IJCV 2025 papers on Detection and segmentation
43 of the 266 papers published in IJCV 2025 (16.2%) are on Detection and segmentation, compared with 15.7% at IJCV 2024. They fall into 5 topics.
See IJCV 2025 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 · 17 papers
- SeaFormer++: Squeeze-Enhanced Axial Transformer for Mobile Visual Recognition (197 citations)
- Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection (47 citations)
- On Efficient Variants of Segment Anything Model: A Survey (41 citations)
- HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning (36 citations)
- SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting (29 citations)
- Fully Decoupled End-to-End Person Search: An Approach without Conflicting Objectives (19 citations)
- Deep Hierarchical Learning for 3D Semantic Segmentation (17 citations)
- NU-AIR: A Neuromorphic Urban Aerial Dataset for Detection and Localization of Pedestrians and Vehicles (10 citations)
- LR-ASD: Lightweight and Robust Network for Active Speaker Detection (9 citations)
- OCCO: LVM-Guided Infrared and Visible Image Fusion Framework Based on Object-Aware and Contextual Contrastive Learning (9 citations)
- Not All Pixels are Equal: Learning Pixel Hardness for Semantic Segmentation (8 citations)
- ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation (8 citations)
and 5 more in the interactive map.
Open-set and few-shot detection · 15 papers
- GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection (51 citations)
- BaboonLand Dataset: Tracking Primates in the Wild and Automating Behaviour Recognition from Drone Videos (35 citations)
- FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms (29 citations)
- Robust Sequential DeepFake Detection (27 citations)
- Bamboo: Building Mega-Scale Vision Dataset Continually with Human–Machine Synergy (22 citations)
- Diagnosing Human-Object Interaction Detectors (18 citations)
- Rethinking Open-Set Object Detection: Issues, A New Formulation, and Taxonomy (9 citations)
- Camouflaged Object Detection with Adaptive Partition and Background Retrieval (6 citations)
- Robust Object Detection with Domain-Invariant Training and Continual Test-Time Adaptation (5 citations)
- A Mutual Supervision Framework for Referring Expression Segmentation and Generation (4 citations)
- Improving Object Detection Models via LLM-Based Training Data Synthesis (1 citation)
- Learning Compositionality from Multifaceted Synthetic Data for Language-based Object Detection (1 citation)
and 3 more in the interactive map.
Weakly supervised detection and segmentation · 6 papers
- PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection (18 citations)
- Weakly Supervised Salient Object Detection With Oversize Bounding Box (8 citations)
- CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation (4 citations)
- P2Object: Single Point Supervised Object Detection and Instance Segmentation (4 citations)
- Discriminatively Matched Part Tokens for Pointly Supervised Instance Segmentation (1 citation)
- DM-PCL: Text-Driven Dual-Modal Prototype Consistency Learning for Weakly-Supervised Few-Shot Part Segmentation (1 citation)
3D detection and driving · 4 papers
- OA-DET3D: Embedding Object Awareness As A General Plug-in for Multi-Camera 3D Object Detection (14 citations)
- LiDAR-guided Geometric Pretraining for Vision-Centric 3D Object Detection (4 citations)
- Fusion4DAL: Offline Multi-modal 3D Object Detection for 4D Auto-labeling (3 citations)
- A Fast and Lightweight 3D Keypoint Detector (1 citation)
