https://github.com/madrylab/modelcomponents
공식 코드Decomposing and Editing Predictions by Modeling Model Computation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image: Rahmani et al
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Decomposing and Editing Predictions by Modeling Model Computation
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
Masked Motion Predictors are Strong 3D Action Representation Learners
Generative Action Description Prompts for Skeleton-based Action Recognition
Generative Action Description Prompts for Skeleton-based Action Recognition
Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks
Improving Phenotype Prediction using Long-Range Spatio-Temporal Dynamics of Functional Connectivity
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
A System for Real-Time Interactive Analysis of Deep Learning Training
Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
Untying the Reversal Curse via Bidirectional Language Model Editing
Neighboring Perturbations of Knowledge Editing on Large Language Models
Improving Skeleton-based Action Recognition with Interactive Object Information
Explicit Visual Prompting for Low-Level Structure Segmentations
Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis
Reasons and Solutions for the Decline in Model Performance after Editing
Simple yet efficient real-time pose-based action recognition
Graph Contrastive Learning for Skeleton-based Action Recognition
Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art
Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN
SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.