Talks
Slides from talks
- A tale of two negative results [slides (pptx)]
- Towards AI agents that can see, talk, and act [slides (pptx)]
- Visual Dialog [slides (pptx)]
- Towards Transparent VQA Models [slides (pptx)]
- Visual Question Answering [slides (pptx)]
- Submodular meets Structured: Finding Diverse Subsets in Exponentially-Large Structured Item Sets.
[ slides (pptx) ]
- M-Best and Diverse M-Best MAP Inference in Graphical Models [ slides ]
- CloudCV: Large-Scale Distributed Computer Vision as a Cloud Service [ slides ]
- Hedging Against Uncertainty via Multiple Diverse Predictions [ slides (pptx) ]
- Structured-Output Models for Computer Vision
- The M-Best Mode Problem [ slides (pptx) ]
- Focused Inference and the M-Best Mode Problem [ slides (pptx) ]
- Focused Inference with Local Primal-Dual Gaps [ slides (pptx) ]
- On Graph-Structured Discrete Labelling Problems in Computer Vision [ slides (pptx) ]
- Beyond Trees: MRF Inference via Outer-Planar Decomposition [ slides (pptx) ]