:https://arxiv.org/abs/1812.01784
源碼鏈接:https://github.com/edgarschnfld/CADA-VAE-PyTorch
【57】PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
作者:Shaoshuai Shi, Xiaogang Wang, Hongsheng Li
論文鏈接:https://arxiv.org/abs/1812.04244
源碼鏈接:https://github.com/sshaoshuai/PointRCNN
【58】FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image
作者:Tsun-Yi Yang, Yi-Ting Chen, Yen-Yu Lin, and Yung-Yu Chuang
論文鏈接:https://github.com/shamangary/FSA-Net/blob/master/0191.pdf
源碼鏈接:https://github.com/shamangary/FSA-Net
【59】Learning Attraction Field Representation for Robust Line Segment Detection
作者:Nan Xue, Song Bai, Fudong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang
論文鏈接:https://arxiv.org/abs/1812.02122
源碼鏈接:https://github.com/cherubicXN/afm_cvpr2019
【60】DFANet:Deep Feature Aggregation for Real-Time Semantic Segmentation(曠視)
作者:Hanchao Li, Pengfei Xiong,Haoqiang Fan,Jian Sun
論文鏈接:https://share.weiyun.com/5NgHbWH
【61】Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
作者:Ondrej Miksik, Vibhav Vineet
論文鏈接:https://arxiv.org/abs/1903.06708
【62】Automatic adaptation of object detectors to new domains using self-training
作者:Aruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin, Huaizu Jiang, Liangliang Cao, Erik Learned-Miller
論文鏈接:https://arxiv.org/abs/1904.07305
【63】A Realistic Dataset and Baseline Temporal Model for Early Drowsiness Detection
作者:Reza Ghoddoosian, Marnim Galib, Vassilis Athitsos
論文鏈接:https://arxiv.org/abs/1904.07312
【64】Exploiting Computation Power of Blockchain for Biomedical Image Segmentation
作者:Boyang Li, Changhao Chenli, Xiaowei Xu, Taeho Jung, Yiyu Shi
論文鏈接:https://arxiv.org/abs/1904.07349
【65】NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection(目標檢測)
作者:Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le
論文鏈接:https://arxiv.org/abs/1904.07392
【66】A Bayesian Perspective on the Deep Image Prior
作者:Zezhou Cheng, Matheus Gadelha, Subhransu Maji, Daniel Sheldon
論文鏈接:https://arxiv.org/abs/1904.07457
源碼鏈接:https://github.com/ZezhouCheng/GP-DIP
【67】Fashion-AttGAN: Attribute-Aware Fashion Editing with Multi-Objective GAN
作者:Qing Ping, Jiangbo Yuan, Bing Wu, Wanying Ding
論文鏈接:https://arxiv.org/abs/1904.07460
【68】Focus Is All You Need: Loss Functions For Event-based Vision
作者:Guillermo Gallego, Mathias Gehrig, Davide Scaramuzza
論文鏈接:https://arxiv.org/abs/1904.07235
【69】Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting
作者:Yanhong Zeng, Jianlong Fu, Hongyang Chao, Baining Guo
論文鏈接:https://arxiv.org/abs/1904.07475
【70】Relation-Shape Convolutional Neural Network for Point Cloud Analysis
作者:Yongcheng Liu, Bin Fan, Shiming Xiang, Chunhong Pan
論文鏈接:https://arxiv.org/abs/1904.07601
項目鏈接:https://yochengliu.github.io/Relation-Shape-CNN/
源碼鏈接:https://github.com/Yochengliu/Relation-Shape-CNN
【71】LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences(人臉識別)
作者:Sudhakar Kumawat, Manisha Verma, Shanmuganathan Raman
論文鏈接:https://arxiv.org/abs/1904.07647
【72】Semantically Aligned Bias Reducing Zero Shot Learning
作者:Akanksha Paul, Narayanan C. Krishnan, Prateek Munjal
論文鏈接:https://arxiv.org/abs/1904.07659
【73】Camera Lens Super-Resolution
作者:Chang Chen, Zhiwei Xiong, Xinmei Tian, Zheng-Jun Zha, Feng Wu
論文鏈接:http://staff.ustc.edu.cn/~zwxiong/cameraSR.pdf
源碼鏈接:https://github.com/ngchc/CameraSR
【74】GolfDB: A Video Database for Golf Swing Sequencing
作者:William McNally, Kanav Vats, Tyler Pinto, Chris Dulhanty, John McPhee, Alexander Wong
論文鏈接:https://arxiv.org/abs/1903.06528v1
【75】R2GAN: Cross-modal Recipe Retrieval with Generative Adversarial Network
作者:Bin Zhu, Chong-Wah Ngo, Jingjing Chen, and Yanbin Hao
論文鏈接:http://vireo.cs.cityu.edu.hk/papers/R2GAN.pdf
【76】Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
作者:Chengquan Zhang, Borong Liang, Zuming Huang, Mengyi En, Junyu Han, Errui Ding, Xinghao Ding
論文鏈接:https://arxiv.org/abs/1904.06535
【77】GA-Net: Guided Aggregation Net for End-to-end Stereo Matching(Oral)
作者:Feihu Zhang, Victor Prisacariu, Ruigang Yang, Philip H.S. Torr
論文鏈接:https://arxiv.org/abs/1904.06587
【78】LiveSketch: Query Perturbations for Guided Sketch-based Visual Search
作者:John Collomosse, Tu Bui, Hailin Jin
論文鏈接:https://arxiv.org/abs/1904.06611
【79】Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
論文鏈接:https://arxiv.org/abs/1904.06627
源碼鏈接:https://github.com/MalongTech/research-ms-loss
【80】Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction
作者:Yi Wei, Shaohui Liu, Wang Zhao, Jiwen Lu, Jie Zhou
論文鏈接:https://arxiv.org/abs/1904.06699
【81】VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal
作者:Ya-Liang Chang, Zhe Yu Liu, Winston Hsu
論文鏈接:https://arxiv.org/abs/1904.06726
【82】Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation(Oral)
作者:Hao Tang, Dan Xu, Nicu Sebe, Yanzhi Wang, Jason J. Corso, Yan Yan
論文鏈接:https://arxiv.org/abs/1904.06807
源碼鏈接:https://github.com/Ha0Tang/SelectionGAN
【83】ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging(Oral)
作者:Samarth Brahmbhatt, Cusuh Ham, Charles C. Kemp, James Hays
論文鏈接:https://arxiv.org/abs/1904.06830
【84】Pedestrian Detection in Thermal Images using Saliency Maps(行人檢測)
作者:Debasmita Ghose, Shasvat Mukeshkumar Desai, Sneha Bhattacharya, Deep Chakraborty, Madalina Fiterau, Tauhidur Rahman
論文鏈接:https://arxiv.org/abs/1904.06859
【85】Self-critical n-step Training for Image Captioning(圖像生成)
作者:Junlong Gao, Shiqi Wang, Shanshe Wang, Siwei Ma, Wen Gao
論文鏈接:https://arxiv.org/abs/1904.06861
【86】Gait Recognition via Disentangled Representation Learning(Oral 步態識別)
作者:Ziyuan Zhang, Luan Tran, Xi Yin, Yousef Atoum, Xiaoming Liu, Jian Wan, Nanxin Wang
論文鏈接:https://arxiv.org/abs/1904.04925
【87】Towards High-fidelity Nonlinear 3D Face Morphable Model
作者:Luan Tran, Feng Liu, Xiaoming Liu
論文鏈接:https://arxiv.org/abs/1904.04933
項目鏈接:http://cvlab.cse.msu.edu/project-nonlinear-3dmm.html
【88】Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations(Oral)
作者:Jiwoon Ahn, Sunghyun Cho, Suha Kwak
論文鏈接:https://arxiv.org/abs/1904.05044
【89】Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
作者:Ruotent Li, Loong Fah Cheong, Robby T. Tan
論文鏈接:https://arxiv.org/abs/1904.05050
【90】C3AE: Exploring the Limits of Compact Model for Age Estimation
作者:Chao Zhang, Shuaicheng Liu, Xun Xu, Ce Zhu
論文鏈接:https://arxiv.org/abs/1904.05059
【91】DAVANet: Stereo Deblurring with View Aggregation(Oral)
作者:Shangchen Zhou, Jiawei Zhang, Wangmeng Zuo, Haozhe Xie, Jinshan Pan, Jimmy Ren
論文鏈接:https://arxiv.org/abs/1904.05065
【92】Text Guided Person Image Synthesis
作者:Xingran Zhou, Siyu Huang, Bin Li, Yingming Li, Jiachen Li, Zhongfei Zhang
論文鏈接:https://arxiv.org/abs/1904.05118
【93】Actor-Critic Instance Segmentation
作者:Kwang In Kim, Hyung Jin Chang
論文鏈接:https://arxiv.org/abs/1904.05126
【94】Joint Manifold Diffusion for Combining Predictions on Decoupled Observations
作者:Kwang In Kim, Hyung Jin Chang
論文鏈接:https://arxiv.org/abs/1904.05159
【95】Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
作者:Junhwa Hur, Stefan Roth
論文鏈接:https://arxiv.org/abs/1904.05290
【96】H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions(Oral)
作者:Bugra Tekin, Federica Bogo, Marc Pollefeys
論文鏈接:https://arxiv.org/abs/1904.05349
【97】Pixel-Adaptive Convolutional Neural Networks
作者:Hang Su, Varun Jampani, Deqing Sun, Orazio Gallo, Erik Learned-Miller, Jan Kautz
論文鏈接:https://arxiv.org/abs/1904.05373
【98】Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres
作者:Shuai Liao, Efstratios Gavves, Cees G. M. Snoek
論文鏈接:https://arxiv.org/abs/1904.05404
【99】Sliced Wasserstein Generative Models
作者:Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc Van Gool
論文鏈接:https://arxiv.org/abs/1904.05408
源碼鏈接:https://github.com/musikisomorphie/swd
【100】Learning to Generate Synthetic Data via Compositing
作者:Shashank Tripathi, Siddhartha Chandra, Amit Agrawal, Ambrish Tyagi, James M. Rehg, Visesh Chari
論文鏈接:https://arxiv.org/abs/1904.05475
【101】Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach(Oral)
作者:Proteek Chandan Roy, Vishnu Naresh Boddeti
論文鏈接:https://arxiv.org/abs/1904.05514
【102】Unified Visual-Semantic Embeddings: Bridging Vision and Language with Structured Meaning Representations
作者:Hao Wu, Jiayuan Mao, Yufeng Zhang, Yuning Jiang, Lei Li, Weiwei Sun, Wei-Ying Ma
論文鏈接:https://arxiv.org/abs/1904.05521
【103】Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
作者:Chen Li, Gim Hee Lee
論文鏈接:https://arxiv.org/abs/1904.05547
【104】Reasoning Visual Dialogs with Structural and Partial Observations(Oral)
作者:Zilong Zheng, Wenguan Wang, Siyuan Qi, Song-Chun Zhu
論文鏈接:https://arxiv.org/abs/1904.05548
【105】C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
作者:Fang Wan, Chang Liu, Wei Ke, Xiangyang Ji, Jianbin Jiao, Qixiang Ye
論文鏈接:https://arxiv.org/abs/1904.05647
【106】TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
作者:Xin Wang, Fisher Yu, Ruth Wang, Trevor Darrell, Joseph E. Gonzalez
論文鏈接:https://arxiv.org/abs/1904.05967
【107】Real-Time Dense Stereo Embedded in A UAV for Road Inspection
作者:Rui Fan, Jianhao Jiao, Jie Pan, Huaiyang Huang, Shaojie Shen, Ming Liu
論文鏈接:https://arxiv.org/abs/1904.06017
【108】Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology
作者:Hiroki Tokunaga, Yuki Teramoto, Akihiko Yoshizawa, Ryoma Bise
論文鏈接:https://arxiv.org/abs/1904.06040
【109】Unifying Heterogeneous Classifiers with Distillation
作者:Jayakorn Vongkulbhisal, Phongtharin Vinayavekhin, Marco Visentini-Scarzanella
論文鏈接:https://arxiv.org/abs/1904.06062
【110】YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving
作者:Thomas Boulay, Said El-Hachimi, Mani Kumar Surisetti, Pullarao Maddu, Saranya Kandan
論文鏈接:https://arxiv.org/abs/1904.05673
【111】A Relation-Augmented Fully Convolutional Network for Semantic Segmentationin Aerial Scenes
作者:Lichao Mou, Yuansheng Hua, Xiao Xiang Zhu
論文鏈接:https://arxiv.org/abs/1904.05730
【112】Learning joint reconstruction of hands and manipulated objects
作者:Yana Hasson, Gül Varol, Dimitrios Tzionas, Igor Kalevatykh, Michael J. Black, Ivan Laptev, Cordelia Schmid
論文鏈接:https://arxiv.org/abs/1904.05767
【113】Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope(Oral)
作者:Tolga Birdal, Umut Şimşekli
論文鏈接:https://arxiv.org/abs/1904.05814
【114】Variational Information Distillation for Knowledge Transfer
作者:Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D. Lawrence, Zhenwen Dai
論文鏈接:https://arxiv.org/abs/1904.05835
【115】Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
作者:Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, Michael J. Black
論文鏈接:https://arxiv.org/abs/1904.05866
【116】A Simple Baseline for Audio-Visual Scene-Aware Dialog
作者:Idan Schwartz, Alexander Schwing, Tamir Hazan
論文鏈接:https://arxiv.org/abs/1904.05876
【117】Max-Sliced Wasserstein Distance and its use for GANs
作者:Ishan Deshpande, Yuan-Ting Hu, Ruoyu Sun, Ayis Pyrros, Nasir Siddiqui, Sanmi Koyejo, Zhizhen Zhao, David Forsyth, Alexander Schwing
論文鏈接:https://arxiv.org/abs/1904.05877
【118】Two Body Problem: Collaborative Visual Task Completion
作者:Unnat Jain, Luca Weihs, Eric Kolve, Mohammad Rastegari, Svetlana Lazebnik, Ali Farhadi, Alexander Schwing, Aniruddha Kembhavi
論文鏈接:https://arxiv.org/abs/1904.05879
【119】Factor Graph Attention
作者:Idan Schwartz, Seunghak Yu, Tamir Hazan, Alexander Schwing
論文鏈接:https://arxiv.org/abs/1904.05880
【120】Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning
作者:Wenbin Li, Lei Wang, Jinglin Xu, Jing Huo, Yang Gao, Jiebo Luo
論文鏈接:http://cs.nju.edu.cn/rl/people/liwb/CVPR19.pdf
源碼鏈接:https://github.com/WenbinLee/DN4.git
【121】Large-Scale Long-Tailed Recognition in an Open World(Oral)
作者:Ziwei Liu*, Zhongqi Miao*, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu
論文鏈接:https://github.com/ofsoundof/3D_Appearance_SR/blob/master/code/scripts/3d_appearance_sr.pdf
源碼鏈接:
https://github.com/zhmiao/OpenLongTailRecognition-OLTR
【122】3D Appearance Super-Resolution with Deep Learning
作者:待補充
論文鏈接:https://github.com/ofsoundof/3D_Appearance_SR/blob/master/code/scripts/3d_appearance_sr.pdf
源碼鏈接:https://github.com/ofsoundof/3D_Appearance_SR
【123】High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection(行人檢測)
作者:Zhao-Min Chen, Xiu-Shen Wei Peng Wang3Yanwen Guo1
論文鏈接:https://github.com/liuwei16/CSP/blob/master/docs/2019CVPR-CSP.pdf
源碼鏈接:https://github.com/liuwei16/CSP
【124】Multi-Label Image Recognition with Graph Convolutional Networks(多標記圖像識別)
作者:Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, Yanwen Guo
論文鏈接:https://arxiv.org/abs/1904.03582
源碼鏈接:https://github.com/chenzhaomin123/ML_GCN
簡介:本工作針對多標記識別的核心問題,即“如何有效建模標記間的協同關係”進行探索,提出基於圖卷積(GCN)的端到端系統,通過data-driven方式建立標記間有向圖(directed graph)並由GCN將類別標記映射(mapping)爲對應類別分類器,以此建模類別關係,同時可提升表示學習能力。此外針對GCN中的關鍵元素correlation matrix進行了深入分析和重設計,使其更勝任多標記問題。
【125】Cycle-Consistency for Robust Visual Question Answering(VQA)
作者:Gao Peng, Zhengkai Jiang, Haoxuan You, Zhengkai Jiang, Pan Lu, Steven Hoi, Xiaogang Wang, Hongsheng Li
論文鏈接:https://arxiv.org/pdf/1812.05252.pdf
【126】Data augmentation using learned transformsfor one-shot medical image segmentation
作者:Amy Zhao, Guha Balakrishnan, Frédo Durand, John V. Guttag, Adrian V. Dalca
論文鏈接:https://arxiv.org/pdf/1902.09383.pdf
源碼鏈接:https://github.com/xamyzhao/brainstorm
【127】DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency (Oral )
作者:Kuang-Jui Hsu, Yen-Yu Lin, Yung-Yu Chuang
論文鏈接:http://cvlab.citi.sinica.edu.tw/images/paper/cvpr-hsu19.pdf
源碼鏈接:https://github.com/KuangJuiHsu/DeepCO3
【128】Calibration of Asynchronous Camera Networks for Object Reconstruction Tasks
作者:Amy Tabb, Henry Medeiros
論文鏈接:https://arxiv.org/abs/1903.06811
【129】LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks
作者:Sudhakar Kumawat, Shanmuganathan Raman
論文鏈接:https://arxiv.org/abs/1904.03498
【130】A Variational Auto-Encoder Model for Stochastic Point Processes
作者:Nazanin Mehrasa, Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, Greg Mori
論文鏈接:https://arxiv.org/abs/1904.03273
【131】2.5D Visual Sound(FAIR Oral)
作者:Ruohan Gao, Kristen Grauman
論文鏈接:https://arxiv.org/abs/1812.04204
項目鏈接:http://vision.cs.utexas.edu/projects/2.5D_visual_sound/
源碼鏈接:https://github.com/facebookresearch/FAIR-Play
【132】DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality
作者:Chloe LeGendre, Wan-Chun Ma, Graham Fyffe, John Flynn, Laurent Charbonnel, Jay Busch, Paul Debevec
論文鏈接:https://arxiv.org/abs/1904.01175
【133】Kervolutional Neural Networks
作者:Chen Wang, Jianfei Yang, Lihua Xie, Junsong Yuan
論文鏈接:https://arxiv.org/abs/1904.03955
【134】SoDeep: a Sorting Deep net to learn ranking loss surrogates
作者:Martin Engilberge, Louis Chevallier, Patrick Pérez, Matthieu Cord
論文鏈接:https://arxiv.org/abs/1904.04272
【135】3D Local Features for Direct Pairwise Registration
作者:Haowen Deng, Tolga Birdal, Slobodan Ilic
論文鏈接:https://arxiv.org/abs/1904.04281
【136】Neural Rerendering in the Wild(Oral)
作者:Moustafa Meshry, Dan B Goldman, Sameh Khamis, Hugues Hoppe, Rohit Pandey, Noah Snavely, Ricardo Martin-Brualla
論文鏈接:https://arxiv.org/abs/1904.04290
【137】End-to-end Projector Photometric Compensation
作者:Bingyao Huang, Haibin Ling
論文鏈接:https://arxiv.org/abs/1904.04335
【138】What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
作者:Paritosh Parmar, Brendan Tran Morris
論文鏈接:https://arxiv.org/abs/1904.04346
【139】Towards Universal Object Detection by Domain Attention
作者:Xudong Wang, Zhaowei Cai, Dashan Gao, Nuno Vasconcelos
論文鏈接:https://arxiv.org/abs/1904.04402
項目鏈接:http://www.svcl.ucsd.edu/projects/universal-detection/
【140】Efficient Decision-based Black-box Adversarial Attacks on Face Recognition(人臉識別)
作者:Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, Jun Zhu
論文鏈接:https://arxiv.org/abs/1904.04433
【141】Reliable and Efficient Image Cropping: A Grid Anchor based Approach
作者:Hui Zeng, Lida Li, Zisheng Cao, Lei Zhang
論文鏈接:https://arxiv.org/abs/1904.04441
代碼鏈接:https://github.com/HuiZeng/Grid-Anchor-based-Image-Cropping
【142】SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking(視覺跟蹤)
作者:Guangting Wang, Chong Luo, Zhiwei Xiong, Wenjun Zeng
論文鏈接:https://arxiv.org/abs/1904.04452
【143】Graphonomy: Universal Human Parsing via Graph Transfer Learning
作者:Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin
論文鏈接:https://arxiv.org/abs/1904.04536
源碼鏈接:https://github.com/Gaoyiminggithub/Graphonomy
【144】Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks
作者:Eunwoo Kim, Chanho Ahn, Philip H.S. Torr, Songhwai Oh
論文鏈接:https://arxiv.org/abs/1904.04562
【145】Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning from Radiology Reports and Label Ontology(Oral)
作者:Ke Yan, Yifan Peng, Veit Sandfort, Mohammadhadi Bagheri, Zhiyong Lu, Ronald M. Summers
論文鏈接:https://arxiv.org/abs/1904.04661
【146】Domain-Symmetric Networks for Adversarial Domain Adaptation
作者:Yabin Zhang, Hui Tang, Kui Jia, Mingkui Tan
論文鏈接:https://arxiv.org/abs/1904.04663
【147】Action Recognition from Single Timestamp Supervision in Untrimmed Videos(動作識別)
作者:Davide Moltisanti, Sanja Fidler, Dima Damen
論文鏈接:https://arxiv.org/abs/1904.04689
【148】Label Propagation for Deep Semi-supervised Learning
作者:Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum
論文鏈接:https://arxiv.org/abs/1904.04717
【149】Cross-Modal Self-Attention Network for Referring Image Segmentation
作者:Linwei Ye, Mrigank Rochan, Zhi Liu, Yang Wang
論文鏈接:https://arxiv.org/abs/1904.04745
【150】Leveraging the Invariant Side of Generative Zero-Shot Learning
作者:Jingjing Li, Mengmeng Jin, Ke Lu, Zhengming Ding, Lei Zhu, Zi Huang
論文鏈接:https://arxiv.org/abs/1904.04092
【151】Learning monocular depth estimation infusing traditional stereo knowledge
作者:Fabio Tosi, Filippo Aleotti, Matteo Poggi, Stefano Mattoccia
論文鏈接:https://arxiv.org/abs/1904.04144
代碼鏈接:https://github.com/fabiotosi92/monoResMatch-Tensorflow
【152】Unsupervised learning of action classes with continuous temporal embedding
作者:Anna Kukleva, Hilde Kuehne, Fadime Sener, Juergen Gall
論文鏈接:https://arxiv.org/abs/1904.04189
【153】Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering
作者:Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
論文鏈接:https://arxiv.org/abs/1904.04196
【154】Relational Action Forecasting(oral)
作者:Chen Sun, Abhinav Shrivastava, Carl Vondrick, Rahul Sukthankar, Kevin Murphy, Cordelia Schmid
論文鏈接:https://arxiv.org/abs/1904.04231
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
https://arxiv.org/abs/1904.08739
【155】A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
https://arxiv.org/abs/1904.08720
【156】Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
https://arxiv.org/abs/1904.08703
【157】DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
https://arxiv.org/abs/1904.08634
【158】Fooling automated surveillance cameras: adversarial patches to attack person detection
https://arxiv.org/abs/1904.08653
【159】Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
https://arxiv.org/abs/1904.08631
【160】Progressive Attention Memory Network for Movie Story Question Answering
https://arxiv.org/abs/1904.08607
【161】Unsupervised Person Image Generation with Semantic Parsing Transformation
https://arxiv.org/abs/1904.03379
【162】Unsupervised Person Image Generation with Semantic Parsing Transformation
論文鏈接:https://arxiv.org/abs/1904.03379
項目鏈接:https://github.com/SijieSong/person_generation_spt
【163】Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?
論文鏈接:https://arxiv.org/abs/1806.07550
【164】Self-Supervised GANs via Auxiliary Rotation Loss
論文鏈接:https://arxiv.org/abs/1811.11212
【165】Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
論文鏈接:https://arxiv.org/abs/1904.04776
【166】L3-Net: Towards Learning based LiDAR Localization for Autonomous Driving
論文鏈接:https://songshiyu01.github.io/pdf/L3Net_W.Lu_Y.Zhou_S.Song_CVPR2019.pdf
【167】Deep Convolutional Networks on 3D Point Clouds
論文鏈接:https://arxiv.org/pdf/1811.07246.pdf
源碼鏈接:https://github.com/DylanWusee/pointconv
【168】CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection
論文鏈接:https://drive.google.com/open?id=1JcZMHBXEX-7AR1P010OXg_wCCC5HukeZ(需要申請)
源碼鏈接:https://github.com/zhangludl/code-and-dataset-for-CapSal
【169】Segmentation-driven 6D Object Pose Estimation
論文鏈接:https://arxiv.org/abs/1812.02541
源碼鏈接:https://github.com/cvlab-epfl/segmentation-driven-pose
【170】LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
論文鏈接:https://arxiv.org/abs/1904.10037
【171】Learning Actor Relation Graphs for Group Activity Recognition
論文鏈接:https://arxiv.org/abs/1904.10117
【172】Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
論文鏈接:https://arxiv.org/abs/1904.10167
【173】Attention-guided Network for Ghost-free High Dynamic Range Imaging
論文鏈接:https://arxiv.org/abs/1904.10293
【174】Data-Driven Neuron Allocation for Scale Aggregation Networks
論文鏈接:https://arxiv.org/abs/1904.09460
【175】A Simple Pooling-Based Design for Real-Time Salient Object Detection
論文鏈接:https://arxiv.org/abs/1904.09569
源碼鏈接:http://mmcheng.net/poolnet/
【176】TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
論文鏈接:https://arxiv.org/abs/1904.09571
【177】Deep Metric Learning Beyond Binary Supervision(Oral)
論文鏈接:https://arxiv.org/abs/1904.09626
【178】Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks
論文鏈接:https://arxiv.org/abs/1904.09791
【179】PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval
論文鏈接:https://arxiv.org/abs/1904.09793
【180】Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids
論文鏈接:https://arxiv.org/abs/1904.09970
源碼鏈接:https://github.com/paschalidoud/superquadric_parsing
【181】ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging(Oral)
論文鏈接:https://contactdb.cc.gatech.edu/contactdb_paper.pdf
源碼鏈接:https://github.com/samarth-robo/contactdb_prediction
【182】Aggregation Cross-Entropy for Sequence Recognition
論文鏈接:https://arxiv.org/abs/1904.08364
【183】Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
論文鏈接:https://arxiv.org/abs/1904.08482
【184】Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset
論文鏈接:https://arxiv.org/abs/1904.08486
【185】Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
論文鏈接:https://arxiv.org/abs/1904.08487
【186】Few-Shot Learning with Localization in Realistic Settings
論文鏈接:https://arxiv.org/abs/1904.08502
【187】Progressive Attention Memory Network for Movie Story Question Answering
論文鏈接:https://arxiv.org/abs/1904.08607
【188】Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
論文鏈接:https://arxiv.org/abs/1904.08631
【189】DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
論文鏈接:https://arxiv.org/abs/1904.08634
【190】Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
論文鏈接:https://arxiv.org/abs/1904.08703
【191】A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
論文鏈接:https://arxiv.org/abs/1904.08720
【192】Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
論文鏈接:https://arxiv.org/abs/1904.08739
【193】4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
論文鏈接:https://arxiv.org/abs/1904.08755
【194】Attentive Single-Tasking of Multiple Tasks
論文鏈接:https://arxiv.org/abs/1904.08918
【195】Towards VQA Models that can Read
論文鏈接:https://arxiv.org/abs/1904.08920
【196】Listen to the Image
論文鏈接:https://arxiv.org/abs/1904.09115
【197】SelFlow: Self-Supervised Learning of Optical Flow
作者:Pengpeng Liu, Michael Lyu, Irwin King, Jia Xu
論文鏈接:https://arxiv.org/abs/1904.09117
【198】Visualizing the decision-making process in deep neural decision forest
論文鏈接:https://arxiv.org/abs/1904.09201
源碼鏈接:https://github.com/Nicholasli1995/VisualizingNDF
【199】STEP: Spatio-Temporal Progressive Learning for Video Action Detection(Oral,視頻動作識別)
論文鏈接:https://arxiv.org/abs/1904.09288
【200】Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
論文鏈接:https://arxiv.org/abs/1812.07179
【201】Transferrable Prototypical Networks for Unsupervised Domain Adaptation
論文鏈接:https://arxiv.org/abs/1904.11227
【202】Exploring Object Relation in Mean Teacher for Cross-Domain Detection
論文鏈接:https://arxiv.org/abs/1904.11245
【203】Pointing Novel Objects in Image Captioning
論文鏈接:https://arxiv.org/abs/1904.11251