AAAI 2019 accepted papers on Detection and segmentation
51 of the 1,147 papers accepted at AAAI 2019 (4.4%) are on Detection and segmentation, compared with 4.2% at AAAI 2018. They fall into 5 topics.
See AAAI 2019 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 · 25 papers
- M2Det: A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network (865 citations)
- Gradient Harmonized Single-Stage Detector (597 citations)
- Devil in the Details: Towards Accurate Single and Multiple Human Parsing (276 citations)
- Scene Text Detection with Supervised Pyramid Context Network (241 citations)
- Selective Refinement Network for High Performance Face Detection (181 citations)
- Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism (154 citations)
- Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks (122 citations)
- Multi3Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery (118 citations)
- Robust Deep Co-Saliency Detection with Group Semantic (75 citations)
- Densely Supervised Grasp Detector (DSGD) (56 citations)
- DeRPN: Taking a Further Step toward More General Object Detection (51 citations)
- TableSense: Spreadsheet Table Detection with Convolutional Neural Networks (50 citations)
and 13 more in the interactive map.
Open-set and few-shot detection · 15 papers
- Large-Scale Visual Relationship Understanding (161 citations)
- Attention-Based Multi-Context Guiding for Few-Shot Semantic Segmentation (141 citations)
- Cooperative Multimodal Approach to Depression Detection in Twitter (138 citations)
- Zero-Shot Object Detection with Textual Descriptions (82 citations)
- Biomedical Image Segmentation via Representative Annotation (69 citations)
- Learning Object Context for Dense Captioning (46 citations)
- Recognizing Unseen Attribute-Object Pair with Generative Model (41 citations)
- MR-NET: Exploiting Mutual Relation for Visual Relationship Detection (20 citations)
- Human-Like Sketch Object Recognition via Analogical Learning (18 citations)
- Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping (7 citations)
- Learning Segmentation Masks with the Independence Prior (3 citations)
- On Lifted Inference Using Neural Embeddings (3 citations)
and 3 more in the interactive map.
Tracking · 6 papers
- Robust Estimation of Similarity Transformation for Visual Object Tracking (97 citations)
- Detect or Track: Towards Cost-Effective Video Object Detection/Tracking (61 citations)
- Learning Attribute-Specific Representations for Visual Tracking (45 citations)
- Learning Non-Uniform Hypergraph for Multi-Object Tracking (41 citations)
- Re2EMA: Regularized and Reinitialized Exponential Moving Average for Target Model Update in Object Tracking (8 citations)
- Learning a Visual Tracker from a Single Movie without Annotation (4 citations)
Weakly supervised detection and segmentation · 4 papers
- Weakly-Supervised Simultaneous Evidence Identification and Segmentation for Automated Glaucoma Diagnosis (45 citations)
- Learning to Localize Objects with Noisy Labeled Instances (15 citations)
- Human-Like Delicate Region Erasing Strategy for Weakly Supervised Detection (1 citation)
- A Topic-Aware Reinforced Model for Weakly Supervised Stance Detection
