IJCV 2020 papers on Detection and segmentation
24 of the 119 papers published in IJCV 2020 (20.2%) are on Detection and segmentation, compared with 18.8% at IJCV 2019. They fall into 4 topics.
See IJCV 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
Open-set and few-shot detection · 9 papers
- Rain Rendering for Evaluating and Improving Robustness to Bad Weather (144 citations)
- Pixel-Wise Crowd Understanding via Synthetic Data (135 citations)
- Benchmarking the Robustness of Semantic Segmentation Models with Respect to Common Corruptions (80 citations)
- Adversarial Confidence Learning for Medical Image Segmentation and Synthesis (60 citations)
- Zero-Shot Object Detection: Joint Recognition and Localization of Novel Concepts (59 citations)
- Multi-task Compositional Network for Visual Relationship Detection (33 citations)
- CDTD: A Large-Scale Cross-Domain Benchmark for Instance-Level Image-to-Image Translation and Domain Adaptive Object Detection (24 citations)
- Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image (5 citations)
- The Open Images Dataset V4
CNN features · 6 papers
- Scene Text Detection and Recognition: The Deep Learning Era (574 citations)
- JÂA-Net: Joint Facial Action Unit Detection and Face Alignment Via Adaptive Attention (160 citations)
- Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion (102 citations)
- Recursive Context Routing for Object Detection (40 citations)
- Rooted Spanning Superpixels (16 citations)
- Bottom-Up Scene Text Detection with Markov Clustering Networks (13 citations)
Tracking · 5 papers
- HOTA: A Higher Order Metric for Evaluating Multi-object Tracking (1,433 citations)
- MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking (426 citations)
- LaSOT: A High-quality Large-scale Single Object Tracking Benchmark (388 citations)
- Unsupervised Deep Representation Learning for Real-Time Tracking (126 citations)
- Semi-online Multi-people Tracking by Re-identification (57 citations)
Weakly supervised detection and segmentation · 4 papers
- Weakly-supervised Semantic Guided Hashing for Social Image Retrieval (192 citations)
- A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains (122 citations)
- Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning (105 citations)
- Weakly Supervised Group Mask Network for Object Detection (11 citations)
