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.
Temporally Coherent Embeddings for Self-Supervised Video Representation Learning
Temporal Extension Module for Skeleton-Based Action Recognition
DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
Feedback Graph Convolutional Network for Skeleton-based Action Recognition
A Novel Online Action Detection Framework from Untrimmed Video Streams
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction
MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps
SF-Net: Single-Frame Supervision for Temporal Action Localization
Collaborative Motion Prediction via Neural Motion Message Passing
Gimme Signals: Discriminative signal encoding for multimodal activity recognition
Skeleton Based Action Recognition using a Stacked Denoising Autoencoder with Constraints of Privileged Information
Accurate Temporal Action Proposal Generation with Relation-Aware Pyramid Network
Unifying Specialist Image Embedding into Universal Image Embedding
Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition
Change Point Models for Real-time Cyber Attack Detection in Connected Vehicle Environment
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition
Addressing target shift in zero-shot learning using grouped adversarial learning
Infrared and 3D skeleton feature fusion for RGB-D action recognition
Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction
Towards Zero-shot Learning for Automatic Phonemic Transcription
Human Action Recognition using Local Two-Stream Convolution Neural Network Features and Support Vector Machines
Bottom-Up Temporal Action Localization with Mutual Regularization
Knowledge Integration Networks for Action Recognition
CRL: Class Representative Learning for Image Classification
A Survey on 3D Skeleton-Based Action Recognition Using Learning Method
Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition
Differentiable Graph Module (DGM) for Graph Convolutional Networks
On Parameter Tuning in Meta-learning for Computer Vision
From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition
Self-Supervised Joint Encoding of Motion and Appearance for First Person Action Recognition
Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
Poisson Kernel Avoiding Self-Smoothing in Graph Convolutional Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.