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.
On Learning Semantic Representations for Million-Scale Free-Hand Sketches
Complex Human Action Recognition in Live Videos Using Hybrid FR-DL Method
VPN: Learning Video-Pose Embedding for Activities of Daily Living
Quo Vadis, Skeleton Action Recognition ?
Weakly Supervised Temporal Action Localization with Segment-Level Labels
JUMPS: Joints Upsampling Method for Pose Sequences
Path Signatures on Lie Groups
The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
Learning unbiased zero-shot semantic segmentation networks via transductive transfer
Motion Prediction in Visual Object Tracking
Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback
Ontology-guided Semantic Composition for Zero-Shot Learning
Deep Learning for Vision-based Prediction: A Survey
Long-term Pedestrian Trajectory Prediction using Mutable Intention Filter and Warp LSTM
Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition
Bookworm continual learning: beyond zero-shot learning and continual learning
One Thousand and One Hours: Self-driving Motion Prediction Dataset
A causal view of compositional zero-shot recognition
Insights from the Future for Continual Learning
3DMotion-Net: Learning Continuous Flow Function for 3D Motion Prediction
Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning
Class Normalization for (Continual)? Generalized Zero-Shot Learning
Zero-Shot Learning with Common Sense Knowledge Graphs
Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition
1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
Towards Incorporating Contextual Knowledge into the Prediction of Driving Behavior
A Taxonomy and Review of Algorithms for Modeling and Predicting Human Driver Behavior
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)
CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)
DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition
3DFCNN: Real-Time Action Recognition using 3D Deep Neural Networks with Raw Depth Information
Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks
Iterate & Cluster: Iterative Semi-Supervised Action Recognition
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.