Publications by authors named "Vittal Premachandran"

When building vision systems that predict structured objects such as image segmentations or human poses, a crucial concern is performance under task-specific evaluation measures (e.g., Jaccard Index or Average Precision).

View Article and Find Full Text PDF

Synopsis of recent research by authors named "Vittal Premachandran"

  • - Vittal Premachandran's research focuses on enhancing the performance of vision systems, particularly in predicting structured objects like image segmentations and human poses, while ensuring effectiveness under task-specific evaluation measures.
  • - His 2017 article, "Empirical Minimum Bayes Risk Prediction," explores the importance of performance metrics such as Jaccard Index and Average Precision in the context of visual object prediction.
  • - The findings highlight the significance of aligning predictive models with specific evaluation criteria to improve the accuracy and reliability of vision-based applications in machine intelligence.