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.
What have we learned from deep representations for action recognition?
A Unified Method for First and Third Person Action Recognition
Zero-Shot Learning via Latent Space Encoding
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
On the Integration of Optical Flow and Action Recognition
Taking Visual Motion Prediction To New Heightfields
Human Action Recognition: Pose-based Attention draws focus to Hands
Train Once, Test Anywhere: Zero-Shot Learning for Text Classification
Weakly Supervised Action Localization by Sparse Temporal Pooling Network
Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition
Im2Flow: Motion Hallucination from Static Images for Action Recognition
Deception Detection in Videos
Generalized Zero-Shot Learning via Synthesized Examples
Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery
Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning
Neural Cross-Lingual Entity Linking
Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition
Feature Generating Networks for Zero-Shot Learning
Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions
A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
Multimodal Visual Concept Learning with Weakly Supervised Techniques
Compressed Video Action Recognition
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Label Efficient Learning of Transferable Representations across Domains and Tasks
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories
Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machines
Highly Efficient Human Action Recognition with Quantum Genetic Algorithm Optimized Support Vector Machine
Structure propagation for zero-shot learning
HP-GAN: Probabilistic 3D human motion prediction via GAN
D numbers theory based game-theoretic framework in adversarial decision making under fuzzy environment
Predictive Learning: Using Future Representation Learning Variantial Autoencoder for Human Action Prediction
Appearance-and-Relation Networks for Video Classification
Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.