https://github.com/chuangchuangtan/c2p-clip-deepfakedetection
공식 코드C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection
Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning
CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning
What makes you, you? Analyzing Recognition by Swapping Face Parts
Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction
Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing
EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection
Countering Malicious DeepFakes: Survey, Battleground, and Horizon
Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling
High-resolution Face Swapping via Latent Semantics Disentanglement
Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
Analytic Manifold Learning: Unifying and Evaluating Representations for Continuous Control
AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
Learning Interpretable, High-Performing Policies for Autonomous Driving
Reconciling Spatial and Temporal Abstractions for Goal Representation
Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
BN-AuthProf: Benchmarking Machine Learning for Bangla Author Profiling on Social Media Texts
FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction
SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person
Matched sample selection with GANs for mitigating attribute confounding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.