Ramprasaath R. Selvaraju
SQuINTing at VQA Models: Interrogating VQA Models with Sub-QuestionsTrick or Treat: Thematic Reinforcement for Artistic TypographyCounting Everyday Objects in Everyday ScenesGrad-CAM: Visual Explanations from Deep Networks via Gradient-based LocalizationAlign before Fuse: Vision and Language Representation Learning with Momentum DistillationDiverse Beam Search: Decoding Diverse Solutions from Neural Sequence ModelsThe Semantic Paintbrush: Interactive 3D Mapping and Recognition in Large Outdoor SpacesTaking a HINT: Leveraging Explanations to Make Vision and Language Models More GroundedCASTing Your Model: Learning to Localize Improves Self-Supervised RepresentationsChoose Your Neuron: Incorporating Domain Knowledge into Deep Networks through Neuron ImportanceSOrTing VQA Models: Improving Consistency via Gradient AlignmentVisual Explanations from Deep Networks

Trick or Treat: Thematic Reinforcement for Artistic Typography

Ramprasaath R. Selvaraju

  • Ramprasaath R. Selvaraju
  • ramprasaath.21@gmail.com
  • Ramprasaath
  • ramprasaath21

Ramprasaath is a Senior Research Scientist at Apple, specializing in Computer Vision.