ICCV 2017 accepted papers on Detection and segmentation
121 of the 621 papers accepted at ICCV 2017 (19.5%) are on Detection and segmentation. They fall into 5 topics.
See ICCV 2017 in the interactive map
Submitting to ICCV? Checklist →
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 · 62 papers
- Focal Loss for Dense Object Detection (31,880 citations)
- Mask R-CNN (30,402 citations)
- Deformable Convolutional Networks (7,800 citations)
- AOD-Net: All-In-One Dehazing Network (2,674 citations)
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era (2,652 citations)
- Soft-NMS -- Improving Object Detection With One Line of Code (2,438 citations)
- Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection (920 citations)
- Large-Scale Image Retrieval With Attentive Deep Local Features (879 citations)
- Flow-Guided Feature Aggregation for Video Object Detection (748 citations)
- DSOD: Learning Deeply Supervised Object Detectors From Scratch (680 citations)
- Learning Uncertain Convolutional Features for Accurate Saliency Detection (493 citations)
- VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition (485 citations)
and 50 more in the interactive map.
Open-set and few-shot detection · 29 papers
- Structure-Measure: A New Way to Evaluate Foreground Maps (2,143 citations)
- The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes (1,479 citations)
- Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection (716 citations)
- Drone-Based Object Counting by Spatially Regularized Regional Proposal Network (569 citations)
- Playing for Benchmarks (451 citations)
- No More Discrimination: Cross City Adaptation of Road Scene Segmenters (342 citations)
- Visual Relationship Detection With Internal and External Linguistic Knowledge Distillation (329 citations)
- Recurrent Multimodal Interaction for Referring Image Segmentation (288 citations)
- TorontoCity: Seeing the World With a Million Eyes (198 citations)
- Phrase Localization and Visual Relationship Detection With Comprehensive Image-Language Cues (169 citations)
- Towards Context-Aware Interaction Recognition for Visual Relationship Detection (162 citations)
- Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings (145 citations)
and 17 more in the interactive map.
Tracking · 15 papers
- Learning Background-Aware Correlation Filters for Visual Tracking (1,279 citations)
- Learning Dynamic Siamese Network for Visual Object Tracking (907 citations)
- Detect to Track and Track to Detect (596 citations)
- Tracking the Untrackable: Learning to Track Multiple Cues With Long-Term Dependencies (580 citations)
- CREST: Convolutional Residual Learning for Visual Tracking (574 citations)
- Need for Speed: A Benchmark for Higher Frame Rate Object Tracking (560 citations)
- Online Multi-Object Tracking Using CNN-Based Single Object Tracker With Spatial-Temporal Attention Mechanism (412 citations)
- Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking (332 citations)
- Learning Policies for Adaptive Tracking With Deep Feature Cascades (238 citations)
- Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection (125 citations)
- Non-Markovian Globally Consistent Multi-Object Tracking (94 citations)
- PathTrack: Fast Trajectory Annotation With Path Supervision (69 citations)
and 3 more in the interactive map.
Weakly supervised detection and segmentation · 12 papers
- Hide-And-Seek: Forcing a Network to Be Meticulous for Weakly-Supervised Object and Action Localization (737 citations)
- Extreme Clicking for Efficient Object Annotation (238 citations)
- Weakly-Supervised Learning of Visual Relations (193 citations)
- Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector (173 citations)
- Soft Proposal Networks for Weakly Supervised Object Localization (155 citations)
- Two-Phase Learning for Weakly Supervised Object Localization (142 citations)
- PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN (136 citations)
- Deep Dual Learning for Semantic Image Segmentation (95 citations)
- WeText: Scene Text Detection Under Weak Supervision (90 citations)
- Weakly Supervised Object Localization Using Things and Stuff Transfer (69 citations)
- Bringing Background Into the Foreground: Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation (42 citations)
- Weakly Supervised Manifold Learning for Dense Semantic Object Correspondence (15 citations)
