ECCV 2026 accepted papers on Detection and segmentation
167 of the 2,834 papers accepted at ECCV 2026 (5.9%) are on Detection and segmentation, compared with 10.6% at ECCV 2024. They fall into 5 topics.
See ECCV 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
CNN features · 60 papers
- Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention (5 citations)
- PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection (5 citations)
- Adaptive Spectrum-Aware Feature Disentangled Network for Small Object Detection (2 citations)
- RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation (2 citations)
- RiO-DETR: DETR for Real-time Oriented Object Detection (2 citations)
- Beyond Aesthetics: Quantifying Information Loss in Turbid Scenes (1 citation)
- Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs (1 citation)
- Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen (1 citation)
- FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small-Object Detection (1 citation)
- HEM: a margin-based loss for visual categorisation tasks (1 citation)
- IoUCert: Robustness Verification for Anchor-based Object Detectors (1 citation)
- Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection (1 citation)
and 48 more in the interactive map.
Open-set and few-shot detection · 59 papers
- Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation (3 citations)
- Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation (2 citations)
- DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection (2 citations)
- Estimating Individual Tree Height and Species from UAV Imagery (2 citations)
- Learning Accurate Segmentation Purely from Self-Supervision (2 citations)
- MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images (2 citations)
- Beyond Common Sense: Grounding Logical Anomaly Detection in Inspection Criteria (1 citation)
- CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation (1 citation)
- Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization (1 citation)
- Environmental Change Detection for Real-World Change Analysis (1 citation)
- From Masks to Pixels and Meaning: A New Taxonomy, Benchmark and Metrics for VLM Image Tampering (1 citation)
- MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment (1 citation)
and 47 more in the interactive map.
3D detection and driving · 27 papers
- M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection (21 citations)
- AffoGato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale (8 citations)
- Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D (8 citations)
- C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillation (1 citation)
- DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection (1 citation)
- LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection (1 citation)
- Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs (1 citation)
- RAF: Reliability-Aware Fusion of Camera, LiDAR, and 4D RADAR for Robust 3D Object Detection in Adverse Weather (1 citation)
- Recurrent Cross-View Object Geo-Localization (1 citation)
- SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations (1 citation)
- Agent-OBJ: Prompt-Driven 3D Adversaries for Multi-Modal Perception
- BEVOpen3D: Towards Open-World 3D Object Detection in Bird's-Eye-View
and 15 more in the interactive map.
Tracking · 14 papers
- ODONet: Online Dynamic Offset Network for Visual Object Tracking (1 citation)
- RT-RMOT: A Dataset and Framework for RGB-Thermal Referring Multi-Object Tracking (1 citation)
- SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking (1 citation)
- FeatTracker: Short- and Long-Range Temporal Feature Consistency for Robust Underwater Object Tracking
- HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking
- Mode-Conditioned Residual Calibration for Multi-Object Tracking
- ModTrack: Sensor-Agnostic Multi-View Tracking via Identity-Informed PHD Filtering with Covariance Propagation
- PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking
- Rethinking Temporal Modeling in Visual Object Tracking via Decoupled Auxiliary Supervision
- SOVTrack: Open-Vocabulary Multi-Object Tracking with Self-Supervised Pseudo Labeling and Feature Distillation
- TR-MoE: Temporal Reliability-Aware Mixture-of-Experts for Robust Tracking
- FusionTrack: Collaborative Multi-Object Tracking with Arbitrary Multi-UAVs
and 2 more in the interactive map.
Weakly supervised detection and segmentation · 7 papers
- Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels
- Cross-token Guidance Transformer for Weakly Supervised Object Localization
- Harnessing SSL for Segmentation in 3D Microscopy with Noisy Labels and Hard Patches
- ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation
- OBBSeg: Irregular Lesion Segmentation under Oriented Bounding Box Annotations
- When Specialists Meet Generalists: Segmenter-Coordinated Asymmetric Learning for Label-Deficient Concealed Object Segmentation
- Calibrate Before Adapt: Training-Free Pseudo-Label Calibration for Semi-Supervised Cross-Domain Few-Shot Detection
