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.
TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
Pose-conditioned Spatio-Temporal Attention for Human Action Recognition
Locality preserving projection on SPD matrix Lie group: algorithm and analysis
Learning and Refining of Privileged Information-based RNNs for Action Recognition from Depth Sequences
A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment
Transductive Zero-Shot Learning with a Self-training dictionary approach
Transductive Zero-Shot Learning with Adaptive Structural Embedding
GPU Activity Prediction using Representation Learning
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
A Bag-of-Words Equivalent Recurrent Neural Network for Action Recognition
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding
Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes
R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
Two-Stream RNN/CNN for Action Recognition in 3D Videos
No Fuss Distance Metric Learning using Proxies
Zero-Shot Learning by Generating Pseudo Feature Representations
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Zero-Shot Recognition using Dual Visual-Semantic Mapping Paths
Prototypical Networks for Few-shot Learning
Zero-Shot Learning -- The Good, the Bad and the Ugly
Improving Interpretability of Deep Neural Networks with Semantic Information
UntrimmedNets for Weakly Supervised Action Recognition and Detection
A New Representation of Skeleton Sequences for 3D Action Recognition
A Pursuit of Temporal Accuracy in General Activity Detection
CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks
Anticipating many futures: Online human motion prediction and synthesis for human-robot collaboration
Deep representation learning for human motion prediction and classification
Crowdsourcing Cybersecurity: Cyber Attack Detection using Social Media
Evolution-Preserving Dense Trajectory Descriptors
Joint Discovery of Object States and Manipulation Actions
Robust features for facial action recognition
Deep Local Video Feature for Action Recognition
Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition
Action Recognition: From Static Datasets to Moving Robots
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.