{
  "patent_number": "US 9965705",
  "country": "US",
  "title": "How AI Uses Question-Guided Attention to Answer Questions About Images",
  "original_title": "Systems and methods for attention-based configurable convolutional neural networks (ABC-CNN) for visual question answering",
  "summary": "A method for AI to answer questions about images by dynamically focusing on relevant parts of the picture based on the specific question asked.",
  "what_it_does": "This patent describes a way to make AI better at answering questions about photos or videos. It uses a system called ABC-CNN that takes both an image and a text question as input. The system extracts features from the image and turns the question into a mathematical representation. It then uses the question to create special 'kernels'—small filters that act like a spotlight—to highlight only the parts of the image relevant to the question. Finally, it combines this focused information with the original image data to generate an accurate answer, effectively ignoring irrelevant background noise.",
  "what_it_does_not_cover": [
    "Does not cover general-purpose image classification that does not involve a natural language question input.",
    "Does not cover attention mechanisms that are not specifically implemented via configurable convolutional kernels.",
    "Does not cover non-neural network methods for image analysis or traditional rule-based computer vision.",
    "Does not cover the specific hardware used to run the neural network, only the algorithmic method."
  ],
  "filed": "2016-06-16",
  "granted": "2018-05-08",
  "expires": "2036-06-16",
  "status": "active",
  "holder": "Baidu USA LLC",
  "holder_url": "https://patentbrief.org/company/baidu-usa-llc",
  "inventors": [
    {
      "name": "Kan Chen",
      "url": "https://patentbrief.org/inventor/kan-chen"
    },
    {
      "name": "Wei Xu",
      "url": "https://patentbrief.org/inventor/wei-xu"
    },
    {
      "name": "Jiang Wang",
      "url": "https://patentbrief.org/inventor/jiang-wang"
    }
  ],
  "times_cited": 28,
  "tags": [
    "ai_ml",
    "consumer_electronics",
    "software"
  ],
  "abstract": "Described herein are systems and methods for generating and using attention-based deep learning architectures for visual question answering task (VQA) to automatically generate answers for image-related (still or video images) questions. To generate the correct answers, it is important for a model's attention to focus on the relevant regions of an image according to the question because different questions may ask about the attributes of different image regions. In embodiments, such question-guided attention is learned with a configurable convolutional neural network (ABC-CNN). Embodiments of the ABC-CNN models determine the attention maps by convolving image feature map with the configurable convolutional kernels determined by the questions semantics. In embodiments, the question-guided attention maps focus on the question-related regions and filters out noise in the unrelated regions.",
  "url": "https://patentbrief.org/patent/us/9965705/systems-and-methods-for-attention-based-configurable-convolutional-neural-networks-abc-cnn-for-visual-question-answering",
  "markdown_url": "https://patentbrief.org/patent/us/9965705/systems-and-methods-for-attention-based-configurable-convolutional-neural-networks-abc-cnn-for-visual-question-answering/md",
  "google_patents_url": "https://patents.google.com/patent/US9965705",
  "relatedPatents": [
    {
      "patentNumber": "10452978",
      "countryCode": "US",
      "title": "How AI Models Understand Language Using 'Attention'",
      "url": "https://patentbrief.org/patent/us/10452978/transformer-attention-mechanism"
    },
    {
      "patentNumber": "20230162023",
      "countryCode": "US",
      "title": "Automated AI for Adapting to New Data Without Retraining",
      "url": "https://patentbrief.org/patent/us/20230162023/system-and-method-for-automated-transfer-learning-with-domain-disentanglement"
    },
    {
      "patentNumber": "11023780",
      "countryCode": "US",
      "title": "How AI Automatically Labels Images and Checks Its Own Work",
      "url": "https://patentbrief.org/patent/us/11023780/siri-on-device-speech-recognition"
    },
    {
      "patentNumber": "20250363357",
      "countryCode": "US",
      "title": "How to Update AI on Small Devices with Slow Internet",
      "url": "https://patentbrief.org/patent/us/20250363357/systems-and-methods-for-deploying-and-updating-neural-networks-at-the-edge-of-a-"
    },
    {
      "patentNumber": "11544573",
      "countryCode": "US",
      "title": "How Projection Neural Networks Speed Up AI Predictions",
      "url": "https://patentbrief.org/patent/us/11544573/llama-large-language-model-architecture"
    }
  ]
}