IJCV 2021 papers on Detection and segmentation
35 of the 130 papers published in IJCV 2021 (26.9%) are on Detection and segmentation, compared with 20.2% at IJCV 2020. They fall into 4 topics.
See IJCV 2021 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 · 18 papers
- FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (2,059 citations)
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation (1,909 citations)
- OCNet: Object Context for Semantic Segmentation (890 citations)
- EfficientPS: Efficient Panoptic Segmentation (270 citations)
- Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild (171 citations)
- Semantic Edge Detection with Diverse Deep Supervision (113 citations)
- Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection (40 citations)
- Guided Attention in CNNs for Occluded Pedestrian Detection and Re-identification (33 citations)
- CNN-Based RGB-D Salient Object Detection: Learn, Select, and Fuse (31 citations)
- NAS-FCOS: Efficient Search for Object Detection Architectures (30 citations)
- Towards Balanced Learning for Instance Recognition (27 citations)
- Saliency Detection Inspired by Topological Perception Theory (26 citations)
and 6 more in the interactive map.
Open-set and few-shot detection · 10 papers
- The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection (674 citations)
- The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation (169 citations)
- Towards High Performance Human Keypoint Detection (97 citations)
- Polysemy Deciphering Network for Robust Human–Object Interaction Detection (60 citations)
- A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection (35 citations)
- Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition (22 citations)
- Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition (20 citations)
- Deep Human-Interaction and Association by Graph-Based Learning for Multiple Object Tracking in the Wild (13 citations)
- DeepFlux for Skeleton Detection in the Wild (10 citations)
- Evaluating Visual Properties via Robust HodgeRank (8 citations)
Tracking · 5 papers
- Learning Adaptive Attribute-Driven Representation for Real-Time RGB-T Tracking (194 citations)
- Learning Regression and Verification Networks for Robust Long-term Tracking (103 citations)
- Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters (74 citations)
- Deep Trajectory Post-Processing and Position Projection for Single & Multiple Camera Multiple Object Tracking (26 citations)
- Tracking by Deblatting (5 citations)
