ECCV 2020 accepted papers on Detection and segmentation
208 of the 1,358 papers accepted at ECCV 2020 (15.3%) are on Detection and segmentation, compared with 18.0% at ECCV 2018. They fall into 5 topics.
See ECCV 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
CNN features · 109 papers
- Object-Contextual Representations for Semantic Segmentation (1,310 citations)
- Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues (1,143 citations)
- SOLO: Segmenting Objects by Locations (932 citations)
- Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training (737 citations)
- Arbitrary-Oriented Object Detection with Circular Smooth Label (709 citations)
- Learning Data Augmentation Strategies for Object Detection (667 citations)
- Ultra Fast Structure-aware Deep Lane Detection (606 citations)
- Probabilistic Anchor Assignment with IoU Prediction for Object Detection (551 citations)
- Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation (506 citations)
- BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (401 citations)
- Disentangled Non-local Neural Networks (378 citations)
- Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems (372 citations)
and 97 more in the interactive map.
Open-set and few-shot detection · 42 papers
- Prototype Mixture Models for Few-shot Semantic Segmentation (471 citations)
- Part-aware Prototype Network for Few-shot Semantic Segmentation (404 citations)
- Multi-Scale Positive Sample Refinement for Few-Shot Object Detection (401 citations)
- Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild (266 citations)
- Attention Guided Anomaly Localization in Images (262 citations)
- Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector (262 citations)
- Segmenting Transparent Objects in the Wild (237 citations)
- Few-Shot Semantic Segmentation with Democratic Attention Networks (227 citations)
- DRG: Dual Relation Graph for Human-Object Interaction Detection (220 citations)
- Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions (209 citations)
- Visual Compositional Learning for Human-Object Interaction Detection (204 citations)
- Contextual Diversity for Active Learning (193 citations)
and 30 more in the interactive map.
Weakly supervised detection and segmentation · 27 papers
- Self-supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation (302 citations)
- Weakly Supervised Semantic Segmentation with Boundary Exploration (194 citations)
- Rethinking Class Activation Mapping for Weakly Supervised Object Localization (118 citations)
- Inter-Image Communication for Weakly Supervised Localization (113 citations)
- Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation (101 citations)
- Geometry Constrained Weakly Supervised Object Localization (90 citations)
- Improving Object Detection with Selective Self-Supervised Self-Training (79 citations)
- Object Detection with a Unified Label Space from Multiple Datasets (68 citations)
- Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation (65 citations)
- Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation (62 citations)
- Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances (62 citations)
- Enabling Deep Residual Networks for Weakly Supervised Object Detection (52 citations)
and 15 more in the interactive map.
3D detection and driving · 18 papers
- Tracking Objects as Points (1,502 citations)
- 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection (527 citations)
- RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving (382 citations)
- ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language (365 citations)
- Rethinking Pseudo-LiDAR Representation (214 citations)
- H3DNet: 3D Object Detection Using Hybrid Geometric Primitives (203 citations)
- Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots (195 citations)
- Kinematic 3D Object Detection in Monocular Video (194 citations)
- Generative Sparse Detection Networks for 3D Single-shot Object Detection (126 citations)
- Towards Generalization Across Depth for Monocular 3D Object Detection (73 citations)
- Improving 3D Object Detection through Progressive Population Based Augmentation (64 citations)
- Distance-Normalized Unified Representation for Monocular 3D Object Detection (56 citations)
and 6 more in the interactive map.
Tracking · 12 papers
- Towards Real-Time Multi-Object Tracking (1,276 citations)
- Ocean: Object-aware Anchor-free Tracking (906 citations)
- Know Your Surroundings: Exploiting Scene Information for Object Tracking (420 citations)
- Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking (406 citations)
- TAO: A Large-Scale Benchmark for Tracking Any Object (186 citations)
- RadarNet: Exploiting Radar for Robust Perception of Dynamic Objects (157 citations)
- Learning Feature Embeddings for Discriminant Model based Tracking (100 citations)
- PG-Net: Pixel to Global Matching Network for Visual Tracking (100 citations)
- CLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers (97 citations)
- Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking (54 citations)
- Object Tracking using Spatio-Temporal Networks for Future Prediction Location (25 citations)
- Learning Object Permanence from Video (20 citations)
