Call for Papers
DLACV 2026 will provide fertile ground for engineers and scientists from around the world to escalate collaboratively the research frontiers within the field of deep learning, algorithms, and computer vision and related areas. Original and unpublished work relevant to, but are not limited to, the following topics are hereby solicited.
Track 1: Machine Learning
- New Convolutional Neural Networks, Recurrent Neural Networks, and Generative Adversarial Networks
- The Design and Optimization of Model Architecture
- Self-supervised Learning, Semi-Supervised Learning, Unsupervised Learning, Algorithm Innovation and Theoretical Analysis.
- Algorithm Improvement of Deep Reinforcement Learning
- Application in Complex Dynamic Environments.
- Neural Symbolic Learning, Graph Neural Networks
- Exploration of Deep Learning Methods for Cross-Domain Integration
Track 2: Core Technologies of Computer Vision
- New Methods for Target Detection and Recognition
- Small Target Detection and Multi-Target Tracking
- Image Semantic Segmentation and Instance Segmentation Techniques
- Optimization in Complex Scenes and High-Resolution Images
- 3D Vision, 3D Reconstruction, Point Cloud Processing, 3d Object Detection and Pose Estimation
- Video Analysis, Covering Action Recognition, Event Detection, Video Understanding, And Video Generation
Track 3: Algorithm Optimization and Efficiency Improvement
- Deep learning algorithm
- Model compression, pruning, and quantization
- Hardware-accelerated optimization of deep learning algorithms
- GPU、TPU
- Computer vision algorithm design
- Computational complexity and resource consumption
- Distributed computing, parallel computing
Track 4: Multimodal and cross-domain integration
- Deep Learning Methods for Multimodal Data Fusion
- Images, Text, Audio
- The combination of Computer Vision and Natural Language Processing
- Visual Question Answering and Image Description Generation
- Cross Algorithm
- Medical Image Analysis, Astronomical Image Processing
Track 5: Interpretability and Security
- Research on the Interpretability of Deep Learning Models
- Visualization Technology, Mechanism Analysis
- Adversarial Attacks and Defenses in Computer Vision Systems
- Enhance the Model's Robustness Against Malicious Attacks.
- Privacy Protection, Differential Privacy, Federated Learning
Track 6: Expansion of Practical Application Scenarios
- Computer Vision Applications in the Field of Intelligent Transportation
- Autonomous Driving, Traffic Flow Monitoring and Analysis
- Applications Related to the Medical and Health Field
- Disease Diagnosis, Medical Image-Assisted Analysis, Surgical Navigation
- Industrial Vision Inspection
- Product Quality Inspection, Defect Identification, And Monitoring of Automated Production Processes
- Face Recognition, Behavior Analysis and Intelligent Early Warning