· ai
YOLOv1 Loss Function Walkthrough: Regression for All
An explanation of how YOLOv1 measures the correctness of its object detection and classification predictions The post YOLOv1 Loss Function Walkthrough: Regressi...
-
- · ai
[Paper] Adaptive Hybrid Optimizer based Framework for Lumpy Skin Disease Identification
Lumpy Skin Disease (LSD) is a contagious viral infection that significantly deteriorates livestock health, thereby posing a serious threat to the global economy...
- · ai
[Paper] VerLM: Explaining Face Verification Using Natural Language
Face verification systems have seen substantial advancements; however, they often lack transparency in their decision-making processes. In this paper, we introd...
- · ai
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Introduction Swapping a face in a video is becoming increasingly easy with new deep‑fake tools, and we have already seen celebrities harmed by fabricated clips...
- · ai
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
Overview ZoeDepth predicts depth from a single image, handling both near and far objects accurately. It combines two learning strategies: one that preserves me...
- · ai
“AI-3D 모션 기술로 ‘Next AI 시대’를 열다”, 네이션에이 유수연 대표
네이션에이는 3D 모션 데이터를 AI로 제작/소비 대중화하여 'Next AI' 시대 핵심인 공간 지능 병목을 해결한다. '뉴로이드Neuroid'와 '헤이디Hey.D'로 3D 데이터 플라이휠을 구축, 백만 사용자 기반 글로벌 시장을 선도하고 있습니다. The post “AI-3D 모션 기...
- · ai
Mish: A Self Regularized Non-Monotonic Activation Function
Overview Mish is a simple activation function that can noticeably improve the performance of image‑based AI models. By replacing the standard activation with M...
- · ai
[Paper] AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction
Reconstructing dynamic 3D scenes from monocular videos requires simultaneously capturing high-frequency appearance details and temporally continuous motion. Exi...
- · ai
[Paper] Two Deep Learning Approaches for Automated Segmentation of Left Ventricle in Cine Cardiac MRI
Left ventricle (LV) segmentation is critical for clinical quantification and diagnosis of cardiac images. In this work, we propose two novel deep learning archi...
- · ai
[Paper] Fusion-SSAT: Unleashing the Potential of Self-supervised Auxiliary Task by Feature Fusion for Generalized Deepfake Detection
In this work, we attempted to unleash the potential of self-supervised learning as an auxiliary task that can optimise the primary task of generalised deepfake ...
- · ai
[Paper] FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing
Federated data sharing promises utility without centralizing raw data, yet existing embedding-level generators struggle under non-IID client heterogeneity and p...
- · ai
[Paper] Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection
While Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have shown strong generalisation in detecting image and video deepfakes, their ...