Search Results for author:
Found 10 papers, 4 papers with code
Conformer: Embedding Continuous Attention in Vision Transformer for Weather Forecasting
Conformer is designed to learn the continuous weather evolution over time by implementing continuity in the multi-head attention mechanism.
SCONE-GAN: Semantic Contrastive learning-based Generative Adversarial Network for an end-to-end image translation
SCONE-GAN presents an end-to-end image translation, which is shown to be effective for learning to generate realistic and diverse scenery images.
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking
Limited availability of labeled data for machine learning on multimodal time-series extensively hampers progress in the field.
Multimodal Trajectory Prediction: A Survey
Trajectory prediction is an important task to support safe and intelligent behaviours in autonomous systems.
How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies
Recent studies have shown that robustness (the ability for a model to perform well on unseen data) plays a significant role in the type of strategy that should be used when approaching a new problem and, hence, measuring the robustness of these strategies has become a fundamental problem.
Long-term Spatio-temporal Forecasting via Dynamic Multiple-Graph Attention
To address these issues, we construct new graph models to represent the contextual information of each node and the long-term spatio-temporal data dependency structure.
GCCN: Global Context Convolutional Network
These global contextual features are defined as local maxima pixels with high visual sharpness in each patch.
Signature-Graph Networks
SGN constructs unique undirected graphs for each image based on the CNN feature maps.
Spatiotemporal Data Mining: A Survey on Challenges and Open Problems
Specifically, we investigate the challenging issues in regards to spatiotemporal relationships, interdisciplinarity, discretisation, and data characteristics.
DroTrack: High-speed Drone-based Object Tracking Under Uncertainty
The combination of the FCM segmentation and the angular scaling increased DroTrack precision by up to $9\%$ and decreased the centre location error by $162$ pixels on average.
