ICCV 2019 accepted papers on Detection and segmentation
200 of the 1,075 papers accepted at ICCV 2019 (18.6%) are on Detection and segmentation, compared with 19.5% at ICCV 2017. They fall into 5 topics.
See ICCV 2019 in the interactive map
Submitting to ICCV? 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 · 99 papers
- FCOS: Fully Convolutional One-Stage Object Detection (7,269 citations)
- CenterNet: Keypoint Triplets for Object Detection (4,213 citations)
- CCNet: Criss-Cross Attention for Semantic Segmentation (3,299 citations)
- YOLACT: Real-Time Instance Segmentation (2,646 citations)
- Attention Augmented Convolutional Networks (1,352 citations)
- RepPoints: Point Set Representation for Object Detection (1,328 citations)
- EGNet: Edge Guidance Network for Salient Object Detection (1,297 citations)
- Scale-Aware Trident Networks for Object Detection (1,254 citations)
- CARAFE: Content-Aware ReAssembly of FEatures (1,223 citations)
- Rethinking ImageNet Pre-Training (1,214 citations)
- SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects (1,111 citations)
- Gated-SCNN: Gated Shape CNNs for Semantic Segmentation (903 citations)
and 87 more in the interactive map.
Open-set and few-shot detection · 47 papers
- PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (1,645 citations)
- Few-Shot Object Detection via Feature Reweighting (917 citations)
- Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning (684 citations)
- Miss Detection vs. False Alarm: Adversarial Learning for Small Object Segmentation in Infrared Images (534 citations)
- nocaps: novel object captioning at scale (427 citations)
- Local Aggregation for Unsupervised Learning of Visual Embeddings (425 citations)
- Feature Weighting and Boosting for Few-Shot Segmentation (411 citations)
- Meta-Learning to Detect Rare Objects (381 citations)
- Multi-Adversarial Faster-RCNN for Unrestricted Object Detection (380 citations)
- Human-Aware Motion Deblurring (368 citations)
- Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation (367 citations)
- Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation (310 citations)
and 35 more in the interactive map.
Weakly supervised detection and segmentation · 31 papers
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features (5,740 citations)
- Integral Object Mining via Online Attention Accumulation (264 citations)
- DANet: Divergent Activation for Weakly Supervised Object Localization (225 citations)
- CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation (197 citations)
- Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation (192 citations)
- WSOD2: Learning Bottom-Up and Top-Down Objectness Distillation for Weakly-Supervised Object Detection (164 citations)
- HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images (161 citations)
- Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization (155 citations)
- Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation (142 citations)
- Semi-Supervised Video Salient Object Detection Using Pseudo-Labels (142 citations)
- Towards Precise End-to-End Weakly Supervised Object Detection Network (141 citations)
- SegSort: Segmentation by Discriminative Sorting of Segments (129 citations)
and 19 more in the interactive map.
Tracking · 12 papers
- Learning Discriminative Model Prediction for Tracking (1,551 citations)
- Tracking Without Bells and Whistles (1,151 citations)
- Learning the Model Update for Siamese Trackers (483 citations)
- Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking (439 citations)
- GradNet: Gradient-Guided Network for Visual Object Tracking (351 citations)
- Spatial-Temporal Relation Networks for Multi-Object Tracking (276 citations)
- Robust Multi-Modality Multi-Object Tracking (255 citations)
- FAMNet: Joint Learning of Feature, Affinity and Multi-Dimensional Assignment for Online Multiple Object Tracking (248 citations)
- Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking (233 citations)
- 'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-Term Tracking (218 citations)
- Deep Meta Learning for Real-Time Target-Aware Visual Tracking (121 citations)
- CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark (81 citations)
3D detection and driving · 11 papers
- M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (603 citations)
- Disentangling Monocular 3D Object Detection (533 citations)
- WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving (338 citations)
- Joint Monocular 3D Vehicle Detection and Tracking (260 citations)
- 3D-LaneNet: End-to-End 3D Multiple Lane Detection (220 citations)
- Deep Optics for Monocular Depth Estimation and 3D Object Detection (189 citations)
- RIO: 3D Object Instance Re-Localization in Changing Indoor Environments (168 citations)
- SpaceNet MVOI: A Multi-View Overhead Imagery Dataset (96 citations)
- Learning Object-Specific Distance From a Monocular Image (88 citations)
- Transferable Semi-Supervised 3D Object Detection From RGB-D Data (39 citations)
- Simultaneous Multi-View Instance Detection With Learned Geometric Soft-Constraints (31 citations)
