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.
Activity Graph Transformer for Temporal Action Localization
Bridging the gap between Human Action Recognition and Online Action Detection
Semantics Disentangling for Generalized Zero-Shot Learning
Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences
CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition
Video action recognition for lane-change classification and prediction of surrounding vehicles
Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts
Investigating the Effect of Sensor Modalities in Multi-Sensor Detection-Prediction Models
Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval
Explainable Neural Network-based Modulation Classification via Concept Bottleneck Models
A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization
Learning to Generate Task-Specific Adapters from Task Description
CIZSL++: Creativity Inspired Generative Zero-Shot Learning
3D Human motion anticipation and classification
Incremental Embedding Learning via Zero-Shot Translation
Integrated Generalized Zero-Shot Learning for Fine-Grained Classification
Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning
Action Recognition with Kernel-based Graph Convolutional Networks
Tensor Representations for Action Recognition
Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain
Multi-grained Trajectory Graph Convolutional Networks for Habit-unrelated Human Motion Prediction
Human Action Recognition from Various Data Modalities: A Review
Evolutionary Variational Optimization of Generative Models
Speech Enhancement with Zero-Shot Model Selection
Multi-shot Temporal Event Localization: a Benchmark
Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN
Temporal Graph Modeling for Skeleton-based Action Recognition
CT Super Resolution via Zero Shot Learning
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses
GTA: Global Temporal Attention for Video Action Understanding
FlowMOT: 3D Multi-Object Tracking by Scene Flow Association
Variable-Shot Adaptation for Online Meta-Learning
MVFNet: Multi-View Fusion Network for Efficient Video Recognition
Improving Zero Shot Learning Baselines with Commonsense Knowledge
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.