Latest Research in Cross-Modal Perception Architectures
434 research papers · 0.0 average citations · 2026 median publication year
Top Research Topics in Cross-Modal Perception Architectures
- Computer Vision and Pattern Recognition — 147 papers
- Advanced Neural Network Applications — 85 papers
- Image Enhancement Techniques — 20 papers
- Video Surveillance and Tracking Methods — 14 papers
- Robotics — 11 papers
- Infrared Target Detection Methodologies — 9 papers
- Synthetic Aperture Radar (SAR) Applications and Techniques — 8 papers
- Autonomous Vehicle Technology and Safety — 7 papers
- Image and Video Processing — 6 papers
- Computation and Language — 6 papers
Highest-Cited Papers
- A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar
- When Fish Look Alike: Tracking Identities with Dual-branch Elasticity
- SpectraDINO: Modality-Conditioned Adaptation of RGB Vision Foundation Models Across Infrared Bands
- Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention
- Object Detection for Autonomous Driving in Chinese Rural Scenes: An Experimental Study on Real-Synthetic Data Mixing and Model Evaluation
- Hyper-FEOD: Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoE
- Dense Soft Weighting for Radar Ego-Velocity Estimation
- A Unified Benchmark and Modality-Adaptive Network for Day-and-Night Drone-View Geo-Localization
- ReLATE: Reliability-Guided Evidence Fusion for Robust UAV--Satellite cross-view Geo-Localization
- A Geographic Consistency-Constrained Cross-Modal Super-Resolution Matching Method for UAV Geo-Localization
- Cross-Modal Offshore Platform Detection Method via Domain-Invariant Feature Learning
- Revisiting Stereo Triangulation in UAV Distance Estimation
- Embedded Oriented Object Detection on MaixCAM Pro for Waste-Sorting Perception
- DDG-Net: a dynamic detail-guided network for aerial small object detection
- DO-CGI: deep-optimized illumination patterns for computational ghost imaging at low sampling ratios
- Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning
- CD-RMOT-Bench: Benchmarking the Cross-Domain Referring Multi-Object Tracking
- HeteroPROPMT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework
- RDVSv2: A Large-scale Benchmark for RGB-D Video Salient Object Detection
- End-to-End 3-D Spatiotemporal Perception with Multimodal Fusion and V2X Collaboration
Sub-Regions
- Computer Vision and Pattern Recognition — 164 papers
- Advanced Neural Network Applications — 151 papers
- Image Enhancement Techniques — 93 papers
- Handwritten Text Recognition Techniques — 40 papers
- Computation and Language — 23 papers