GMU:Computer's Cut/Kristin Jakubek - Revision history

A-Kristin Jakubek at 15:56, 31 January 2022

2022-01-31T15:56:02Z

← Older revision		Revision as of 15:56, 31 January 2022
Line 1:		Line 1:

	== Bicycle Supercut with image recognition ==		== (1) Bicycle Supercut with image recognition ==


Line 20:		Line 20:
	[[File:Screenshot 2022-01-26 at 13.23.34.png\|800px]]		[[File:Screenshot 2022-01-26 at 13.23.34.png\|800px]]

	== Videoediting with Subtitles ==		== (2) Videoediting with Subtitles ==


Line 47:		Line 47:
	Subtitles via: downsub		Subtitles via: downsub

	== Videoediting with sound using PD ==		== (3) Videoediting with sound using PD ==

	[[File:PD Patch MIDI file.png\|400px]]		[[File:PD Patch MIDI file.png\|400px]]

A-Kristin Jakubek: /* Bicycle Supercut with image recognition */

2022-01-27T17:40:51Z

Bicycle Supercut with image recognition

← Older revision		Revision as of 17:40, 27 January 2022
Line 10:		Line 10:
	To create this supercut of bicycles in film and television I used the Python script for 'object detection' we developed together during our course. By running the MobileNetSSD caffemodel, which includes amongst others, the CLASS of 'bicycle' the pre-trained neural network is able to apply image recognition to the supplied video inputs and indeed detect 'bicycles'.		To create this supercut of bicycles in film and television I used the Python script for 'object detection' we developed together during our course. By running the MobileNetSSD caffemodel, which includes amongst others, the CLASS of 'bicycle' the pre-trained neural network is able to apply image recognition to the supplied video inputs and indeed detect 'bicycles'.

	Instantly, when reading the CLASS 'bicycle' provided by the model, I had to think of a pivotal scene from the anime 'The girl who leapt through time', in which the main character dies due to failure of her bike's breaks. I was curious to see how the computer would 'see' this scene. As humans we can deduct that the bike is present - yet sometimes only partially in frame - for almost all of the shots of this short sequence. But when run through the image recognition script only brief appearances of the 'bicycle' can be detected, subsequently the scene looses its narrative and meaning. I remained curious to see how the machine would see other scenes of film and television history, which specifically came up in my mind as featuring, being defined by or being memorable because of the bicycles in them. The result is a short trip through film history from one of the first real motion picture films ever made ('Workers Leaving the Lumière Factory in Lyon') other classics and personal favourites.		Instantly, when reading the CLASS 'bicycle' provided by the model, I had to think of a pivotal scene from the anime 'The girl who leapt through time', in which the main character dies due to failure of her bike's breaks. I was curious to see how the computer would 'see' this scene. As humans we can deduct that the bike is present - yet sometimes only partially in frame - for almost all of the shots of this short sequence. But when run through the image recognition script only brief appearances of the 'bicycle' can be detected, subsequently the scene looses its narrative and meaning. I remained curious to see how the machine would see other scenes of film and television history, which specifically came up in my mind as featuring, being defined by or being memorable because of the bicycles in them. The result is a short trip through film history from one of the first real motion picture films ever made ('Workers Leaving the Lumière Factory in Lyon') other classics and personal favourites. Do you recognise them?

	[[File:Screenshot 2022-01-24 at 09.06.08.png\|800px]]		[[File:Screenshot 2022-01-24 at 09.06.08.png\|800px]]

A-Kristin Jakubek: /* Bicycle Supercut with image recognition */

2022-01-27T17:39:53Z

Bicycle Supercut with image recognition

← Older revision		Revision as of 17:39, 27 January 2022
Line 12:		Line 12:
	Instantly, when reading the CLASS 'bicycle' provided by the model, I had to think of a pivotal scene from the anime 'The girl who leapt through time', in which the main character dies due to failure of her bike's breaks. I was curious to see how the computer would 'see' this scene. As humans we can deduct that the bike is present - yet sometimes only partially in frame - for almost all of the shots of this short sequence. But when run through the image recognition script only brief appearances of the 'bicycle' can be detected, subsequently the scene looses its narrative and meaning. I remained curious to see how the machine would see other scenes of film and television history, which specifically came up in my mind as featuring, being defined by or being memorable because of the bicycles in them. The result is a short trip through film history from one of the first real motion picture films ever made ('Workers Leaving the Lumière Factory in Lyon') other classics and personal favourites.		Instantly, when reading the CLASS 'bicycle' provided by the model, I had to think of a pivotal scene from the anime 'The girl who leapt through time', in which the main character dies due to failure of her bike's breaks. I was curious to see how the computer would 'see' this scene. As humans we can deduct that the bike is present - yet sometimes only partially in frame - for almost all of the shots of this short sequence. But when run through the image recognition script only brief appearances of the 'bicycle' can be detected, subsequently the scene looses its narrative and meaning. I remained curious to see how the machine would see other scenes of film and television history, which specifically came up in my mind as featuring, being defined by or being memorable because of the bicycles in them. The result is a short trip through film history from one of the first real motion picture films ever made ('Workers Leaving the Lumière Factory in Lyon') other classics and personal favourites.

	[[File:Screenshot 2022-01-24 at 09.06.08.png\|~~400px~~]]		[[File:Screenshot 2022-01-24 at 09.06.08.png\|800px]]
	[[File:Screenshot 2022-01-24 at 09.06.22.png\|~~400px~~]]
	[[File:Screenshot 2022-01-26 at 13.23.34.png\|~~400px~~]]
			[[File:Screenshot 2022-01-24 at 09.06.22.png\|800px]]


			[[File:Screenshot 2022-01-26 at 13.23.34.png\|800px]]

	== Videoediting with Subtitles ==		== Videoediting with Subtitles ==

A-Kristin Jakubek: /* Bicycle Supercut with image recognition */

2022-01-27T17:39:25Z

Bicycle Supercut with image recognition

← Older revision		Revision as of 17:39, 27 January 2022
Line 11:		Line 11:

	Instantly, when reading the CLASS 'bicycle' provided by the model, I had to think of a pivotal scene from the anime 'The girl who leapt through time', in which the main character dies due to failure of her bike's breaks. I was curious to see how the computer would 'see' this scene. As humans we can deduct that the bike is present - yet sometimes only partially in frame - for almost all of the shots of this short sequence. But when run through the image recognition script only brief appearances of the 'bicycle' can be detected, subsequently the scene looses its narrative and meaning. I remained curious to see how the machine would see other scenes of film and television history, which specifically came up in my mind as featuring, being defined by or being memorable because of the bicycles in them. The result is a short trip through film history from one of the first real motion picture films ever made ('Workers Leaving the Lumière Factory in Lyon') other classics and personal favourites.		Instantly, when reading the CLASS 'bicycle' provided by the model, I had to think of a pivotal scene from the anime 'The girl who leapt through time', in which the main character dies due to failure of her bike's breaks. I was curious to see how the computer would 'see' this scene. As humans we can deduct that the bike is present - yet sometimes only partially in frame - for almost all of the shots of this short sequence. But when run through the image recognition script only brief appearances of the 'bicycle' can be detected, subsequently the scene looses its narrative and meaning. I remained curious to see how the machine would see other scenes of film and television history, which specifically came up in my mind as featuring, being defined by or being memorable because of the bicycles in them. The result is a short trip through film history from one of the first real motion picture films ever made ('Workers Leaving the Lumière Factory in Lyon') other classics and personal favourites.

			[[File:Screenshot 2022-01-24 at 09.06.08.png\|400px]]
			[[File:Screenshot 2022-01-24 at 09.06.22.png\|400px]]
			[[File:Screenshot 2022-01-26 at 13.23.34.png\|400px]]

	== Videoediting with Subtitles ==		== Videoediting with Subtitles ==

A-Kristin Jakubek: /* Bicycle Supercut with image recognition */

2022-01-27T17:36:18Z

Bicycle Supercut with image recognition

← Older revision		Revision as of 17:36, 27 January 2022
Line 6:		Line 6:

	Password: bike		Password: bike


			To create this supercut of bicycles in film and television I used the Python script for 'object detection' we developed together during our course. By running the MobileNetSSD caffemodel, which includes amongst others, the CLASS of 'bicycle' the pre-trained neural network is able to apply image recognition to the supplied video inputs and indeed detect 'bicycles'.

			Instantly, when reading the CLASS 'bicycle' provided by the model, I had to think of a pivotal scene from the anime 'The girl who leapt through time', in which the main character dies due to failure of her bike's breaks. I was curious to see how the computer would 'see' this scene. As humans we can deduct that the bike is present - yet sometimes only partially in frame - for almost all of the shots of this short sequence. But when run through the image recognition script only brief appearances of the 'bicycle' can be detected, subsequently the scene looses its narrative and meaning. I remained curious to see how the machine would see other scenes of film and television history, which specifically came up in my mind as featuring, being defined by or being memorable because of the bicycles in them. The result is a short trip through film history from one of the first real motion picture films ever made ('Workers Leaving the Lumière Factory in Lyon') other classics and personal favourites.

	== Videoediting with Subtitles ==		== Videoediting with Subtitles ==

A-Kristin Jakubek: /* Videoediting with image recognition */

2022-01-26T13:30:46Z

Videoediting with image recognition

← Older revision		Revision as of 13:30, 26 January 2022
Line 1:		Line 1:

	== ~~Videoediting~~ with image recognition ==		== Bicycle Supercut with image recognition ==


	{{#ev:vimeo\|670209857\|left\|}}		{{#ev:vimeo\|670209857\|left\|}}

	Password: bike		Password: bike






	== Videoediting with Subtitles ==		== Videoediting with Subtitles ==

A-Kristin Jakubek at 13:30, 26 January 2022

2022-01-26T13:30:25Z

← Older revision	Revision as of 13:30, 26 January 2022
Line 1:	Line 1:

		== Videoediting with image recognition ==


		{{#ev:vimeo\|670209857\|left\|}}

		Password: bike

A-Kristin Jakubek: /* Videoediting with sound using PD */

2021-12-13T08:21:44Z

Videoediting with sound using PD

← Older revision		Revision as of 08:21, 13 December 2021
Line 39:		Line 39:
	Assignment 13.12.2021		Assignment 13.12.2021

	~~[https://vimeo.com/656032961]]]~~

	{{#ev:vimeo\|656032961\|left\|}}		{{#ev:vimeo\|656032961\|left\|}}

A-Kristin Jakubek at 08:15, 13 December 2021

2021-12-13T08:15:17Z

← Older revision		Revision as of 08:15, 13 December 2021
Line 1:		Line 1:


	== Videoediting with Subtitles ==		== Videoediting with Subtitles ==
Line 38:		Line 39:
	Assignment 13.12.2021		Assignment 13.12.2021

			[https://vimeo.com/656032961]]]

			{{#ev:vimeo\|656032961\|left\|}}


	Password: PD		Password: PD

A-Kristin Jakubek: /* Videoediting with sound using PD */

2021-12-13T08:14:01Z

Videoediting with sound using PD

← Older revision		Revision as of 08:14, 13 December 2021
Line 33:		Line 33:

	[[File:PD Patch GEM Videoplayback.png\|400px]]		[[File:PD Patch GEM Videoplayback.png\|400px]]



			Assignment 13.12.2021



			Password: PD