DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video

Abstract

The optimization capabilities of Kolmogorov–Arnold Networks (KANs) remain largely unexplored, which has limited their practical use in video anomaly recognition compared to conventional 3D-CNNs. To address this gap, we introduce a novel hybrid optimization framework that combines a Minimax Ant System (MMAS) for hyperparameter selection with a modified DARTS strategy for adaptive tuning of the 3D KAN architecture. Unlike existing approaches, our method simultaneously optimizes both learning dynamics and architectural configurations, enabling KANs to better exploit their expressive power in spatiotemporal feature extraction. Applied to a three-class video dataset, the proposed approach improved model accuracy to 87%, surpassing the performance of a standard 3D-CNN by 6%.

Related publications

• Bidirectional Kazakh Sign Language prosody-aware translation using computer vision and speech recognition techniquesFrontiers in Artificial Intelligence · 2026 · Same author: Maria Aouani
• Enhancing Kazakh Sign Language Recognition with BiLSTM Using YOLO Keypoints and Optical FlowApplied Sciences · 2025 · Citations: 15 · Same author: Maria Aouani
• Scratch-Trained CRNNs vs. Pretrained Vision Transformers: A Controlled Benchmark of Augmentation and Model Scale in Low-Resource Chagatai HTRInformation · 2026 · Shared topic: Advanced Neural Network Applications
• From Algorithms to Bitstreams: A Survey of FPGA-Based Acceleration for Transformer InferencePreprints.org · 2026 · Shared topic: Advanced Neural Network Applications