Zero-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 33
- 보존된 평가 기록
- 84
Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.
Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.
Benchmark datasets for zero-shot learning include aPY, AwA, and CUB, among others.
( Image credit: Prototypical Networks for Few shot Learning in PyTorch )
Further readings:
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction
Prediction of Human Full-Body Movements with Motion Optimization and Recurrent Neural Networks
Zero Shot Learning on Simulated Robots
Latent-Variable Generative Models for Data-Efficient Text Classification
Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image Interpretation
Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps
Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction
Generalized Zero-shot ICD Coding
C-3PO: Cyclic-Three-Phase Optimization for Human-Robot Motion Retargeting based on Reinforcement Learning
OCTNet: Trajectory Generation in New Environments from Past Experiences
Learning deep representations for video-based intake gesture detection
Learning Coupled Spatial-temporal Attention for Skeleton-based Action Recognition
CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language
Making the Invisible Visible: Action Recognition Through Walls and Occlusions
Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos
Global Temporal Representation based CNNs for Infrared Action Recognition
Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition
Class Feature Pyramids for Video Explanation
Alleviating Feature Confusion for Generative Zero-shot Learning
Deep Point-wise Prediction for Action Temporal Proposal
NEMO: Future Object Localization Using Noisy Ego Priors
Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model
Adversarial Attack on Skeleton-based Human Action Recognition
Metric-Based Few-Shot Learning for Video Action Recognition
Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
Zero-Shot Action Recognition in Videos: A Survey
Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints
A Meta-Learning Framework for Generalized Zero-Shot Learning
Video Representation Learning by Dense Predictive Coding
SDM-Net: A Simple and Effective Model for Generalized Zero-Shot Learning
Episode-based Prototype Generating Network for Zero-Shot Learning
Multi-Modal Three-Stream Network for Action Recognition
Graph Convolutional Networks for Temporal Action Localization
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.