ECCV 2018 accepted papers on Detection and segmentation
140 of the 776 papers accepted at ECCV 2018 (18.0%) are on Detection and segmentation, compared with 19.0% at ECCV 2016. They fall into 5 topics.
See ECCV 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 · 71 papers
- CBAM: Convolutional Block Attention Module (26,917 citations)
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (21,095 citations)
- CornerNet: Detecting Objects as Paired Keypoints (3,907 citations)
- BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation (3,023 citations)
- Receptive Field Block Net for Accurate and Fast Object Detection (1,914 citations)
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images (1,751 citations)
- PSANet: Point-wise Spatial Attention Network for Scene Parsing (1,245 citations)
- Acquisition of Localization Confidence for Accurate Object Detection (1,071 citations)
- ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation (1,048 citations)
- Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (904 citations)
- Reverse Attention for Salient Object Detection (728 citations)
- TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (650 citations)
and 59 more in the interactive map.
Open-set and few-shot detection · 34 papers
- Recognition in Terra Incognita (753 citations)
- SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network (497 citations)
- Zero-Shot Object Detection (390 citations)
- License Plate Detection and Recognition in Unconstrained Scenarios (379 citations)
- Instance-level Human Parsing via Part Grouping Network (378 citations)
- BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization (365 citations)
- Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (350 citations)
- Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding (279 citations)
- Modeling Visual Context is Key to Augmenting Object Detection Datasets (275 citations)
- Dynamic Multimodal Instance Segmentation Guided by Natural Language Queries (192 citations)
- Key-Word-Aware Network for Referring Expression Image Segmentation (184 citations)
- Attributes as Operators: Factorizing Unseen Attribute-Object Compositions (183 citations)
and 22 more in the interactive map.
Tracking · 18 papers
- Distractor-aware Siamese Networks for Visual Object Tracking (1,584 citations)
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (1,237 citations)
- The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking (1,170 citations)
- Triplet Loss in Siamese Network for Object Tracking (670 citations)
- Unveiling the Power of Deep Tracking (515 citations)
- Learning Dynamic Memory Networks for Object Tracking (387 citations)
- Online Multi-Object Tracking with Dual Matching Attention Networks (378 citations)
- Real-Time MDNet (295 citations)
- Structured Siamese Network for Real-Time Visual Tracking (273 citations)
- Deep Regression Tracking with Shrinkage Loss (252 citations)
- Multi-object Tracking with Neural Gating Using Bilinear LSTM (246 citations)
- Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers (191 citations)
and 6 more in the interactive map.
Weakly supervised detection and segmentation · 14 papers
- Exploring the Limits of Weakly Supervised Pretraining (1,271 citations)
- On Regularized Losses for Weakly-supervised CNN Segmentation (299 citations)
- Self-produced Guidance for Weakly-supervised Object Localization (248 citations)
- Weakly Supervised Region Proposal Network and Object Detection (204 citations)
- Adaptive Affinity Fields for Semantic Segmentation (202 citations)
- Weakly- and Semi-Supervised Panoptic Segmentation (173 citations)
- TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection (140 citations)
- Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation (104 citations)
- Learning to Segment via Cut-and-Paste (97 citations)
- C-WSL: Count-guided Weakly Supervised Localization (96 citations)
- PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence (57 citations)
- DOCK: Detecting Objects by transferring Common-sense Knowledge (29 citations)
and 2 more in the interactive map.
3D detection and driving · 3 papers
- Deep Continuous Fusion for Multi-Sensor 3D Object Detection (1,010 citations)
- Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving (157 citations)
- Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery (3 citations)
