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.
Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization
A Novel Approach for Robust Multi Human Action Recognition and Summarization based on 3D Convolutional Neural Networks
Zero-Shot Sign Language Recognition: Can Textual Data Uncover Sign Languages?
Make Skeleton-based Action Recognition Model Smaller, Faster and Better
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
Bayesian Zero-Shot Learning
TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning
GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving
Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
Slow Feature Analysis for Human Action Recognition
Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
Two-stream Spatiotemporal Feature for Video QA Task
Kernel Trajectory Maps for Multi-Modal Probabilistic Motion Prediction
Video Action Recognition Via Neural Architecture Searching
A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data
Learning Shape-Motion Representations from Geometric Algebra Spatio-Temporal Model for Skeleton-Based Action Recognition
Zero-shot Learning for Audio-based Music Classification and Tagging
Molecular activity prediction using graph convolutional deep neural network considering distance on a molecular graph
Visual Space Optimization for Zero-shot Learning
SpliceRadar: A Learned Method For Blind Image Forensics
A Comparative Review of Recent Kinect-based Action Recognition Algorithms
Planning Robot Motion using Deep Visual Prediction
Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets
From Zero-Shot Learning to Cold-Start Recommendation
Zero-shot Learning and Knowledge Transfer in Music Classification and Tagging
Understanding More about Human and Machine Attention in Deep Neural Networks
Unsupervised Learning of Object Keypoints for Perception and Control
R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition
Weakly Supervised Clustering by Exploiting Unique Class Count
Accelerating temporal action proposal generation via high performance computing
PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction
Representation Quality Of Neural Networks Links To Adversarial Attacks and Defences
Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.