TPAMI 2023 papers on Detection and segmentation
77 of the 664 papers published in TPAMI 2023 (11.6%) are on Detection and segmentation, compared with 13.7% at TPAMI 2022. They fall into 5 topics.
See TPAMI 2023 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 · 31 papers
- CycleMLP: A MLP-Like Architecture for Dense Visual Predictions (325 citations)
- Conformer: Local Features Coupling Global Representations for Recognition and Detection (196 citations)
- Sparse R-CNN: An End-to-End Framework for Object Detection (140 citations)
- Mutual-Assistance Learning for Object Detection (130 citations)
- CenterNet++ for Object Detection (125 citations)
- Adaptive Region-Specific Loss for Improved Medical Image Segmentation (76 citations)
- SODFormer: Streaming Object Detection With Transformer Using Events and Frames (71 citations)
- Lightweight Pixel Difference Networks for Efficient Visual Representation Learning (70 citations)
- SPTS v2: Single-Point Scene Text Spotting (70 citations)
- A Thorough Benchmark and a New Model for Light Field Saliency Detection (66 citations)
- Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection (55 citations)
- Semantic Hierarchy-Aware Segmentation (50 citations)
and 19 more in the interactive map.
Open-set and few-shot detection · 23 papers
- Towards Large-Scale Small Object Detection: Survey and Benchmarks (759 citations)
- Visible and Infrared Image Fusion Using Deep Learning (438 citations)
- Unsupervised Domain Adaptation of Object Detectors: A Survey (370 citations)
- Base and Meta: A New Perspective on Few-Shot Segmentation (188 citations)
- TokenCut: Segmenting Objects in Images and Videos With Self-Supervised Transformer and Normalized Cut (124 citations)
- FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery (107 citations)
- PFENet++: Boosting Few-Shot Semantic Segmentation With the Noise-Filtered Context-Aware Prior Mask (92 citations)
- Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning (85 citations)
- FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection (71 citations)
- SIGMA++: Improved Semantic-complete Graph Matching for Domain Adaptive Object Detection (66 citations)
- SAN: Side Adapter Network for Open-Vocabulary Semantic Segmentation (61 citations)
- Revisiting Computer-Aided Tuberculosis Diagnosis (51 citations)
and 11 more in the interactive map.
Weakly supervised detection and segmentation · 11 papers
- Fully Convolutional Change Detection Framework With Generative Adversarial Network for Unsupervised, Weakly Supervised and Regional Supervised Change Detection (234 citations)
- A Survey on Label-Efficient Deep Image Segmentation: Bridging the Gap Between Weak Supervision and Dense Prediction (158 citations)
- Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes (137 citations)
- Robust Perception and Precise Segmentation for Scribble-Supervised RGB-D Saliency Detection (57 citations)
- Background-Aware Classification Activation Map for Weakly Supervised Object Localization (37 citations)
- Saliency as Pseudo-Pixel Supervision for Weakly and Semi-Supervised Semantic Segmentation (31 citations)
- Learning an Invariant and Equivariant Network for Weakly Supervised Object Detection (25 citations)
- Positive-Negative Receptive Field Reasoning for Omni-Supervised 3D Segmentation (21 citations)
- Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting (20 citations)
- Salvage of Supervision in Weakly Supervised Object Detection and Segmentation (15 citations)
- Tobias: A Random CNN Sees Objects (4 citations)
3D detection and driving · 7 papers
- Delving Into the Devils of Bird’s-Eye-View Perception: A Review, Evaluation and Recipe (223 citations)
- 3D Object Detection From Images for Autonomous Driving: A Survey (169 citations)
- Super Sparse 3D Object Detection (49 citations)
- Hypergraph-Based Multi-Modal Representation for Open-Set 3D Object Retrieval (32 citations)
- MsSVT++: Mixed-Scale Sparse Voxel Transformer With Center Voting for 3D Object Detection (31 citations)
- Learning Dynamic Scene-Conditioned 3D Object Detectors (25 citations)
- Back to Reality: Learning Data-Efficient 3D Object Detector With Shape Guidance (2 citations)
Tracking · 5 papers
- Anti-UAV410: A Thermal Infrared Benchmark and Customized Scheme for Tracking Drones in the Wild (208 citations)
- QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking (182 citations)
- Towards Real-World Visual Tracking With Temporal Contexts (120 citations)
- Towards Trajectory Forecasting From Detection (24 citations)
- Adaptive Part Mining for Robust Visual Tracking (18 citations)
