tomaarsen HF staff commited on
Commit
3a519c5
1 Parent(s): 1cfe586

Fix punctuation in examples

Browse files
Files changed (1) hide show
  1. README.md +73 -73
README.md CHANGED
@@ -15,98 +15,98 @@ metrics:
15
  - recall
16
  - f1
17
  widget:
18
- - text: 'Genetic algorithm guided selection : variable selection and subset selection
19
- A novel genetic algorithm guided selection method , GAS , has been described .
20
  The method utilizes a simple encoding scheme which can represent both compounds
21
- and variables used to construct a QSAR/QSPR model . A genetic algorithm is then
22
  utilized to simultaneously optimize the encoded variables that include both descriptors
23
- and compound subsets . The GAS method generates multiple models each applying
24
- to a subset of the compounds . Typically the subsets represent clusters with different
25
- chemotypes . Also a procedure based on molecular similarity is presented to determine
26
- which model should be applied to a given test set compound . The variable selection
27
  method implemented in GAS has been tested and compared using the Selwood data
28
- set -LRB- n = 31 compounds ; nu = 53 descriptors -RRB- . The results showed that
29
- the method is comparable to other published methods . The subset selection method
30
  implemented in GAS has been first tested using an artificial data set -LRB- n
31
- = 100 points ; nu = 1 descriptor -RRB- to examine its ability to subset data points
32
- and second applied to analyze the XLOGP data set -LRB- n = 1831 compounds ; nu
33
- = 126 descriptors -RRB- . The method is able to correctly identify artificial
34
- data points belonging to various subsets . The analysis of the XLOGP data set
35
  shows that the subset selection method can be useful in improving a QSAR/QSPR
36
  model when the variable selection method fails'
37
- - text: Presentation media , information complexity , and learning outcomes Multimedia
38
- computing provides a variety of information presentation modality combinations
39
- . Educators have observed that visuals enhance learning which suggests that multimedia
40
  presentations should be superior to text-only and text with static pictures in
41
- facilitating optimal human information processing and , therefore , comprehension
42
- . The article reports the findings from a 3 -LRB- text-only , overhead slides
43
- , and multimedia presentation -RRB- * 2 -LRB- high and low information complexity
44
- -RRB- factorial experiment . Subjects read a text script , viewed an acetate overhead
45
- slide presentation , or viewed a multimedia presentation depicting the greenhouse
46
  effect -LRB- low complexity -RRB- or photocopier operation -LRB- high complexity
47
- -RRB- . Multimedia was superior to text-only and overhead slides for comprehension
48
- . Information complexity diminished comprehension and perceived presentation quality
49
- . Multimedia was able to reduce the negative impact of information complexity
50
- on comprehension and increase the extent of sustained attention to the presentation
51
- . These findings suggest that multimedia presentations invoke the use of both
52
  the verbal and visual working memory channels resulting in a reduction of the
53
- cognitive load imposed by increased information complexity . Moreover , multimedia
54
  superiority in facilitating comprehension goes beyond its ability to increase
55
- sustained attention ; the quality and effectiveness of information processing
56
- attained -LRB- i.e. , use of verbal and visual working memory -RRB- is also significant
57
  - text: Adaptive filtering for noise reduction in hue saturation intensity color space
58
  Even though the hue saturation intensity -LRB- HSI -RRB- color model has been
59
- widely used in color image processing and analysis , the conversion formulas from
60
  the RGB color model to HSI are nonlinear and complicated in comparison with the
61
- conversion formulas of other color models . When an RGB image is degraded by random
62
- Gaussian noise , this nonlinearity leads to a nonuniform noise distribution in
63
- HSI , making accurate image analysis more difficult . We have analyzed the noise
64
  characteristics of the HSI color model and developed an adaptive spatial filtering
65
  method to reduce the magnitude of noise and the nonuniformity of noise variance
66
- in the HSI color space . With this adaptive filtering method , the filter kernel
67
- for each pixel is dynamically adjusted , depending on the values of intensity
68
- and saturation . In our experiments we have filtered the saturation and hue components
69
- and generated edge maps from color gradients . We have found that by using the
70
- adaptive filtering method , the minimum error rate in edge detection improves
71
- by approximately 15 %
72
  - text: Restoration of broadband imagery steered with a liquid-crystal optical phased
73
- array In many imaging applications , it is highly desirable to replace mechanical
74
- beam-steering components -LRB- i.e. , mirrors and gimbals -RRB- with a nonmechanical
75
- device . One such device is a nematic liquid crystal optical phased array -LRB-
76
- LCOPA -RRB- . An LCOPA can implement a blazed phase grating to steer the incident
77
- light . However , when a phase grating is used in a broadband imaging system ,
78
- two adverse effects can occur . First , dispersion will cause different incident
79
- wavelengths arriving at the same angle to be steered to different output angles
80
- , causing chromatic aberrations in the image plane . Second , the device will
81
- steer energy not only to the first diffraction order , but to others as well .
82
  This multiple-order effect results in multiple copies of the scene appearing in
83
- the image plane . We describe a digital image restoration technique designed to
84
- overcome these degradations . The proposed postprocessing technique is based on
85
- a Wiener deconvolution filter . The technique , however , is applicable only to
86
  scenes containing objects with approximately constant reflectivities over the
87
- spectral region of interest . Experimental results are presented to demonstrate
88
  the effectiveness of this technique
89
- - text: A comparison of computational color constancy Algorithms . II . Experiments
90
- with image data For pt.I see ibid. , vol . 11 , no. 9 , p.972-84 -LRB- 2002 -RRB-
91
- . We test a number of the leading computational color constancy algorithms using
92
- a comprehensive set of images . These were of 33 different scenes under 11 different
93
- sources representative of common illumination conditions . The algorithms studied
94
- include two gray world methods , a version of the Retinex method , several variants
95
- of Forsyth 's -LRB- 1990 -RRB- gamut-mapping method , Cardei et al. 's -LRB- 2000
96
- -RRB- neural net method , and Finlayson et al. 's color by correlation method
97
- -LRB- Finlayson et al. 1997 , 2001 ; Hubel and Finlayson 2000 -RRB- . We discuss
98
- a number of issues in applying color constancy ideas to image data , and study
99
- in depth the effect of different preprocessing strategies . We compare the performance
100
- of the algorithms on image data with their performance on synthesized data . All
101
- data used for this study are available online at http://www.cs.sfu.ca/~color/data
102
- , and implementations for most of the algorithms are also available -LRB- http://www.cs.sfu.ca/~color/code
103
- -RRB- . Experiments with synthesized data -LRB- part one of this paper -RRB- suggested
104
- that the methods which emphasize the use of the input data statistics , specifically
105
- color by correlation and the neural net algorithm , are potentially the most effective
106
- at estimating the chromaticity of the scene illuminant . Unfortunately , we were
107
- unable to realize comparable performance on real images . Here exploiting pixel
108
  intensity proved to be more beneficial than exploiting the details of image chromaticity
109
- statistics , and the three-dimensional -LRB- 3-D -RRB- gamut-mapping algorithms
110
  gave the best performance
111
  pipeline_tag: token-classification
112
  co2_eq_emissions:
@@ -184,7 +184,7 @@ from span_marker import SpanMarkerModel
184
  # Download from the 🤗 Hub
185
  model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-uncased-keyphrase-inspec")
186
  # Run inference
187
- entities = model.predict("Adaptive filtering for noise reduction in hue saturation intensity color space Even though the hue saturation intensity -LRB- HSI -RRB- color model has been widely used in color image processing and analysis , the conversion formulas from the RGB color model to HSI are nonlinear and complicated in comparison with the conversion formulas of other color models . When an RGB image is degraded by random Gaussian noise , this nonlinearity leads to a nonuniform noise distribution in HSI , making accurate image analysis more difficult . We have analyzed the noise characteristics of the HSI color model and developed an adaptive spatial filtering method to reduce the magnitude of noise and the nonuniformity of noise variance in the HSI color space . With this adaptive filtering method , the filter kernel for each pixel is dynamically adjusted , depending on the values of intensity and saturation . In our experiments we have filtered the saturation and hue components and generated edge maps from color gradients . We have found that by using the adaptive filtering method , the minimum error rate in edge detection improves by approximately 15 %")
188
  ```
189
 
190
  ### Downstream Use
 
15
  - recall
16
  - f1
17
  widget:
18
+ - text: 'Genetic algorithm guided selection: variable selection and subset selection
19
+ A novel genetic algorithm guided selection method, GAS, has been described.
20
  The method utilizes a simple encoding scheme which can represent both compounds
21
+ and variables used to construct a QSAR/QSPR model. A genetic algorithm is then
22
  utilized to simultaneously optimize the encoded variables that include both descriptors
23
+ and compound subsets. The GAS method generates multiple models each applying
24
+ to a subset of the compounds. Typically the subsets represent clusters with different
25
+ chemotypes. Also a procedure based on molecular similarity is presented to determine
26
+ which model should be applied to a given test set compound. The variable selection
27
  method implemented in GAS has been tested and compared using the Selwood data
28
+ set -LRB- n = 31 compounds; nu = 53 descriptors -RRB-. The results showed that
29
+ the method is comparable to other published methods. The subset selection method
30
  implemented in GAS has been first tested using an artificial data set -LRB- n
31
+ = 100 points; nu = 1 descriptor -RRB- to examine its ability to subset data points
32
+ and second applied to analyze the XLOGP data set -LRB- n = 1831 compounds; nu
33
+ = 126 descriptors -RRB-. The method is able to correctly identify artificial
34
+ data points belonging to various subsets. The analysis of the XLOGP data set
35
  shows that the subset selection method can be useful in improving a QSAR/QSPR
36
  model when the variable selection method fails'
37
+ - text: Presentation media, information complexity, and learning outcomes Multimedia
38
+ computing provides a variety of information presentation modality combinations.
39
+ Educators have observed that visuals enhance learning which suggests that multimedia
40
  presentations should be superior to text-only and text with static pictures in
41
+ facilitating optimal human information processing and, therefore, comprehension.
42
+ The article reports the findings from a 3 -LRB- text-only, overhead slides,
43
+ and multimedia presentation -RRB- * 2 -LRB- high and low information complexity
44
+ -RRB- factorial experiment. Subjects read a text script, viewed an acetate overhead
45
+ slide presentation, or viewed a multimedia presentation depicting the greenhouse
46
  effect -LRB- low complexity -RRB- or photocopier operation -LRB- high complexity
47
+ -RRB-. Multimedia was superior to text-only and overhead slides for comprehension.
48
+ Information complexity diminished comprehension and perceived presentation quality.
49
+ Multimedia was able to reduce the negative impact of information complexity
50
+ on comprehension and increase the extent of sustained attention to the presentation.
51
+ These findings suggest that multimedia presentations invoke the use of both
52
  the verbal and visual working memory channels resulting in a reduction of the
53
+ cognitive load imposed by increased information complexity. Moreover, multimedia
54
  superiority in facilitating comprehension goes beyond its ability to increase
55
+ sustained attention; the quality and effectiveness of information processing
56
+ attained -LRB- i.e., use of verbal and visual working memory -RRB- is also significant
57
  - text: Adaptive filtering for noise reduction in hue saturation intensity color space
58
  Even though the hue saturation intensity -LRB- HSI -RRB- color model has been
59
+ widely used in color image processing and analysis, the conversion formulas from
60
  the RGB color model to HSI are nonlinear and complicated in comparison with the
61
+ conversion formulas of other color models. When an RGB image is degraded by random
62
+ Gaussian noise, this nonlinearity leads to a nonuniform noise distribution in
63
+ HSI, making accurate image analysis more difficult. We have analyzed the noise
64
  characteristics of the HSI color model and developed an adaptive spatial filtering
65
  method to reduce the magnitude of noise and the nonuniformity of noise variance
66
+ in the HSI color space. With this adaptive filtering method, the filter kernel
67
+ for each pixel is dynamically adjusted, depending on the values of intensity
68
+ and saturation. In our experiments we have filtered the saturation and hue components
69
+ and generated edge maps from color gradients. We have found that by using the
70
+ adaptive filtering method, the minimum error rate in edge detection improves
71
+ by approximately 15%
72
  - text: Restoration of broadband imagery steered with a liquid-crystal optical phased
73
+ array In many imaging applications, it is highly desirable to replace mechanical
74
+ beam-steering components -LRB- i.e., mirrors and gimbals -RRB- with a nonmechanical
75
+ device. One such device is a nematic liquid crystal optical phased array -LRB-
76
+ LCOPA -RRB-. An LCOPA can implement a blazed phase grating to steer the incident
77
+ light. However, when a phase grating is used in a broadband imaging system,
78
+ two adverse effects can occur. First, dispersion will cause different incident
79
+ wavelengths arriving at the same angle to be steered to different output angles,
80
+ causing chromatic aberrations in the image plane. Second, the device will
81
+ steer energy not only to the first diffraction order, but to others as well.
82
  This multiple-order effect results in multiple copies of the scene appearing in
83
+ the image plane. We describe a digital image restoration technique designed to
84
+ overcome these degradations. The proposed postprocessing technique is based on
85
+ a Wiener deconvolution filter. The technique, however, is applicable only to
86
  scenes containing objects with approximately constant reflectivities over the
87
+ spectral region of interest. Experimental results are presented to demonstrate
88
  the effectiveness of this technique
89
+ - text: A comparison of computational color constancy Algorithms. II. Experiments
90
+ with image data For pt.I see ibid., vol. 11, no. 9, p.972-84 -LRB- 2002 -RRB-.
91
+ We test a number of the leading computational color constancy algorithms using
92
+ a comprehensive set of images. These were of 33 different scenes under 11 different
93
+ sources representative of common illumination conditions. The algorithms studied
94
+ include two gray world methods, a version of the Retinex method, several variants
95
+ of Forsyth's -LRB- 1990 -RRB- gamut-mapping method, Cardei et al.'s -LRB- 2000
96
+ -RRB- neural net method, and Finlayson et al.'s color by correlation method
97
+ -LRB- Finlayson et al. 1997, 2001; Hubel and Finlayson 2000 -RRB-. We discuss
98
+ a number of issues in applying color constancy ideas to image data, and study
99
+ in depth the effect of different preprocessing strategies. We compare the performance
100
+ of the algorithms on image data with their performance on synthesized data. All
101
+ data used for this study are available online at http://www.cs.sfu.ca/~color/data,
102
+ and implementations for most of the algorithms are also available -LRB- http://www.cs.sfu.ca/~color/code
103
+ -RRB-. Experiments with synthesized data -LRB- part one of this paper -RRB- suggested
104
+ that the methods which emphasize the use of the input data statistics, specifically
105
+ color by correlation and the neural net algorithm, are potentially the most effective
106
+ at estimating the chromaticity of the scene illuminant. Unfortunately, we were
107
+ unable to realize comparable performance on real images. Here exploiting pixel
108
  intensity proved to be more beneficial than exploiting the details of image chromaticity
109
+ statistics, and the three-dimensional -LRB- 3-D -RRB- gamut-mapping algorithms
110
  gave the best performance
111
  pipeline_tag: token-classification
112
  co2_eq_emissions:
 
184
  # Download from the 🤗 Hub
185
  model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-uncased-keyphrase-inspec")
186
  # Run inference
187
+ entities = model.predict("Adaptive filtering for noise reduction in hue saturation intensity color space Even though the hue saturation intensity -LRB- HSI -RRB- color model has been widely used in color image processing and analysis, the conversion formulas from the RGB color model to HSI are nonlinear and complicated in comparison with the conversion formulas of other color models. When an RGB image is degraded by random Gaussian noise, this nonlinearity leads to a nonuniform noise distribution in HSI, making accurate image analysis more difficult. We have analyzed the noise characteristics of the HSI color model and developed an adaptive spatial filtering method to reduce the magnitude of noise and the nonuniformity of noise variance in the HSI color space. With this adaptive filtering method, the filter kernel for each pixel is dynamically adjusted, depending on the values of intensity and saturation. In our experiments we have filtered the saturation and hue components and generated edge maps from color gradients. We have found that by using the adaptive filtering method, the minimum error rate in edge detection improves by approximately 15%")
188
  ```
189
 
190
  ### Downstream Use