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.
Temporal-Spatial Mapping for Action Recognition
Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
Using phase instead of optical flow for action recognition
A Neural Temporal Model for Human Motion Prediction
Multi-Target Prediction: A Unifying View on Problems and Methods
Unsupervised Learning of View-invariant Action Representations
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition
Zero-shot User Intent Detection via Capsule Neural Networks
On the Role of Event Boundaries in Egocentric Activity Recognition from Photostreams
Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset
Towards Effective Deep Embedding for Zero-Shot Learning
Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos
Open Set Chinese Character Recognition using Multi-typed Attributes
Targeted Nonlinear Adversarial Perturbations in Images and Videos
Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition
Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing
Universal Image Manipulation Detection using Deep Siamese Convolutional Neural Network
Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
Typhoon track prediction using satellite images in a Generative Adversarial Network
Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
Time Perception Machine: Temporal Point Processes for the When, Where and What of Activity Prediction
Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance
Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection
Early action prediction by soft regression
RGB Video Based Tennis Action Recognition Using a Deep Historical Long Short-Term Memory
Attributes' Importance for Zero-Shot Pose-Classification Based on Wearable Sensors
Multi-modal Cycle-consistent Generalized Zero-Shot Learning
Action Anticipation By Predicting Future Dynamic Images
Analyzing Human-Human Interactions: A Survey
Pose Guided Human Video Generation
Towards Automatic Speech Identification from Vocal Tract Shape Dynamics in Real-time MRI
Actor-Centric Relation Network
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.