Publications by authors named "Neal Mazur"
Article Synopsis
- Drug-target affinity (DTA) prediction is crucial for drug development, helping researchers gauge the potential effectiveness and safety of new drugs early on.
- Traditional models struggle with accuracy due to inadequate representation of substructure interactions in drug molecules.
- The new TDGraphDTA model uses advanced techniques like transformers and diffusion graphs to enhance prediction accuracy and interpretability by capturing detailed relationships among molecular substructures, showing improved results on benchmark datasets.
Person re-identification (Re-ID) is challenging due to host of factors: the variety of human positions, difficulties in aligning bounding boxes, and complex backgrounds, among other factors. This paper proposes a new framework called EXAM (EXtreme And Moderate feature embeddings) for Re-ID tasks. This is done using discriminative feature learning, requiring attention-based guidance during training.
View Article and Find Full Text PDF