CVPR 2017 accepted papers on Detection and segmentation
159 of the 783 papers accepted at CVPR 2017 (20.3%) are on Detection and segmentation, compared with 23.3% at CVPR 2016. They fall into 5 topics.
See CVPR 2017 in the interactive map
Submitting to CVPR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
CNN features · 87 papers
- Feature Pyramid Networks for Object Detection (29,987 citations)
- YOLO9000: Better, Faster, Stronger (19,336 citations)
- Pyramid Scene Parsing Network (15,903 citations)
- RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation (3,229 citations)
- Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors (2,699 citations)
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (1,859 citations)
- EAST: An Efficient and Accurate Scene Text Detector (1,852 citations)
- Dilated Residual Networks (1,789 citations)
- Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network (1,737 citations)
- Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition (1,477 citations)
- Deep Joint Rain Detection and Removal From a Single Image (1,280 citations)
- Deeply Supervised Salient Object Detection With Short Connections (1,206 citations)
and 75 more in the interactive map.
Open-set and few-shot detection · 36 papers
- Scene Parsing Through ADE20K Dataset (3,305 citations)
- Perceptual Generative Adversarial Networks for Small Object Detection (895 citations)
- A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection (674 citations)
- Learning Video Object Segmentation From Static Images (620 citations)
- Visual Translation Embedding Network for Visual Relation Detection (584 citations)
- YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video (566 citations)
- Learning Features by Watching Objects Move (491 citations)
- Annotating Object Instances With a Polygon-RNN (376 citations)
- Deep Learning Human Mind for Automated Visual Classification (295 citations)
- Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks (281 citations)
- Deep Variation-Structured Reinforcement Learning for Visual Relationship and Attribute Detection (248 citations)
- Cross-View Image Matching for Geo-Localization in Urban Environments (228 citations)
and 24 more in the interactive map.
Weakly supervised detection and segmentation · 20 papers
- Learning to Detect Salient Objects With Image-Level Supervision (1,320 citations)
- Object Region Mining With Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach (905 citations)
- Simple Does It: Weakly Supervised Instance and Semantic Segmentation (825 citations)
- Multiple Instance Detection Network With Online Instance Classifier Refinement (528 citations)
- WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation (368 citations)
- Weakly Supervised Cascaded Convolutional Networks (317 citations)
- Deep Self-Taught Learning for Weakly Supervised Object Localization (218 citations)
- Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation (218 citations)
- Exploiting Saliency for Object Segmentation From Image Level Labels (205 citations)
- Weakly Supervised Semantic Segmentation Using Web-Crawled Videos (150 citations)
- FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence (134 citations)
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (127 citations)
and 8 more in the interactive map.
Tracking · 11 papers
- Discriminative Correlation Filter With Channel and Spatial Reliability (1,189 citations)
- Large Margin Object Tracking With Circulant Feature Maps (606 citations)
- Multi-Task Correlation Particle Filter for Robust Object Tracking (446 citations)
- Multi-Object Tracking With Quadruplet Convolutional Neural Networks (265 citations)
- Deep Network Flow for Multi-Object Tracking (226 citations)
- End-To-End Representation Learning for Correlation Filter Based Tracking (189 citations)
- Object Detection in Videos With Tubelet Proposal Networks (161 citations)
- Robust Visual Tracking Using Oblique Random Forests (88 citations)
- Superpixel-Based Tracking-By-Segmentation Using Markov Chains (85 citations)
- Saliency Revisited: Analysis of Mouse Movements Versus Fixations (40 citations)
- The World of Fast Moving Objects (39 citations)
3D detection and driving · 5 papers
- 3D Bounding Box Estimation Using Deep Learning and Geometry (1,208 citations)
- SGM-Nets: Semi-Global Matching With Neural Networks (295 citations)
- Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation (189 citations)
- Amodal Detection of 3D Objects: Inferring 3D Bounding Boxes From 2D Ones in RGB-Depth Images (108 citations)
- Visual-Inertial-Semantic Scene Representation for 3D Object Detection (51 citations)
