TPAMI 2024 papers on Detection and segmentation
73 of the 666 papers published in TPAMI 2024 (11.0%) are on Detection and segmentation, compared with 11.6% at TPAMI 2023. They fall into 5 topics.
See TPAMI 2024 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 · 30 papers
- Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation (485 citations)
- Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition (291 citations)
- Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection (289 citations)
- CamoFormer: Masked Separable Attention for Camouflaged Object Detection (252 citations)
- Cross-Image Pixel Contrasting for Semantic Segmentation (134 citations)
- Prototype-Based Semantic Segmentation (92 citations)
- Learning to Holistically Detect Bridges From Large-Size VHR Remote Sensing Imagery (63 citations)
- Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos (55 citations)
- Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network With Token Migration (38 citations)
- HDF-Net: Capturing Homogeny Difference Features to Localize the Tampered Image (38 citations)
- On Boundary Discontinuity in Angle Regression Based Arbitrary Oriented Object Detection (35 citations)
- Gradient-Based Instance-Specific Visual Explanations for Object Specification and Object Discrimination (34 citations)
and 18 more in the interactive map.
Open-set and few-shot detection · 25 papers
- Medical Image Segmentation Review: The Success of U-Net (1,333 citations)
- Towards Open Vocabulary Learning: A Survey (221 citations)
- ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection (148 citations)
- A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future (115 citations)
- PhenoBench: A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain (92 citations)
- Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation (59 citations)
- A Dempster-Shafer Approach to Trustworthy AI With Application to Fetal Brain MRI Segmentation (56 citations)
- Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy (50 citations)
- Robust Domain Adaptive Object Detection With Unified Multi-Granularity Alignment (47 citations)
- A Comprehensive Review of Image Line Segment Detection and Description: Taxonomies, Comparisons, and Challenges (45 citations)
- Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding (42 citations)
- Prompt-and-Transfer: Dynamic Class-Aware Enhancement for Few-Shot Segmentation (38 citations)
and 13 more in the interactive map.
3D detection and driving · 8 papers
- BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers (387 citations)
- Fully Sparse Fusion for 3D Object Detection (63 citations)
- FSD V2: Improving Fully Sparse 3D Object Detection With Virtual Voxels (62 citations)
- Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning (37 citations)
- GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection (21 citations)
- Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection (16 citations)
- Weakly Supervised Monocular 3D Object Detection by Spatial-Temporal View Consistency (9 citations)
- Monocular BEV Perception of Road Scenes via Front-to-Top View Projection (8 citations)
Weakly supervised detection and segmentation · 8 papers
- MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation (95 citations)
- Box2Mask: Box-Supervised Instance Segmentation via Level-Set Evolution (79 citations)
- Rethinking Self-Supervised Semantic Segmentation: Achieving End-to-End Segmentation (18 citations)
- CC4S: Encouraging Certainty and Consistency in Scribble-Supervised Semantic Segmentation (12 citations)
- Competing for Pixels: A Self-Play Algorithm for Weakly-Supervised Semantic Segmentation (7 citations)
- Pixel is All You Need: Adversarial Spatio-Temporal Ensemble Active Learning for Salient Object Detection (7 citations)
- Boosting Weakly Supervised Object Localization and Segmentation With Domain Adaption (4 citations)
- Regularized Loss With Hyperparameter Estimation for Weakly Supervised Single Class Segmentation (2 citations)
