Feature-wise transformations
Explore this paper's citation graph
- Type
- article
- Published
- 2018-07-09
- Cited by
- 233
- References
- 59
- Access
- Open access
- OpenAlex
- https://openalex.org/W2879390606
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:69938552
Keywords
Computer science, Feature (linguistics), Image (mathematics), Modalities, Artificial intelligence
References
- A Parallel Computation that Assigns Canonical Object-Based Frames of Reference
- Generating Text with Recurrent Neural Networks
- Learning to Relate Images
- Combining discriminative features to infer complex trajectories
- Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis
- Matrix Factorization Techniques for Recommender Systems
- Robust Boltzmann Machines for recognition and denoising
- Long Short-Term Memory
- Bilinear CNN Models for Fine-Grained Visual Recognition
- Personalized recommendation on dynamic content using predictive bilinear models
- Factored conditional restricted Boltzmann Machines for modeling motion style
- Facial expression space learning
- DeViSE: A Deep Visual-Semantic Embedding Model
- Zero-Shot Learning Through Cross-Modal Transfer
- Separating Style and Content
- Learning Where to Attend with Deep Architectures for Image Tracking
- Separating Style and Content with Bilinear Models
- Visualizing Data using t-SNE
- ReferItGame: Referring to Objects in Photographs of Natural Scenes
- Convolutional Two-Stream Network Fusion for Video Action Recognition
Cited by
- The Visual QA Devil in the Details: The Impact of Early Fusion and Batch Norm on CLEVR
- Conditional WaveGAN
- End-to-end Sound Source Separation Conditioned on Instrument Labels
- A Style-Based Generator Architecture for Generative Adversarial Networks
- CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
- Variation Network: Learning High-level Attributes for Controlled Input Manipulation
- Conditioning Neural Networks: A Case Study of Electricity Load Forecasting
- Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks
- A Highly Adaptive Acoustic Model for Accurate Multi-dialect Speech Recognition
- Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network
- Attention-based Conditioning Methods for External Knowledge Integration
- Human-Machine Collaboration for Fast Land Cover Mapping
- Visual Reasoning with Multi-hop Feature Modulation
- Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations
- A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization
- Data Preprocessing Technique for Neural Networks Based on Image Represented by a Fuzzy Function
- Deep Network Interpolation for Continuous Imagery Effect Transition
- Gating Mechanisms for Combining Character and Word-level Word Representations: an Empirical Study
- Convolution-deconvolution architecture with the pyramid pooling module for semantic segmentation
- Deep Dexterous Grasping of Novel Objects from a Single View
Related papers
- The Effect of Teaching Practical Physical Modalities on the Ordering Skills of Residents in Physical Medicine and Rehabilitation
- SHAPE: An Unified Approach to Evaluate the Contribution and Cooperation of Individual Modalities
- EMOTIONAL MODALITIES OF A MODERN TEACHER AND THEIR CORRECTION
- Interruptions as multimodal outputs: which are the less disruptive?
- Beyond a Generic Complementary and Alternative Medicine: The Holistic Health Care- Conventional Medicine Continuum
- Counseling Students' Perceptions of Supervisory Modalities
- Patients' and therapists' expectations and evaluations of hospital treatment: satisfactions and disappointments.
- Analysis of Pacing Strategies in AMRAP, EMOM, and FOR TIME Training Models during “Cross” Modalities
- Nanjing-style Illustrations in A Journey to the West and the Spread of the Book:Differences and Similarities of the Illustrations among Nanjing-style,Huizhou-style and Jianyang-style