TPAMI 2016 papers on Detection and segmentation
70 of the 377 papers published in TPAMI 2016 (18.6%) are on Detection and segmentation. They fall into 5 topics.
See TPAMI 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 · 32 papers
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (74,198 citations)
- Fully Convolutional Networks for Semantic Segmentation (39,639 citations)
- An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition (3,346 citations)
- Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (3,034 citations)
- Accelerating Very Deep Convolutional Networks for Classification and Detection (874 citations)
- What Makes for Effective Detection Proposals? (762 citations)
- Hierarchical Image Saliency Detection on Extended CSSD (596 citations)
- Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (506 citations)
- Saliency Detection on Light Field (504 citations)
- Object Detection Networks on Convolutional Feature Maps (470 citations)
- Salient Object Detection via Structured Matrix Decomposition (382 citations)
- A Fast and Accurate Unconstrained Face Detector (297 citations)
and 20 more in the interactive map.
Open-set and few-shot detection · 14 papers
- Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (618 citations)
- Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (594 citations)
- Supervised Evaluation of Image Segmentation and Object Proposal Techniques (141 citations)
- Analysing Domain Shift Factors between Videos and Images for Object Detection (61 citations)
- Convexity Shape Prior for Binary Segmentation (58 citations)
- Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels (58 citations)
- A Deterministic Analysis for LRR (56 citations)
- Joint Color-Spatial-Directional Clustering and Region Merging (JCSD-RM) for Unsupervised RGB-D Image Segmentation (40 citations)
- Evaluation of Segmentation Quality via Adaptive Composition of Reference Segmentations (25 citations)
- Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding (23 citations)
- Data-Driven Detection of Prominent Objects (16 citations)
- Mixture of Switching Linear Dynamics to Discover Behavior Patterns in Object Tracks (15 citations)
and 2 more in the interactive map.
Tracking · 13 papers
- Discriminative Scale Space Tracking (1,323 citations)
- Struck: Structured Output Tracking with Kernels (999 citations)
- A Novel Performance Evaluation Methodology for Single-Target Trackers (632 citations)
- NUS-PRO: A New Visual Tracking Challenge (176 citations)
- Tracking Interacting Objects Using Intertwined Flows (120 citations)
- Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation (83 citations)
- Online Object Tracking, Learning and Parsing with And-Or Graphs (67 citations)
- Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking (60 citations)
- Network Consistent Data Association (36 citations)
- Interacting Multiview Tracker (29 citations)
- Online Metric-Weighted Linear Representations for Robust Visual Tracking (22 citations)
- Multi-Timescale Collaborative Tracking (10 citations)
and 1 more in the interactive map.
Weakly supervised detection and segmentation · 6 papers
- STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation (586 citations)
- Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning (424 citations)
- Learning from Weak and Noisy Labels for Semantic Segmentation (115 citations)
- Weakly Supervised Large Scale Object Localization with Multiple Instance Learning and Bag Splitting (78 citations)
- Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes (49 citations)
- Learning to Segment Human by Watching YouTube (22 citations)
3D detection and driving · 5 papers
- Detecting Flying Objects Using a Single Moving Camera (279 citations)
- Learning Category-Specific Deformable 3D Models for Object Reconstruction (66 citations)
- A Global Hypothesis Verification Framework for 3D Object Recognition in Clutter (49 citations)
- Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation (49 citations)
- Lifting Object Detection Datasets into 3D (17 citations)
