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.
Joint Dictionaries for Zero-Shot Learning
Detecting Hands in Egocentric Videos: Towards Action Recognition
RNN-based Early Cyber-Attack Detection for the Tennessee Eastman Process
Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs
A Compact Kernel Approximation for 3D Action Recognition
Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks
Link the head to the "beak": Zero Shot Learning from Noisy Text Description at Part Precision
A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders
Two-stream Flow-guided Convolutional Attention Networks for Action Recognition
Hierarchical Multi-scale Attention Networks for Action Recognition
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
Generating Visual Representations for Zero-Shot Classification
Human Action Recognition System using Good Features and Multilayer Perceptron Network
Recognizing Involuntary Actions from 3D Skeleton Data Using Body States
Attentive Semantic Video Generation using Captions
Pillar Networks++: Distributed non-parametric deep and wide networks
Eigen Evolution Pooling for Human Action Recognition
Lattice Long Short-Term Memory for Human Action Recognition
Motion Feature Augmented Recurrent Neural Network for Skeleton-based Dynamic Hand Gesture Recognition
Exploring Temporal Preservation Networks for Precise Temporal Action Localization
Attention Transfer from Web Images for Video Recognition
When Kernel Methods meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data
Unsupervised Representation Learning by Sorting Sequences
Action recognition by learning pose representations
Predicting Human Activities Using Stochastic Grammar
Weakly-supervised learning of visual relations
Learning from Video and Text via Large-Scale Discriminative Clustering
Boosted Zero-Shot Learning with Semantic Correlation Regularization
A Simple Exponential Family Framework for Zero-Shot Learning
Automatic Curation of Golf Highlights using Multimodal Excitement Features
Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017
Multi-kernel learning of deep convolutional features for action recognition
Discriminative convolutional Fisher vector network for action recognition
Visually Aligned Word Embeddings for Improving Zero-shot Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.