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.
A Hybrid Framework for Action Recognition in Low-Quality Video Sequences
Investigation on Combining 3D Convolution of Image Data and Optical Flow to Generate Temporal Action Proposals
Transfer feature generating networks with semantic classes structure for zero-shot learning
Improving SIEM for Critical SCADA Water Infrastructures Using Machine Learning
Spatiotemporal Pyramid Network for Video Action Recognition
Zero-Shot Task Transfer
Collaborative Spatio-temporal Feature Learning for Video Action Recognition
Let's Transfer Transformations of Shared Semantic Representations
Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
Semantic-Guided Multi-Attention Localization for Zero-Shot Learning
Zero-shot Learning of 3D Point Cloud Objects
Neural Imaging Pipelines - the Scourge or Hope of Forensics?
Joint Face Detection and Facial Motion Retargeting for Multiple Faces
Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions
IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition
STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection
Privacy-Preserving Action Recognition using Coded Aperture Videos
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
Human Motion Prediction via Learning Local Structure Representations and Temporal Dependencies
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
Dynamic Matrix Decomposition for Action Recognition
Predicting tongue motion in unlabeled ultrasound videos using convolutional LSTM neural network
Evaluating the Effectiveness of Automated Identity Masking (AIM) Methods with Human Perception and a Deep Convolutional Neural Network (CNN)
Simplifying Graph Convolutional Networks
Exploring Frame Segmentation Networks for Temporal Action Localization
Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification
Forensic Similarity for Digital Images
Session-based Sequential Skip Prediction via Recurrent Neural Networks
Peeking into the Future: Predicting Future Person Activities and Locations in Videos
Skeleton-Based Online Action Prediction Using Scale Selection Network
Harnessing GANs for Zero-shot Learning of New Classes in Visual Speech Recognition
Spatio-temporal Action Recognition: A Survey
DistInit: Learning Video Representations Without a Single Labeled Video
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.