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.
A Zero-Shot Learning application in Deep Drawing process using Hyper-Process Model
ODN: Opening the Deep Network for Open-set Action Recognition
Semantic Image Networks for Human Action Recognition
Skeleton-based Action Recognition of People Handling Objects
Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Abstract]
Multi-modal Ensemble Classification for Generalized Zero Shot Learning
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
Cricket stroke extraction: Towards creation of a large-scale cricket actions dataset
UAV-GESTURE: A Dataset for UAV Control and Gesture Recognition
Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions
Transductive Zero-Shot Learning with Visual Structure Constraint
Graph Neural Networks with convolutional ARMA filters
Action2Vec: A Crossmodal Embedding Approach to Action Learning
Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks
Coupled Recurrent Network (CRN)
Adaptive Confidence Smoothing for Generalized Zero-Shot Learning
Temporal Hockey Action Recognition via Pose and Optical Flows
Canonical Correlation Analysis for Misaligned Satellite Image Change Detection
Animating Arbitrary Objects via Deep Motion Transfer
D3D: Distilled 3D Networks for Video Action Recognition
Multi-Level Sequence GAN for Group Activity Recognition
Classifier and Exemplar Synthesis for Zero-Shot Learning
Action Machine: Rethinking Action Recognition in Trimmed Videos
AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection
Few-shot classification in Named Entity Recognition Task
TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition
Nrityantar: Pose oblivious Indian classical dance sequence classification system
Human Motion Prediction via Spatio-Temporal Inpainting
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition
Learning Discriminative Motion Features Through Detection
Loss Guided Activation for Action Recognition in Still Images
Zero-Shot Learning with Sparse Attribute Propagation
Zero-Shot Anticipation for Instructional Activities
BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN
Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifold
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.