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.
Learning a Deep Embedding Model for Zero-Shot Learning
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
Action2Activity: Recognizing Complex Activities from Sensor Data
Spatiotemporal Residual Networks for Video Action Recognition
Learning recurrent representations for hierarchical behavior modeling
Sliding Dictionary Based Sparse Representation For Action Recognition
Exploiting Structure Sparsity for Covariance-based Visual Representation
Local Similarity-Aware Deep Feature Embedding
Short-term prediction of localized cloud motion using ground-based sky imagers
Review of Action Recognition and Detection Methods
ARTiS: Appearance-based Action Recognition in Task Space for Real-Time Human-Robot Collaboration
Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning
Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions
Zero Shot Hashing
Real-time Human Pose Estimation from Video with Convolutional Neural Networks
Pose from Action: Unsupervised Learning of Pose Features based on Motion
Deep Coevolutionary Network: Embedding User and Item Features for Recommendation
Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups
Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN
A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories
Image and Video Mining through Online Learning
Semi-Supervised Classification with Graph Convolutional Networks
Making a Case for Learning Motion Representations with Phase
Human Action Recognition without Human
Spatio-temporal Aware Non-negative Component Representation for Action Recognition
Hard Negative Mining for Metric Learning Based Zero-Shot Classification
Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition
Infinite-Label Learning with Semantic Output Codes
We Can "See" You via Wi-Fi - WiFi Action Recognition via Vision-based Methods
Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition
Solving Visual Madlibs with Multiple Cues
Discriminatively Trained Latent Ordinal Model for Video Classification
Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition
Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification
A Survey of Visual Analysis of Human Motion and Its Applications
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.