HN Explorer

rdabane

↗ HN profile [ 543 ms ] full profile
Karma
99
Created
March 24, 2008 (18y ago)
Submissions
0
  1. Ask HN: Annotation tool for video

    What is commonly used tool for 'fast' annotation of video frames with bounding boxes ( e.g. Face detection)?

    1 points 0
  2. Ask HN: Annotated training/test data for driver monitoring algorithms

    I'm looking for annotated training/test video data sequences for driver monitoring(Driver drowsiness etc) application development.

    2 points 0
  3. Ask HN: Where is the industry to get large amounts of video data annotated?

    I'm looking for outsourcing firms to get hours of video data annotated .. on the topic, are there any good open source tools for video annotations ?

    3 points 3
  4. Ask HN: How much sharpening an image degrade Object detection

    I'm wondering in both classical and deep learning approaches if the input is sharpened images, does it affect the quality of detection?

    2 points 0
  5. U.S. Accuses Tech Firm of Bias Against Asian Software Engineers (mobile.nytimes.com)
    28 points 22
  6. Ask HN: Which is the smallest size CNN for Pedestrian Detection?

    Smallest size=memory required for intermediate + Network

    1 points 0
  7. How to estimate minimum memory required for forward pass in a CNN?

    Assuming I've a MxN input image, I need to estimate minimum memory required for inference. I'm ok with any kind of reordering of computations.

    1 points 1
  8. Why CNN papers use 224x224 images?

    Why most of CNN papers use 224x224 or 223x223 size images? Why not use more standard like 640x480?

    3 points 1
  9. First Proof That Wild Animals Really Can Communicate with Us (news.nationalgeographic.com)
    9 points 1
  10. End to End Learning for Self-Driving Cars [pdf] (images.nvidia.com)
    157 points 101