AAAI 2021 accepted papers on Detection and segmentation
88 of the 1,654 papers accepted at AAAI 2021 (5.3%) are on Detection and segmentation, compared with 6.0% at AAAI 2020. They fall into 5 topics.
See AAAI 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 · 41 papers
- R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object (1,151 citations)
- Dynamic Anchor Learning for Arbitrary-Oriented Object Detection (361 citations)
- Dual-level Collaborative Transformer for Image Captioning (323 citations)
- Learning Modulated Loss for Rotated Object Detection (320 citations)
- Local Relation Learning for Face Forgery Detection (314 citations)
- RESA: Recurrent Feature-Shift Aggregator for Lane Detection (307 citations)
- Locate Globally, Segment Locally: A Progressive Architecture With Knowledge Review Network for Salient Object Detection (180 citations)
- Pyramidal Feature Shrinking for Salient Object Detection (171 citations)
- RGB-D Salient Object Detection via 3D Convolutional Neural Networks (171 citations)
- Inferring Camouflaged Objects by Texture-Aware Interactive Guidance Network (139 citations)
- Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification (133 citations)
- Localization in the Crowd with Topological Constraints (124 citations)
and 29 more in the interactive map.
Open-set and few-shot detection · 28 papers
- Learning Semantic Context from Normal Samples for Unsupervised Anomaly Detection (177 citations)
- Object-Centric Image Generation from Layouts (78 citations)
- Amodal Segmentation Based on Visible Region Segmentation and Shape Prior (62 citations)
- Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks (61 citations)
- DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection (51 citations)
- Bidirectional RNN-based Few Shot Learning for 3D Medical Image Segmentation (46 citations)
- Efficient Poverty Mapping from High Resolution Remote Sensing Images (44 citations)
- DropLoss for Long-Tail Instance Segmentation (36 citations)
- Semantic-guided Reinforced Region Embedding for Generalized Zero-Shot Learning (33 citations)
- Distilling Localization for Self-Supervised Representation Learning (31 citations)
- Rethinking Object Detection in Retail Stores (27 citations)
- Binaural Audio-Visual Localization (25 citations)
and 16 more in the interactive map.
Weakly supervised detection and segmentation · 9 papers
- Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence (163 citations)
- DenserNet: Weakly Supervised Visual Localization Using Multi-Scale Feature Aggregation (134 citations)
- Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation (131 citations)
- Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation (115 citations)
- Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection (42 citations)
- Instance Mining with Class Feature Banks for Weakly Supervised Object Detection (41 citations)
- GradingNet: Towards Providing Reliable Supervisions for Weakly Supervised Object Detection by Grading the Box Candidates (20 citations)
- StarNet: towards Weakly Supervised Few-Shot Object Detection (14 citations)
- How to Save your Annotation Cost for Panoptic Segmentation? (2 citations)
Tracking · 5 papers
- Towards Universal Physical Attacks on Single Object Tracking (33 citations)
- A Scalable Reasoning and Learning Approach for Neural-Symbolic Stream Fusion (14 citations)
- Model Uncertainty Guides Visual Object Tracking (11 citations)
- AugSplicing: Synchronized Behavior Detection in Streaming Tensors (3 citations)
- The Complexity of Object Association in Multiple Object Tracking (2 citations)
3D detection and driving · 5 papers
- Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection (1,004 citations)
- RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving (34 citations)
- Boosting Image-based Mutual Gaze Detection using Pseudo 3D Gaze (18 citations)
- Semantic Consistency Networks for 3D Object Detection (8 citations)
- Supervised Training of Dense Object Nets using Optimal Descriptors for Industrial Robotic Applications (7 citations)
