https://github.com/Ymm-cll/UniErase
공식 코드UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Temporal Action Localization aims to detect activities in the video stream and output beginning and end timestamps. It is closely related to Temporal Action Proposal Generation.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition
Hypergraph Transformer for Skeleton-based Action Recognition
Unsupervised Motion Representation Learning with Capsule Autoencoders
Evaluating the Ability of LLMs to Solve Semantics-Aware Process Mining Tasks
Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction
Generative Model-based Feature Knowledge Distillation for Action Recognition
Semantics2Hands: Transferring Hand Motion Semantics between Avatars
Skinned Motion Retargeting with Dense Geometric Interaction Perception
FollowMe: Vehicle Behaviour Prediction in Autonomous Vehicle Settings
Ionospheric activity prediction using convolutional recurrent neural networks
Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge
Infrared and 3D skeleton feature fusion for RGB-D action recognition
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition
Saliency-Guided DETR for Moment Retrieval and Highlight Detection
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
Consistency-based Self-supervised Learning for Temporal Anomaly Localization
Video action detection by learning graph-based spatio-temporal interactions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.