CVPR 2022 accepted papers on Detection and segmentation
337 of the 2,077 papers accepted at CVPR 2022 (16.2%) are on Detection and segmentation, compared with 17.4% at CVPR 2021. They fall into 5 topics.
See CVPR 2022 in the interactive map
Submitting to CVPR? 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 · 120 papers
- A ConvNet for the 2020s (8,138 citations)
- Masked-Attention Mask Transformer for Universal Image Segmentation (3,259 citations)
- Swin Transformer V2: Scaling Up Capacity and Resolution (2,405 citations)
- Target-Aware Dual Adversarial Learning and a Multi-Scenario Multi-Modality Benchmark To Fuse Infrared and Visible for Object Detection (1,179 citations)
- DN-DETR: Accelerate DETR Training by Introducing Query DeNoising (1,031 citations)
- MViTv2: Improved Multiscale Vision Transformers for Classification and Detection (792 citations)
- ISNet: Shape Matters for Infrared Small Target Detection (715 citations)
- QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection (572 citations)
- Oriented RepPoints for Aerial Object Detection (545 citations)
- End-to-End Reconstruction-Classification Learning for Face Forgery Detection (394 citations)
- Rethinking Semantic Segmentation: A Prototype View (379 citations)
- MPViT: Multi-Path Vision Transformer for Dense Prediction (357 citations)
and 108 more in the interactive map.
Open-set and few-shot detection · 104 papers
- Towards Total Recall in Industrial Anomaly Detection (1,653 citations)
- Grounded Language-Image Pre-Training (1,055 citations)
- DenseCLIP: Language-Guided Dense Prediction With Context-Aware Prompting (615 citations)
- RegionCLIP: Region-Based Language-Image Pretraining (572 citations)
- Image Segmentation Using Text and Image Prompts (527 citations)
- Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection (480 citations)
- GroupViT: Semantic Segmentation Emerges From Text Supervision (443 citations)
- Learning To Prompt for Open-Vocabulary Object Detection With Vision-Language Model (351 citations)
- Detecting Camouflaged Object in Frequency Domain (316 citations)
- ObjectFormer for Image Manipulation Detection and Localization (225 citations)
- OW-DETR: Open-World Detection Transformer (223 citations)
- Deep Hierarchical Semantic Segmentation (184 citations)
and 92 more in the interactive map.
Weakly supervised detection and segmentation · 55 papers
- Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation (297 citations)
- Learning Affinity From Attention: End-to-End Weakly-Supervised Semantic Segmentation With Transformers (279 citations)
- Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation (235 citations)
- Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation (205 citations)
- Self-Supervised Image-Specific Prototype Exploration for Weakly Supervised Semantic Segmentation (203 citations)
- CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation (192 citations)
- Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast (190 citations)
- L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation (189 citations)
- Self-Supervised Transformers for Unsupervised Object Discovery Using Normalized Cut (151 citations)
- Pointly-Supervised Instance Segmentation (147 citations)
- Unbiased Teacher v2: Semi-Supervised Object Detection for Anchor-Free and Anchor-Based Detectors (142 citations)
- DETReg: Unsupervised Pretraining With Region Priors for Object Detection (136 citations)
and 43 more in the interactive map.
3D detection and driving · 37 papers
- TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers (939 citations)
- DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection (560 citations)
- DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection (559 citations)
- Focal Sparse Convolutional Networks for 3D Object Detection (320 citations)
- MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer (226 citations)
- Voxel Field Fusion for 3D Object Detection (122 citations)
- VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention (99 citations)
- Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving (94 citations)
- Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection (84 citations)
- MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection (71 citations)
- Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving (64 citations)
- Ithaca365: Dataset and Driving Perception Under Repeated and Challenging Weather Conditions (58 citations)
and 25 more in the interactive map.
Tracking · 21 papers
- TrackFormer: Multi-Object Tracking With Transformers (1,023 citations)
- DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion (363 citations)
- TCTrack: Temporal Contexts for Aerial Tracking (269 citations)
- Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline (269 citations)
- MeMOT: Multi-Object Tracking With Memory (238 citations)
- Transformer Tracking With Cyclic Shifting Window Attention (237 citations)
- Global Tracking Transformers (205 citations)
- Correlation-Aware Deep Tracking (199 citations)
- Spiking Transformers for Event-Based Single Object Tracking (184 citations)
- Multi-Object Tracking Meets Moving UAV (131 citations)
- Unified Transformer Tracker for Object Tracking (128 citations)
- Unsupervised Learning of Accurate Siamese Tracking (74 citations)
and 9 more in the interactive map.
