https://github.com/andreYoo/PeGCNs
공식 코드Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
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.
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark
History Matters: Temporal Knowledge Editing in Large Language Model
Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities
Reconstructing undersampled photoacoustic microscopy images using deep learning
Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition
Editing Implicit Assumptions in Text-to-Image Diffusion Models
Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
Recognizing Involuntary Actions from 3D Skeleton Data Using Body States
Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition
In-Context Editing: Learning Knowledge from Self-Induced Distributions
UniPose: Unified Human Pose Estimation in Single Images and Videos
MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA
Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action Recognition
Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.