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.
Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition
Skeleton-based Action Recognition Using LSTM and CNN
Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics
Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
Alternative Semantic Representations for Zero-Shot Human Action Recognition
A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning
Recurrent Residual Learning for Action Recognition
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates
Detekcja upadku i wybranych akcji na sekwencjach obrazów cyfrowych
Sampling Matters in Deep Embedding Learning
Pedestrian Prediction by Planning using Deep Neural Networks
Learning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition
Zero-Shot Relation Extraction via Reading Comprehension
Joint Max Margin and Semantic Features for Continuous Event Detection in Complex Scenes
Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization
Learning to Learn from Noisy Web Videos
Generative-Discriminative Variational Model for Visual Recognition
Learning Structured Semantic Embeddings for Visual Recognition
Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition
Deep manifold-to-manifold transforming network for action recognition
Continuous Video to Simple Signals for Swimming Stroke Detection with Convolutional Neural Networks
Zero-Shot Learning with Generative Latent Prototype Model
Sequence Summarization Using Order-constrained Kernelized Feature Subspaces
Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition
Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
Semantic Softmax Loss for Zero-Shot Learning
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Learning Spatiotemporal Features for Infrared Action Recognition with 3D Convolutional Neural Networks
Single Image Action Recognition by Predicting Space-Time Saliency
An Improved Video Analysis using Context based Extension of LSH
CHAM: action recognition using convolutional hierarchical attention model
Deep Spatio-temporal Manifold Network for Action Recognition
Temporal Segment Networks for Action Recognition in Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.