写在前面

未经允许，不得转载，谢谢~~~

把目前看的一些论文简单整理一下，方便以后查阅。

看的论文还是太少了，都不好意思放出来ε(┬┬﹏┬┬)3，接下来持续更新~

1. Video Captioning

• CVPR2015: sequence to sequence - video to text 0

2. Video Action Recognition（Video Representation Learning）

• ICCV2015: Learning Spatiotemporal Features with 3D Convolutional Networks 1 C3D
• ICCV2017: Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks 2 P3D
• CVPR2018: A Closer Look at Spatiotemporal convolutions for action recognition 3 R(2+1)D
• CVPR2018: What makes a video a video: Analyzing Temporal Information in Video Understanding models and Dateset 8
• CVPR2018: Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning 9
• ECCV2016: Temporal Segment Networks：Towards Good Practices for Deep Action Recognition12 TSN
• CVPR2017: Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset 14 I3D
• ICCV2011: HMDB: A Large Video Database for Human Motion Recognition 15 HMDB dataset
• ACM-MM2016: Multi-Stream Multi-Class Fusion of Deep Networks for Video Classification 19 multi-model
• ECCV2018：Temporal relational reasoning in videos 24 TRN
• NIPS2014: Two-stream Convolution Networks for Action Recognition in Videos 41 two-stream
• CVPR2015: long-term recurrent convolutional networks for visual recognition and description 42 LRCN
• CVPR2016：convolutional two-stream network fusion for video action recognition 43
• CVPR2019: PA3D: Pose-Action 3D Machine for Video Recognition 60 PA3D combine pose

3. Image Retrieval

• [TPAMI重磅综述]SIFT与CNN的碰撞：万字长文回顾图像检索任务十年探索历程（上篇） review
• [TPAMI重磅综述]SIFT与CNN的碰撞：万字长文回顾图像检索任务十年探索历程（下篇） review
• ACM Transactions on Graphics 2015：Learning visual similarity for product design with convolutional neural networks 6
• CVPR2015: FaceNet: A unified Embedding for face recognition and clustering 7 facenet

4. Object Detection

• ECCV2016: SSD: Single Shot MultiBox Detector 11 SSD

5. Knowledge Distillation

• NIPS2015: Distilling the knowledge in a neural network 18
• arxiv2019: dataset distillation 45

6. 3D Reconstruction

• ECCV2018：Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images 26 pixel2mesh
• CVPR2018: End-to-end Recovery of Human Shape and Pose 27 HMR
• 3DV2017: towards accurate markerless human shape and pose estimation over time 28
• CVPR2018： DensePose: Dense Human Pose Estimation In The Wild 29 DensePose DensePose-COCO dataset
• Computer Vision and Image Understanding 2016: 3D Human pose estimation: A review of the literature and analysis of covariates 30 review
• CVPR2017: Unite the People: Closing the Loop Between 3D and 2D Human Representations 31 up-3d dataset
• NIPS2018: Visual Object Networks: Image Generation with Disentangled 3D Representation 46 VON
• CVPR2019 oral：Deep Voxels: Learning Persistent 3D Feature Embeddings 47 DeepVoxels
• arxiv2019: Vid2Game: Controllable Characters Extracted from Real-World Videos 48
• CVPR2019 oral：Convolutional Mesh Regression for Single-Image Human Shape Reconstruction 49
• ACM TOG 2015： SMPL: A Skinned Multi-Person Linear Model 50 SMPL
• arxiv2019: DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction 54 DISN
• CVPR2019: Learning joint reconstruction of hands and manipulated objects 55
• CVPR2019: DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation 55 DeepSDF
• CVPR2019: Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation 56
• CVPR2019: Photo Wake-Up: 3D Character Animation from a Single Photo, 58 animation

7. One-shot Leaning

One-shot Image classification

• ICLR2019：image deformation meta-network for one-shot learning 32 IDeMeNet
• NIPS2017：prototypical networks for few-shot learning 36
• AAAI 2019：image block augmentation for one-shot learning 37
• NIPS2016: matching networks for one-shot learning 57 Matching Net

One-shot video classification

• ECCV2018: compound memory networks for few-shot video classification 33 CMN

else one-shot learning tasks

• CVPR2018: one-shot action localization by learning sequence matching network 39 action localization sliding window

8. Else

• ICCV2017: Deformable Convolutional Networks 4 deform conv
• CVPR2018： Learning Semantic Concepts and Order for Image and Sentence Matching 5 Image and sentence matching
• CVPR2018: temporal deformable residual networks for action segmentation in videos 10 deform conv TDRN
• IEEE Access 2018：POLSAR image classification via Clustering-WAE classification model 17 image classifictaion clustering
• CVPR2015：Webly Supervised Learning of Convolutional Networks 20 webly learning image classification
• CVPR 2018：Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification 21 webly learning image classification zero-shot learning
• ICML2018：Block-box adversarial attacks with limited queries and information 22 adversarial attack
• Neuro-computing 2014：a novel graph-based k-means for nonlinear manifold clustering and representative selection 23 clustering
• Artificial Intelligence 2002：A perspective view and survey of meta-learning 34 review meta-learning
• arxiv2018：meta-learining: a survey 35 review meta-learning
• CVPR2015: show attend and tell neural image caption generation with visual attention 38 attention image captioning
• CVPR2017：adversarial discriminative domain adaptation 40 adversarial learning domain adaptation
• CVPR2019: Synthesizing Environment-Aware Activities via Activity Sketches 59 agent synthesis videos VirtualHome VirtualHome-Env

papers for course projects

• CHI2014： CHI 1994-2013: mapping two decades of intellectual progress through co-word analysis 13 human interaction
• LERC2016：RankDCG：Rank-ordering evaluation measure 16 retrieval rank measure RankDCG
• ACL2017: Deep Pyramid Convolutional Neural Networks for Text Categorization 25 nlp text categorization pyramid DPCNN
• CVPR2015: Histograms of Oriented Gradients for Human Detection 52 HOG human detection object detection
• PAMI2010：object detection with discriminatively trained part based models 53 DPM object detection