Current face video forgery detectors use wide or dual-stream backbones. We show that a single, lightweight fusion of two handcrafted cues can achieve higher accuracy with a much smaller model. Based on the Xception baseline model (21.9 million parameters), we build two detectors: LFWS, which adds a 1×1 convolution to combine a low-frequency Wavelet-Denoised Feature (WDF) with the phase-only Spatial-Phase Shallow Learning (SPSL) map, and LFWL, which merges WDF with Local Binary Patterns (LBP) in the same way. This extra module adds only 292 parameters, keeping the total at 21.9 million—smaller… Read More
Multi-Frequency Fusion for Robust Video Face Forgery Detection
Current face video forgery detectors use wide or dual-stream backbones. We show that a single, lightweight fusion of two handcrafted cues can achieve higher accuracy with a much smaller model. Based on the Xception baseline model (21.9 million parameters), we build two detectors: LFWS, which adds a 1×1 convolution to combine a low-frequency Wavelet-Denoised Feature (WDF) with the phase-only Spatial-Phase Shallow Learning (SPSL) map, and LFWL, which merges WDF with Local Binary Patterns (LBP) in the same way. This extra module adds only 292 parameters, keeping the total at 21.9 million—smaller…
Related Posts
Can LLM Embeddings Improve Time Series Forecasting? A Practical Feature Engineering Approach
Using large language models (LLMs) — or their outputs, for that matter — for all…
Everything You Need to Know About LLM Evaluation Metrics
When large language models first came out, most of us were just thinking about what…
Gemini 3 Flash: frontier intelligence built for speed
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.