Search Results for author:
Found 8 papers, 1 papers with code
Canonical Face Embeddings
When instead evaluating embeddings generated from two CNNs, where one CNN's embeddings are mapped with a linear transformation, the mean true accept rate drops to 0. 95 using the same verification paradigm.
Locally Linear Attributes of ReLU Neural Networks
The weights in the neural network determine a decomposition of the input space into convex polytopes and on each of these polytopes the network can be described by a single affine mapping.
Exploring the Interchangeability of CNN Embedding Spaces
When image embeddings generated by one CNN are transformed into embeddings corresponding to the feature space of a second CNN trained on the same task, their respective image classification or face verification performance is largely preserved.
A Pose Proposal and Refinement Network for Better Object Pose Estimation
Our approach is composed of 2 main components: the first component classifies the objects in the input image and proposes an initial 6D pose estimate through a multi-task, CNN-based encoder/multi-decoder module.
End-to-end Learning Improves Static Object Geo-localization in Monocular Video
We also show that the end-to-end system performance is further improved via joint-training of the constituent models.
Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Prediction
Our end-to-end model consists of two stages: the first stage is an encoder/decoder network that learns to predict future video frames.
Gesture Recognition: Focus on the Hands
Gestures are a common form of human communication and important for human computer interfaces (HCI).
