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.
Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
Long-Range Trajectories from Global and Local Motion Representations
Hyper-Fisher Vectors for Action Recognition
Macau: Scalable Bayesian Multi-relational Factorization with Side Information using MCMC
Zero-Shot Learning via Semantic Similarity Embedding
Bio-Inspired Human Action Recognition using Hybrid Max-Product Neuro-Fuzzy Classifier and Quantum-Behaved PSO
Manipulated Object Proposal: A Discriminative Object Extraction and Feature Fusion Framework for First-Person Daily Activity Recognition
Action Recognition by Hierarchical Mid-level Action Elements
Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos
Action Recognition based on Subdivision-Fusion Model
Predicting respiratory motion for real-time tumour tracking in radiotherapy
Multimodal Multipart Learning for Action Recognition in Depth Videos
Action recognition in still images by latent superpixel classification
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
Towards Good Practices for Very Deep Two-Stream ConvNets
An embarrassingly simple approach to zero-shot learning
Ridge Regression, Hubness, and Zero-Shot Learning
Unsupervised Learning from Narrated Instruction Videos
Tell and Predict: Kernel Classifier Prediction for Unseen Visual Classes from Unstructured Text Descriptions
Time Series Classification using the Hidden-Unit Logistic Model
Slow and steady feature analysis: higher order temporal coherence in video
P-CNN: Pose-based CNN Features for Action Recognition
Hierarchical recurrent neural network for skeleton based action recognition
First-Take-All: Temporal Order-Preserving Hashing for 3D Action Videos
Learning to track for spatio-temporal action localization
Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning
Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition
Visual Semantic Role Labeling
Sparse 3D convolutional neural networks
Contextual Action Recognition with R*CNN
Modeling Representation of Videos for Anomaly Detection using Deep Learning: A Review
Dense Optical Flow Prediction from a Static Image
Differential Recurrent Neural Networks for Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.