CVPR 2026 accepted papers on Detection and segmentation
247 of the 4,042 papers accepted at CVPR 2026 (6.1%) are on Detection and segmentation, compared with 6.9% at CVPR 2025. They fall into 5 topics.
See CVPR 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Open-set and few-shot detection · 101 papers
- CountGD++: Generalized Prompting for Open-World Counting (1 citation)
- A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps
- A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World
- A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection
- AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
- All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark
- Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object Detection in Remote Sensing Images
- Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance
- Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization
- BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection
- CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild
- ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Data
and 89 more in the interactive map.
CNN features · 74 papers
- YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection (4 citations)
- Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction (1 citation)
- MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention (1 citation)
- Computer Vision with a Superpixelation Camera
- CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird's-Eye-View Semantic Segmentation
- D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation
- DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization
- Does YOLO Really Need to See Every Training Image in Every Epoch?
- Efficiency Follows Global-Local Decoupling
- Explaining Object Detectors via Collective Contribution of Pixels
- F2Net: A Frequency-Fused Network for Ultra-High Resolution Remote Sensing Segmentation
- Fourier Angle Alignment for Oriented Object Detection in Remote Sensing
and 62 more in the interactive map.
3D detection and driving · 39 papers
- CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection
- DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video
- DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidance
- DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR
- EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
- Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments
- HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation
- Learnability-Driven Submodular Optimization for Active Roadside 3D Detection
- Mind the Hitch: Dynamic Calibration and Articulated Perception for Autonomous Trucks
- MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label
- MTA: Multimodal Task Alignment for BEV Perception and Captioning
- Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift
and 27 more in the interactive map.
Tracking · 17 papers
- Hypergraph-State Collaborative Reasoning for Multi-Object Tracking (1 citation)
- An Efficient Token Compression Framework for Visual Object Tracking
- AnthroTAP: Learning Point Tracking with Real-World Motion
- Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions
- Drift-Resilient Temporal Priors for Visual Tracking
- From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
- Instance-level Visual Active Tracking with Occlusion-Aware Planning
- Occlusion-Aware SORT: Observing Occlusion for Robust Multi-Object Tracking
- Spatio-Temporal Conditional Denoising Transformer for Modality-Missing RGBT Tracking
- SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking
- Fast Spatial Tracking with Visual Geometry Transformer
- ProgTrack: A Multi-Object Tracking Algorithm with Progressive Matching Strategy
and 5 more in the interactive map.
Weakly supervised detection and segmentation · 16 papers
- ReSAM: Refine, Requery, and Reinforce: Self-Prompting Point-Supervised Segmentation for Remote Sensing Images (1 citation)
- BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation
- EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection
- INSID3: Training-Free In-Context Segmentation with DINOv3
- Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
- TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement
- Beyond Weak Supervision: MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged Object Detection
- Bridging RGB and Hematoxylin Components: An Interleaved Guidance and Fusion Framework for Point Supervised Nuclei Segmentation
- Frequency-Aware Affinity for Weakly Supervised Semantic Segmentation
- Leveraging Class Distributions in CLIP for Weakly Supervised Semantic Segmentation
- MatchMask: Mask-Centric Generative Data Augmentation for Label-Scarce Semantic Segmentation
- Mind the Gap: Transferring Labels to Align Object Detection Datasets
and 4 more in the interactive map.