ECCV 2016 accepted papers on Detection and segmentation
79 of the 415 papers accepted at ECCV 2016 (19.0%) are on Detection and segmentation. They fall into 5 topics.
See ECCV 2016 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 · 39 papers
- SSD: Single Shot MultiBox Detector (31,619 citations)
- A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection (1,625 citations)
- LIFT: Learned Invariant Feature Transform (1,341 citations)
- Detecting Text in Natural Image with Connectionist Text Proposal Network (1,088 citations)
- Is Faster R-CNN Doing Well for Pedestrian Detection? (860 citations)
- Learning to Refine Object Segments (781 citations)
- Saliency Detection with Recurrent Fully Convolutional Networks (521 citations)
- Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation (505 citations)
- Segmentation from Natural Language Expressions (483 citations)
- A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning (396 citations)
- Recurrent Instance Segmentation (332 citations)
- Higher Order Conditional Random Fields in Deep Neural Networks (212 citations)
and 27 more in the interactive map.
Open-set and few-shot detection · 16 papers
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (2,820 citations)
- Playing for Data: Ground Truth from Computer Games (1,987 citations)
- Visual Relationship Detection with Language Priors (1,148 citations)
- Towards Perspective-Free Object Counting with Deep Learning (656 citations)
- Modeling Context Between Objects for Referring Expression Understanding (472 citations)
- A 4D Light-Field Dataset and CNN Architectures for Material Recognition (179 citations)
- Amodal Instance Segmentation (163 citations)
- Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net (157 citations)
- A Multi-scale CNN for Affordance Segmentation in RGB Images (147 citations)
- It’s Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos (131 citations)
- COCO Attributes: Attributes for People, Animals, and Objects (99 citations)
- Interactive Image Segmentation Using Constrained Dominant Sets (44 citations)
and 4 more in the interactive map.
Weakly supervised detection and segmentation · 13 papers
- What’s the Point: Semantic Segmentation with Point Supervision (1,003 citations)
- Top-Down Neural Attention by Excitation Backprop (820 citations)
- Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation (786 citations)
- Learning Visual Features from Large Weakly Supervised Data (317 citations)
- ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization (297 citations)
- Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation (158 citations)
- Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation (140 citations)
- Augmented Feedback in Semantic Segmentation Under Image Level Supervision (127 citations)
- Weakly Supervised Localization Using Deep Feature Maps (74 citations)
- End-to-End Localization and Ranking for Relative Attributes (68 citations)
- Weakly Supervised Object Localization Using Size Estimates (68 citations)
- Image Co-localization by Mimicking a Good Detector’s Confidence Score Distribution (50 citations)
and 1 more in the interactive map.
Tracking · 9 papers
- A Benchmark and Simulator for UAV Tracking (1,965 citations)
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking (1,857 citations)
- Learning to Track at 100 FPS with Deep Regression Networks (1,223 citations)
- Improving Multi-frame Data Association with Sparse Representations for Robust Near-online Multi-object Tracking (94 citations)
- Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning (52 citations)
- CDT: Cooperative Detection and Tracking for Tracing Multiple Objects in Video Sequences (46 citations)
- Distractor-Supported Single Target Tracking in Extremely Cluttered Scenes (34 citations)
- Tracking Completion (14 citations)
- A Generalized Successive Shortest Paths Solver for Tracking Dividing Targets (12 citations)
