Search Results for author:
Found 6 papers, 4 papers with code
Center Prediction Loss for Re-identification
In this paper, we propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of same-class samples.
Fast Fourier Convolution
FFC is a generic operator that can directly replace vanilla convolutions in a large body of existing networks, without any adjustments and with comparable complexity metrics (e. g., FLOPs).
Non-Local Neural Networks With Grouped Bilinear Attentional Transforms
The core of our method is learnable and data-adaptive bilinear attentional transform (BA-Transform), whose merits are three-folds: first, BA-Transform is versatile to model a wide spectrum of local or global attentional operations, such as emphasizing specific local regions.
Fast Non-Local Neural Networks with Spectral Residual Learning
We show its equivalence to conducting residual learning in some spectral domain and carefully re-formulate a variety of neural layers into their spectral forms, such as ReLU or convolutions.
Two-Stream Video Classification with Cross-Modality Attention
In the experiments, we comprehensively compare our method with two-stream and non-local models widely used in video classification.
Ranked #32 on
Action Recognition
on UCF101
Deep Steering: Learning End-to-End Driving Model from Spatial and Temporal Visual Cues
There are multiple fronts to these endeavors, including object detection on roads, 3-D reconstruction etc., but in this work we focus on a vision-based model that directly maps raw input images to steering angles using deep networks.
