IJCV 2026 papers on Detection and segmentation
57 of the 477 papers published in IJCV 2026 (11.9%) are on Detection and segmentation, compared with 16.2% at IJCV 2025. They fall into 5 topics.
See IJCV 2026 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
Open-set and few-shot detection · 28 papers
- The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detection (71 citations)
- A Survey of Multimodal Hallucination Evaluation and Detection (33 citations)
- Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark (31 citations)
- Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion (9 citations)
- Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation (9 citations)
- GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation (5 citations)
- Scaling Up Forest Vision with Synthetic Data (5 citations)
- Semantic-Centric Alignment for Zero-shot Panoptic Segmentation with Limited Data (5 citations)
- DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting (3 citations)
- Visual-Geometric Collaborative Guidance for Affordance Learning (3 citations)
- Implicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection (2 citations)
- Power Battery Detection (2 citations)
and 16 more in the interactive map.
CNN features · 17 papers
- Physical Regularization Loss: Integrating Physical Knowledge to Image Segmentation (27 citations)
- Iterative Global Mapping-Local Searching for Heterogeneous Change Detection with Unregistered Images (26 citations)
- Practical Video Object Detection via Feature Selection and Aggregation (17 citations)
- Rethinking Neuromorphic Object Detection with Hybrid Dynamic Interaction Transformers (11 citations)
- Constellation Dataset: Benchmarking High-Altitude Object Detection for an Urban Intersection (4 citations)
- Universal Facial Landmark Detection by Landmark-Clustering Relation-Reasoning Transformer (2 citations)
- A Color Information Driven Collaborative Training of Dual Task Parallel Network for Visible and Thermal Infrared Image Fusion and Saliency Object Detection (1 citation)
- A Novel Dataset and Lightweight Distillation Baseline for Highlight Transparent Object Detection (1 citation)
- Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones (1 citation)
- EMUFormer: Efficient Multi-task Uncertainties for Reliable Joint Semantic Segmentation and Monocular Depth Estimation (1 citation)
- IPDiff: Diffusion-driven ORSI Salient Object Detection with Information Reconstruction and Multi-Prior Guidance (1 citation)
- Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling (1 citation)
and 5 more in the interactive map.
Tracking · 4 papers
- Efficient Vision Transformer with Token Sparsification for Event-Based Object Tracking (8 citations)
- NOOUGAT Towards Unified Online and Offline Multi-Object Tracking (6 citations)
- An HMM-Based Framework for Identity-Aware Long-Term Multi-Object Tracking From Sparse and Uncertain Identification: Use Case on Long-Term Tracking in Livestock (3 citations)
- Distractor-Aware Memory-Based Visual Object Tracking (3 citations)
Weakly supervised detection and segmentation · 4 papers
- Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis (6 citations)
- Weakly Supervised Salient Object Detection with Text Supervision (3 citations)
- Learning Complex Scene Segmentation from Noisy Label
- Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions
3D detection and driving · 4 papers
- Learning Pseudo 3D Representation for Ego-centric 2D Multiple Object Tracking (2 citations)
- Object-Scene-Camera Decomposition and Recomposition for Data Efficient Monocular 3D Object Detection (1 citation)
- RGB-D Indiscernible Object Counting in Underwater Scenes (1 citation)
- MonoSOWA++: Universal Autolabeling Pipeline for Monocular 3D Object Detection
