AAAI 2026 accepted papers on Detection and segmentation
168 of the 4,417 papers accepted at AAAI 2026 (3.8%) are on Detection and segmentation, compared with 5.2% at AAAI 2025. They fall into 5 topics.
See AAAI 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 · 66 papers
- Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing (27 citations)
- DynamicEarth: How Far Are We from Open-Vocabulary Change Detection? (5 citations)
- Effective Robotic Cloth Grasping Through Suppressing False Discoveries (5 citations)
- RS2-SAM2: Customized SAM2 for Referring Remote Sensing Image Segmentation (4 citations)
- Deeply Seeking Boundary for Lunar Regolith Segmentation (3 citations)
- Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter (3 citations)
- QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection (3 citations)
- X-SAM: From Segment Anything to Any Segmentation (3 citations)
- Cross-domain Joint Learning with Prototype-guided Mixture-of-Experts for Infrared Moving Small Target Detection (2 citations)
- EIDSeg: A Pixel-Level Semantic Segmentation Dataset for Post-Earthquake Damage Assessment from Social Media Images (2 citations)
- Generalizable Slum Detection from Satellite Imagery with Mixture-of-Experts (2 citations)
- MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation (2 citations)
and 54 more in the interactive map.
CNN features · 48 papers
- Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection (22 citations)
- LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attention (21 citations)
- WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation (5 citations)
- Fine-Grained DINO Tuning with Dual Supervision for Face Forgery Detection (4 citations)
- Seeing Beyond Illusion: Generalized and Efficient Mirror Detection (4 citations)
- Beyond Quadratic: Linear-Time Change Detection with RWKV (3 citations)
- MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images (3 citations)
- PEOD: A Pixel-Aligned Event-RGB Benchmark for Object Detection Under Challenging Conditions (3 citations)
- Revisiting Downsampling in Semantic Segmentation: Fighting Aliasing with Dynamic Gaussian and Gabor Frequency Filters (3 citations)
- Adaptive Morph-Patch Transformer for Aortic Vessel Segmentation (2 citations)
- Blur-Robust Detection via Feature Restoration: An End-to-End Framework for Prior-Guided Infrared UAV Target Detection (2 citations)
- Breaking Alignment Barriers: TPS-Driven Semantic Correlation Learning for Alignment-Free RGB-T Salient Object Detection (2 citations)
and 36 more in the interactive map.
3D detection and driving · 28 papers
- SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection (10 citations)
- BEVDilation: LiDAR-Centric Multi-Modal Fusion for 3D Object Detection (4 citations)
- MonoCLUE: Object-Aware Clustering Enhances Monocular 3D Object Detection (4 citations)
- Griffin: Aerial-Ground Cooperative Detection and Tracking Dataset and Benchmark (3 citations)
- WinMamba: Multi-Scale Shifted Windows in State Space Model for 3D Object Detection (3 citations)
- OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding (2 citations)
- CLIPDet3D: Vision-Language Collaborative Distillation for 3D Object Detection (1 citation)
- Exploring Surround-View Fisheye Camera 3D Object Detection (1 citation)
- Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion (1 citation)
- Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunable (1 citation)
- Refine3D: Scene-Adaptive Reference Point Refinement for Sparse 3D Object Detection (1 citation)
- Adaptive LiDAR Scanning: Harnessing Temporal Cues for Efficient 3D Object Detection via Multi-Modal Fusion
and 16 more in the interactive map.
Weakly supervised detection and segmentation · 15 papers
- SeViL: Semi-supervised Vision-Language Learning with Text Prompt Guiding for Moving Infrared Small Target Detection (3 citations)
- Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization (2 citations)
- CaPro: Curvilinear-aware Prompt Learning with Single Unlabeled Image for Cost-effective Curvilinear Structure Segmentation (2 citations)
- From Passive Perception to Active Memory: A Weakly Supervised Image Manipulation Localization Framework Driven by Coarse-Grained Annotations (2 citations)
- RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels (2 citations)
- GeoCoBox: Box-supervised 3D Tumor Segmentation via Geometric Co-embedding (1 citation)
- S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything Without Supervision (1 citation)
- SOAR: Semi-Supervised Open-Vocabulary Aerial Object Detection via Dual-Aware Enhanced Prior Denoising (1 citation)
- SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation (1 citation)
- S²Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection (1 citation)
- A²LC: Active and Automated Label Correction for Semantic Segmentation
- DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation
and 3 more in the interactive map.
Tracking · 11 papers
- SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation (6 citations)
- When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking (5 citations)
- Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos (3 citations)
- AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios (2 citations)
- Exploring Reliable Spatiotemporal Dependencies for Efficient Visual Tracking (2 citations)
- GLoMOT: Efficient Online GNN-based Low-Frame-Rate Multi-Object Tracker (1 citation)
- Motion-Aware Object Tracking via Motion and Geometry-Aware Cues (1 citation)
- PlugTrack: Multi-Perceptive Motion Analysis for Adaptive Fusion in Multi-Object Tracking (1 citation)
- Delving into Dynamic Scene Cue-Consistency for Robust 3D Multi-Object Tracking
- HTTrack: Learning to Perceive Targets via Historical Trajectories in Satellite Video Tracking
- MUTrack: A Memory-Aware Unified Representation Framework for Visual Tracking