ICCV 2023 accepted papers on Detection and segmentation
260 of the 2,156 papers accepted at ICCV 2023 (12.1%) are on Detection and segmentation, compared with 13.8% at ICCV 2021. They fall into 5 topics.
See ICCV 2023 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
Open-set and few-shot detection · 90 papers
- Segment Anything (16,978 citations)
- DiffusionDet: Diffusion Model for Object Detection (799 citations)
- CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection (391 citations)
- UniverSeg: Universal Medical Image Segmentation (245 citations)
- A Simple Framework for Open-Vocabulary Segmentation and Detection (186 citations)
- Towards Geospatial Foundation Models via Continual Pretraining (158 citations)
- Self-Calibrated Cross Attention Network for Few-Shot Segmentation (98 citations)
- Open-vocabulary Object Segmentation with Diffusion Models (89 citations)
- Beyond One-to-One: Rethinking the Referring Image Segmentation (87 citations)
- A Low-Shot Object Counting Network With Iterative Prototype Adaptation (82 citations)
- High Quality Entity Segmentation (79 citations)
- Exploring Predicate Visual Context in Detecting of Human-Object Interactions (77 citations)
and 78 more in the interactive map.
CNN features · 74 papers
- Large Selective Kernel Network for Remote Sensing Object Detection (1,034 citations)
- Learning to Upsample by Learning to Sample (947 citations)
- DETRs with Collaborative Hybrid Assignments Training (742 citations)
- Dynamic Snake Convolution Based on Topological Geometric Constraints for Tubular Structure Segmentation (699 citations)
- SegGPT: Towards Segmenting Everything in Context (545 citations)
- Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation (375 citations)
- Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment (341 citations)
- UCF: Uncovering Common Features for Generalizable Deepfake Detection (309 citations)
- Scale-Aware Modulation Meet Transformer (238 citations)
- Adaptive Rotated Convolution for Rotated Object Detection (228 citations)
- SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (178 citations)
- Deep Directly-Trained Spiking Neural Networks for Object Detection (177 citations)
and 62 more in the interactive map.
3D detection and driving · 46 papers
- PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images (497 citations)
- Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection (380 citations)
- MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection (271 citations)
- Cross Modal Transformer: Towards Fast and Robust 3D Object Detection (236 citations)
- SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos (181 citations)
- CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception (176 citations)
- SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection (172 citations)
- Source-free Depth for Object Pop-out (157 citations)
- Robo3D: Towards Robust and Reliable 3D Perception against Corruptions (137 citations)
- FocalFormer3D: Focusing on Hard Instance for 3D Object Detection (129 citations)
- UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation (120 citations)
- MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation (90 citations)
and 34 more in the interactive map.
Weakly supervised detection and segmentation · 31 papers
- FPR: False Positive Rectification for Weakly Supervised Semantic Segmentation (74 citations)
- Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection (54 citations)
- Referring Image Segmentation Using Text Supervision (51 citations)
- USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation (51 citations)
- Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation (46 citations)
- BoxSnake: Polygonal Instance Segmentation with Box Supervision (41 citations)
- MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation (37 citations)
- Generative Prompt Model for Weakly Supervised Object Localization (35 citations)
- Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport (34 citations)
- Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning (32 citations)
- ALWOD: Active Learning for Weakly-Supervised Object Detection (31 citations)
- SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining (26 citations)
and 19 more in the interactive map.
Tracking · 19 papers
- SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes (245 citations)
- TAPIR: Tracking Any Point with Per-Frame Initialization and Temporal Refinement (209 citations)
- MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking (193 citations)
- Robust Object Modeling for Visual Tracking (175 citations)
- 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking (67 citations)
- ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking (67 citations)
- Foreground-Background Distribution Modeling Transformer for Visual Object Tracking (61 citations)
- PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework (29 citations)
- Uncertainty-aware Unsupervised Multi-Object Tracking (29 citations)
- Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking (28 citations)
- Tracking by Natural Language Specification with Long Short-term Context Decoupling (27 citations)
- End-to-end 3D Tracking with Decoupled Queries (23 citations)
and 7 more in the interactive map.
