{
  "docId": "019dd923-5e88-73ef-bd5c-f812573a947a",
  "docSlug": "eea7524c557036f4",
  "documentTitle": "2020 Air Street Capital The State of AI Report 2020",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 54,
  "pageCount": 177,
  "prevPage": 53,
  "nextPage": 55,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 3,
  "notes": "The slide explains the LoRRA architecture and provides two examples of its application.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "flowchart",
    "photo",
    "data_table"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-f812573a947a/54",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a#slide-54",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "LoRRA is an approach that reads text in an image and jointly reasons about the image and text content to answer a question from a fixed or by selecting one of the OCR strings derived from the image.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c5-73ac-aa64-6a7ee73d0e4c",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.51,
        "x": 0.46,
        "y": 0.28
      },
      "kind": "diagram",
      "text": "LoRRA model architecture diagram",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "ea929206-1990-4edd-baf5-d939cc1be622",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.3,
        "w": 0.51,
        "x": 0.46,
        "y": 0.65
      },
      "kind": "image",
      "text": "Examples of LoRRA in action",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "b3e109fb-1e48-422f-8121-7d5c948db20e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.42,
        "x": 0.03,
        "y": 0.28
      },
      "kind": "list",
      "text": "While progress has been made in visual question answering (VQA), today’s systems cannot read and reason about text in an image. LoRRA is an approach that reads text in an image and jointly reasons about the image and text content to answer a question from a fixed or by selecting one of the OCR strings derived from the image. The system is trained on a new dataset that includes 45,336 questions on 28,408 images.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "94f4da18-7ef2-4156-a217-556ee66608dc",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.03,
        "w": 0.85,
        "x": 0.03,
        "y": 0.22
      },
      "kind": "title",
      "text": "Look, Read, Reason & Answer (LoRRA), a novel model for answering questions based on text in images.",
      "attrs": null,
      "subkind": "action-title",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "0fc4f2a3-8823-478d-a602-cea7af15d019",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.45,
        "x": 0.03,
        "y": 0.14
      },
      "kind": "title",
      "text": "Visual Question Answering about everyday images",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7bfd6b34-f1fb-4a93-8d15-b23364cb1afb",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 129,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-ed2a8f38a754",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Research, Talent, Industry sections inventory what happened in AI in 2020.",
      "position": 1,
      "confidence": 60,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 129,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-fc384f439bba",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Research, Talent and Industry sections build momentum of AI progress.",
      "position": 2,
      "confidence": 40,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 57,
      "from": 47,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3c-f820616b6fcc",
      "evidence": "Wimbledon synth video, object detection, depth, AutoML-Zero examples in sequence.",
      "position": 5,
      "objective": "Catalog computer vision and generative model advances",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 70,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}