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.
DWnet: Deep-Wide Network for 3D Action Recognition
Cooperative Cross-Stream Network for Discriminative Action Representation
Mobile Video Action Recognition
Accelerated Motion-Aware MR Imaging via Motion Prediction from K-Space Center
Bayesian Nonparametrics for Non-exhaustive Learning
A Semantics-Guided Class Imbalance Learning Model for Zero-Shot Classification
Graph Based Skeleton Modeling for Human Activity Analysis
3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
Learning stochastic differential equations using RNN with log signature features
Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control
Multi-Modal Recognition of Worker Activity for Human-Centered Intelligent Manufacturing
Human activity recognition from skeleton poses
Weakly-supervised Action Localization with Background Modeling
Zero Shot Learning for Multi-Modal Real Time Image Registration
Mixed High-Order Attention Network for Person Re-Identification
Transferable Contrastive Network for Generalized Zero-Shot Learning
Zero-Shot Crowd Behavior Recognition
Learning Trajectory Dependencies for Human Motion Prediction
Generalised Zero-Shot Learning with Domain Classification in a Joint Semantic and Visual Space
Three Branches: Detecting Actions With Richer Features
Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning
Domain-Specific Embedding Network for Zero-Shot Recognition
Zero-Shot Feature Selection via Transferring Supervised Knowledge
What goes around comes around: Cycle-Consistency-based Short-Term Motion Prediction for Anomaly Detection using Generative Adversarial Networks
Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization
STM: SpatioTemporal and Motion Encoding for Action Recognition
Generalised Zero-Shot Learning with a Classifier Ensemble over Multi-Modal Embedding Spaces
Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework
Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos
Learning Variations in Human Motion via Mix-and-Match Perturbation
Deep Kinematic Models for Kinematically Feasible Vehicle Trajectory Predictions
Image Captioning with Unseen Objects
Time Series Analysis of Big Data for Electricity Price and Demand to Find Cyber-Attacks part 2: Decomposition Analysis
SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition
Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.