Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.

Sign up to join this community

Anybody can ask a question

Anybody can answer

The best answers are voted up and rise to the top

Explore our Questions

Ask Question

more tags

Active Hot Week Month

3

votes

1

answer

62

views

Why should one focus on spectral operations as a computer vision researcher?

computer-vision academia spectral-analysis

modified yesterday nbro♦ 31.7k

2

votes

2

answers

70

views

How to classify two very similar images using Deep Learning?

computer-vision image-recognition opencv

answered Jan 19 at 18:54 NikoNyrh 215

0

votes

2

answers

56

views

Are there any works that deal with 2D pose estimation in videos?

convolutional-neural-networks computer-vision reference-request transformer pose-estimation

modified Jan 18 at 17:13 Avatrin 386

1

vote

1

answer

124

views

How do I segment each part of a DICOM image?

computer-vision matlab image-segmentation

modified Jan 16 at 18:05 CommunityBot 1

1

vote

1

answer

132

views

How to normalize for perceptual loss when training neural net from scratch?

deep-learning computer-vision

modified Jan 16 at 17:04 CommunityBot 1

8

votes

1

answer

254

views

Why does nobody use decision trees for visual question answering?

neural-networks computer-vision decision-trees explainable-ai question-answering

modified Jan 15 at 5:57 hanugm 2,783

2

votes

2

answers

2k

views

How can I detect thin objects (like pens and pencils) without a bounding box but only 2 endpoints and the orientation?

convolutional-neural-networks computer-vision object-detection yolo model-request

answered Jan 12 at 16:00 Marcel_marcel1991 556

2

votes

1

answer

34

views

How does a bounding box detection network "know" about absolute position?

computer-vision object-detection bounding-box

answered Jan 12 at 15:17 Marcel_marcel1991 556

3

votes

2

answers

564

views

Alternative to sliding window neural network (was: Object detect (or) image classification at specific locations in the frame)

deep-learning classification computer-vision object-recognition

modified Jan 6 at 23:01 CommunityBot 1

0

votes

0

answers

19

views

Does adding new keypoints increase accuracy for foot keypoint detection?

computer-vision image-recognition object-detection data-labelling pose-estimation

asked Jan 2 at 14:36 dasmehdix 247

1

vote

1

answer

203

views

How to choose a suitable threshold value for the Shi-Tomasi corner detection algorithm?

computer-vision hyperparameter-optimization feature-extraction shi-tomasi-algorithm corner-detection

modified Jan 1 at 9:02 CommunityBot 1

0

votes

1

answer

31

views

What is the expression for projective transformation?

computer-vision image-processing affine-transformations image-transformations projective-transformations

modified Dec 30 '21 at 10:03 nbro♦ 31.7k

6

votes

1

answer

284

views

Which neural networks are suitable for visual place recognition?

machine-learning convolutional-neural-networks computer-vision visual-place-recognition

modified Dec 30 '21 at 2:01 CommunityBot 1

0

votes

1

answer

124

views

In this paper, if region $R_{2}$ moves in a sliding window manner, won't the saliency map have a smaller size than the original image?

computer-vision papers math convolution saliency-map

modified Dec 29 '21 at 5:29 Archana David 1

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled