AAAI 2025 accepted papers on Detection and segmentation

181 of the 3,486 papers accepted at AAAI 2025 (5.2%) are on Detection and segmentation, compared with 5.3% at AAAI 2024. They fall into 5 topics.

See AAAI 2025 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 · 77 papers

C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection (43 citations)
Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community (27 citations)
Fields of The World: A Machine Learning Benchmark Dataset for Global Agricultural Field Boundary Segmentation (16 citations)
SAFIRE: Segment Any Forged Image Region (15 citations)
Object-level Geometric Structure Preserving for Natural Image Stitching (14 citations)
OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision (14 citations)
FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring (13 citations)
PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection (13 citations)
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection (11 citations)
Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation (11 citations)
Self-Prompting Analogical Reasoning for UAV Object Detection (11 citations)
3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly Detection (10 citations)

and 65 more in the interactive map.

CNN features · 59 papers

Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection (199 citations)
Mamba YOLO: A Simple Baseline for Object Detection with State Space Model (169 citations)
FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection (157 citations)
HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection (108 citations)
ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement (78 citations)
RemDet: Rethinking Efficient Model Design for UAV Object Detection (44 citations)
FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection (43 citations)
Mesoscopic Insights: Orchestrating Multi-Scale & Hybrid Architecture for Image Manipulation Localization (32 citations)
Ultra-High Resolution Segmentation via Boundary-Enhanced Patch-Merging Transformer (21 citations)
SalM²: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention (19 citations)
IRMamba: Pixel Difference Mamba with Layer Restoration for Infrared Small Target Detection (17 citations)
S³-Mamba: Small-Size-Sensitive Mamba for Lesion Segmentation (15 citations)

and 47 more in the interactive map.

3D detection and driving · 21 papers

Language Prompt for Autonomous Driving (62 citations)
L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection (27 citations)
HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection (24 citations)
GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection (20 citations)
UniDet3D: Multi-dataset Indoor 3D Object Detection (19 citations)
RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detection (15 citations)
SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection (15 citations)
Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection (12 citations)
M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving (9 citations)
PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation (8 citations)
DSRC: Learning Density-Insensitive and Semantic-Aware Collaborative Representation Against Corruptions (7 citations)
MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert (5 citations)

and 9 more in the interactive map.

Tracking · 14 papers

SUTrack: Towards Simple and Unified Single Object Tracking (50 citations)
Exploring Enhanced Contextual Information for Video-Level Object Tracking (39 citations)
Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking (29 citations)
MambaLCT: Boosting Tracking via Long-term Context State Space Model (25 citations)
Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking (25 citations)
Less Is More: Token Context-Aware Learning for Object Tracking (22 citations)
MM-Tracker: Motion Mamba for UAV-platform Multiple Object Tracking (15 citations)
Temporal Coherent Object Flow for Multi-Object Tracking (11 citations)
Patch-level Sounding Object Tracking for Audio-Visual Question Answering (10 citations)
TGFormer: Transformer with Track Query Group for Multi-Object Tracking (6 citations)
Cross-View Referring Multi-Object Tracking (5 citations)
Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (5 citations)

and 2 more in the interactive map.