Search Results for author:
Found 9 papers, 3 papers with code
Sparse Pose Trajectory Completion
In the absence of dense pose sampling in image space, these latent space trajectories provide cross-modal guidance for learning.
Connectivity-Optimized Representation Learning via Persistent Homology
In particular, we control the connectivity of an autoencoder's latent space via a novel type of loss, operating on information from persistent homology.
Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes
Somewhat surprisingly, the scene classification results are superior to those of a CNN explicitly trained for scene classification, using a large scene dataset (Places).
Feature Space Transfer for Data Augmentation
A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose.
Deep Scene Image Classification With the MFAFVNet
This enables the design of a network architecture, the MFAFVNet, that can be trained in an end to end manner.
AGA: Attribute-Guided Augmentation
We implement our approach as a deep encoder-decoder architecture that learns the synthesis function in an end-to-end manner.
AGA: Attribute Guided Augmentation
We implement our approach as a deep encoder-decoder architecture that learns the synthesis function in an end-to-end manner.
Semantic Clustering for Robust Fine-Grained Scene Recognition
In this work, we propose a novel domain generalization approach for fine-grained scene recognition.
Scene Classification With Semantic Fisher Vectors
A semantic FV is then computed as a Gaussian Mixture FV in the space of these natural parameters.
