TPAMI 2020 papers on Detection and segmentation
38 of the 368 papers published in TPAMI 2020 (10.3%) are on Detection and segmentation, compared with 13.2% at TPAMI 2019. They fall into 5 topics.
See TPAMI 2020 in the interactive map
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 · 22 papers
- Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection (1,065 citations)
- FCOS: A Simple and Strong Anchor-free Object Detector (996 citations)
- Imbalance Problems in Object Detection: A Review (632 citations)
- YOLACT++ Better Real-Time Instance Segmentation (581 citations)
- JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (297 citations)
- DSNet: Joint Semantic Learning for Object Detection in Inclement Weather Conditions (277 citations)
- Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection (246 citations)
- BDCN: Bi-Directional Cascade Network for Perceptual Edge Detection (164 citations)
- Kernel-Based Density Map Generation for Dense Object Counting (148 citations)
- RefineFace: Refinement Neural Network for High Performance Face Detection (119 citations)
- AP-Loss for Accurate One-Stage Object Detection (87 citations)
- DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Discriminative Multi-Scale Deep Features (84 citations)
and 10 more in the interactive map.
Weakly supervised detection and segmentation · 7 papers
- Self-Correction for Human Parsing (461 citations)
- A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology (325 citations)
- Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation (161 citations)
- Weakly Supervised Object Detection Using Proposal- and Semantic-Level Relationships (140 citations)
- Attention-Based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation (120 citations)
- Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-Segmentation (73 citations)
- Towards Partial Supervision for Generic Object Counting in Natural Scenes (14 citations)
Open-set and few-shot detection · 4 papers
- Prior Guided Feature Enrichment Network for Few-Shot Segmentation (720 citations)
- Chart Mining: A Survey of Methods for Automated Chart Analysis (107 citations)
- Revisiting Image-Language Networks for Open-Ended Phrase Detection (18 citations)
- Consistent estimation of the max-flow problem: Towards unsupervised image segmentation
Tracking · 3 papers
- Deep Object Tracking with Shrinkage Loss (82 citations)
- Deep Visual Odometry With Adaptive Memory (27 citations)
- Efficient Global MOT Under Minimum-Cost Circulation Framework (13 citations)
