AAAI 2018 accepted papers on Detection and segmentation
39 of the 937 papers accepted at AAAI 2018 (4.2%) are on Detection and segmentation, compared with 3.6% at AAAI 2017. They fall into 5 topics.
See AAAI 2018 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 · 19 papers
- Spatial as Deep: Spatial CNN for Traffic Scene Understanding (1,251 citations)
- PixelLink: Detecting Scene Text via Instance Segmentation (648 citations)
- Recurrently Aggregating Deep Features for Salient Object Detection (168 citations)
- A Neural Attention Model for Urban Air Quality Inference: Learning the Weights of Monitoring Stations (151 citations)
- SqueezedText: A Real-Time Scene Text Recognition by Binary Convolutional Encoder-Decoder Network (98 citations)
- SEE: Towards Semi-Supervised End-to-End Scene Text Recognition (67 citations)
- Feature Enhancement Network: A Refined Scene Text Detector (58 citations)
- SFCN-OPI: Detection and Fine-Grained Classification of Nuclei Using Sibling FCN With Objectness Prior Interaction (57 citations)
- Deep Region Hashing for Generic Instance Search from Images (51 citations)
- R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection (37 citations)
- Audio Visual Attribute Discovery for Fine-Grained Object Recognition (30 citations)
- Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection (27 citations)
and 7 more in the interactive map.
Open-set and few-shot detection · 11 papers
- LSTD: A Low-Shot Transfer Detector for Object Detection (407 citations)
- Visual Relationship Detection With Deep Structural Ranking (97 citations)
- Using Syntax to Ground Referring Expressions in Natural Images (57 citations)
- Deep Structured Learning for Visual Relationship Detection (56 citations)
- HCVRD: A Benchmark for Large-Scale Human-Centered Visual Relationship Detection (47 citations)
- RelNN: A Deep Neural Model for Relational Learning (46 citations)
- Progressive Cognitive Human Parsing (45 citations)
- MixedPeds: Pedestrian Detection in Unannotated Videos Using Synthetically Generated Human-Agents for Training (19 citations)
- Learning to Rank Based on Analogical Reasoning (17 citations)
- Tap and Shoot Segmentation (17 citations)
- Towards Efficient Detection of Overlapping Communities in Massive Networks
Weakly supervised detection and segmentation · 6 papers
- Weakly Supervised Salient Object Detection Using Image Labels (139 citations)
- Mix-and-Match Tuning for Self-Supervised Semantic Segmentation (34 citations)
- Transferable Semi-Supervised Semantic Segmentation (26 citations)
- Weakly Supervised Induction of Affective Events by Optimizing Semantic Consistency (22 citations)
- Lagrangian Constrained Community Detection (9 citations)
- Kill Two Birds With One Stone: Weakly-Supervised Neural Network for Image Annotation and Tag Refinement (7 citations)
