Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

exploring 2,500 named colour terms, organised by similarity in CLIP's 512-dimensional text embedding space. the structure that emerges from just text inputs forms a kind of continuous colour space, hinting at a low-dimensional manifold for colour language.

Matt DesLauriers

61,504 subscribers

13,971 просмотров • 4 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Data often lie on a low-dimensional manifold embedded in a high-dimensional space. But these manifolds are often highly non-linear, making linear dimensionality reduction methods like PCA insufficient. This has motivated the development of non-linear dimensionality reduction.

Data often lie on a low-dimensional manifold embedded in a high-dimensional space. But these manifolds are often highly non-linear, making linear dimensionality reduction methods like PCA insufficient. This has motivated the development of non-linear dimensionality reduction.

Alec Helbling

212,685 просмотров • 9 месяцев назад

🚨Joe Rogan: Eric Weinstein "The successor to spacetime is the Observerse" 🤯 Overcoming the spacetime speed limit... "The successor to spacetime, I'm happy to predict this on your show, will be named the observerse, which is a combination of not just using a four-dimensional space-time manifold, but a 14 and a four-dimensional space simultaneously." #ufotwitter #uapX Source:

🚨Joe Rogan: Eric Weinstein "The successor to spacetime is the Observerse" 🤯 Overcoming the spacetime speed limit... "The successor to spacetime, I'm happy to predict this on your show, will be named the observerse, which is a combination of not just using a four-dimensional space-time manifold, but a 14 and a four-dimensional space simultaneously." #ufotwitter #uapX Source:

Skywatch Signal

141,128 просмотров • 3 месяцев назад

an esoteric colour picker exploring perceptual ambiguities, drawn from ~3 million human-labelled colours. for each named colour (eg. "pink"), the disc represents the two primary axes of uncertainty in the data, and the slider exposes a third axis. more details below.

an esoteric colour picker exploring perceptual ambiguities, drawn from ~3 million human-labelled colours. for each named colour (eg. "pink"), the disc represents the two primary axes of uncertainty in the data, and the slider exposes a third axis. more details below.

Matt DesLauriers

76,008 просмотров • 4 месяцев назад

Language models process data as one-dimensional sequences of tokens — ideal for text, but limited for understanding the physical world. In contrast, spatial intelligence embraces a 3D representation, unlocking a deeper understanding of space and time. More from martin_casado's interview with Fei-Fei Li and Justin Johnson:

Language models process data as one-dimensional sequences of tokens — ideal for text, but limited for understanding the physical world. In contrast, spatial intelligence embraces a 3D representation, unlocking a deeper understanding of space and time. More from martin_casado's interview with Fei-Fei Li and Justin Johnson:

a16z

64,662 просмотров • 1 год назад

branching interface for writing a tighter creative feedback loop guided by a language model to weave through the possibility space of text

branching interface for writing a tighter creative feedback loop guided by a language model to weave through the possibility space of text

Azlen

53,043 просмотров • 2 лет назад

So the colour Saffron is an eyesore for the CM !!! A building near the Kolkata Airport which was painted in Saffron colour was forcefully covered by Green Net by the Mamata Police and local Municipality Officials so that the CM who was returning back from North Bengal doesn't get annoyed. It's unfortunate that the colour Saffron; a symbol of Valor which also signifies sacrifice and salvation, worn proudly by Swami Vivekananda, makes the CM uncomfortable. The name of the building is Joy Mata Di Apartment owned by Shri Panna Bardhan. The colour of the Sun at dawn paints the whole sky Saffron, what would the Administration do to cover that?

So the colour Saffron is an eyesore for the CM !!! A building near the Kolkata Airport which was painted in Saffron colour was forcefully covered by Green Net by the Mamata Police and local Municipality Officials so that the CM who was returning back from North Bengal doesn't get annoyed. It's unfortunate that the colour Saffron; a symbol of Valor which also signifies sacrifice and salvation, worn proudly by Swami Vivekananda, makes the CM uncomfortable. The name of the building is Joy Mata Di Apartment owned by Shri Panna Bardhan. The colour of the Sun at dawn paints the whole sky Saffron, what would the Administration do to cover that?

Suvendu Adhikari

89,981 просмотров • 1 год назад

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

Andrew Ng

107,967 просмотров • 1 год назад

For a while now, I feel like my sense of seeing surfaces in terms of colour has developed.⬆️ By changing color to match surface changes, three-dimensionality comes through. When i understood that, i thought this is what it means to paint with colour, i found it delightful !🤩

For a while now, I feel like my sense of seeing surfaces in terms of colour has developed.⬆️ By changing color to match surface changes, three-dimensionality comes through. When i understood that, i thought this is what it means to paint with colour, i found it delightful !🤩

ShimodaSketch EN

29,610 просмотров • 1 год назад

[CLIP] by Hand ✍️ The CLIP (Contrastive Language–Image Pre-training) model, a groundbreaking work by OpenAI, redefines the intersection of computer vision and natural language processing. It is the basis of all the multi-modal foundation models we see today. How does CLIP work? Goal: 🟨 Learn a shared embedding space for text and image [1] Given ↳ A mini batch of 3 text-image pairs ↳ OpenAI used 400 million text-image pairs to train its original CLIP model. Process 1st pair: "big table" [2] 🟪 Text → 2 Vectors (3D) ↳ Look up word embedding vectors using word2vec. [3] 🟩 Image → 2 Vectors (4D) ↳ Divide the image into two patches. ↳ Flatten each patch [4] Process other pairs ↳ Repeat [2]-[3] [5] 🟪 Text Encoder & 🟩 Image Encoder ↳ Encode input vectors into feature vectors ↳ Here, both encoders are simple one layer perceptron (linear + ReLU) ↳ In practice, the encoders are usually transformer models. [6] 🟪 🟩 Mean Pooling: 2 → 1 vector ↳ Average 2 feature vectors into a single vector by averaging across the columns ↳ The goal is to have one vector to represent each image or text [7] 🟪 🟩 -> 🟨 Projection ↳ Note that the text and image feature vectors from the encoders have different dimensions (3D vs. 4D). ↳ Use a linear layer to project image and text vectors to a 2D shared embedding space. 🏋️ Contrastive Pre-training 🏋️ [8] Prepare for MatMul ↳ Copy text vectors (T1,T2,T3) ↳ Copy the transpose of image vectors (I1,I2,I3) ↳ They are all in the 2D shared embedding space. [9] 🟦 MatMul ↳ Multiply T and I matrices. ↳ This is equivalent to taking dot product between every pair of image and text vectors. ↳ The purpose is to use dot product to estimate the similarity between a pair of image-text. [10] 🟦 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [11] 🟦 Softmax: ∑ ↳ Sum each row for 🟩 image→🟪 text ↳ Sum each column for 🟪 text→ 🟩 image [12] 🟦 Softmax: 1 / sum ↳ Divide each element by the column sum to obtain a similarity matrix for 🟪 text→🟩 image ↳ Divide each element by the row sum to obtain a similarity matrix for 🟩 image→🟪 text [13] 🟥 Loss Gradients ↳ The "Targets" for the similarity matrices are Identity Matrices. ↳ Why? If I and T come from the same pair (i=j), we want the highest value, which is 1, and 0 otherwise. ↳ Apply the simple equation of [Similarity - Target] to compute gradients of for both directions. ↳ Why so simple? Because when Softmax and Cross-Entropy Loss are used together, the math magically works out that way. ↳ These gradients kick off the backpropagation process to update weights and biases of the encoders and projection layers (red borders).

[CLIP] by Hand ✍️ The CLIP (Contrastive Language–Image Pre-training) model, a groundbreaking work by OpenAI, redefines the intersection of computer vision and natural language processing. It is the basis of all the multi-modal foundation models we see today. How does CLIP work? Goal: 🟨 Learn a shared embedding space for text and image [1] Given ↳ A mini batch of 3 text-image pairs ↳ OpenAI used 400 million text-image pairs to train its original CLIP model. Process 1st pair: "big table" [2] 🟪 Text → 2 Vectors (3D) ↳ Look up word embedding vectors using word2vec. [3] 🟩 Image → 2 Vectors (4D) ↳ Divide the image into two patches. ↳ Flatten each patch [4] Process other pairs ↳ Repeat [2]-[3] [5] 🟪 Text Encoder & 🟩 Image Encoder ↳ Encode input vectors into feature vectors ↳ Here, both encoders are simple one layer perceptron (linear + ReLU) ↳ In practice, the encoders are usually transformer models. [6] 🟪 🟩 Mean Pooling: 2 → 1 vector ↳ Average 2 feature vectors into a single vector by averaging across the columns ↳ The goal is to have one vector to represent each image or text [7] 🟪 🟩 -> 🟨 Projection ↳ Note that the text and image feature vectors from the encoders have different dimensions (3D vs. 4D). ↳ Use a linear layer to project image and text vectors to a 2D shared embedding space. 🏋️ Contrastive Pre-training 🏋️ [8] Prepare for MatMul ↳ Copy text vectors (T1,T2,T3) ↳ Copy the transpose of image vectors (I1,I2,I3) ↳ They are all in the 2D shared embedding space. [9] 🟦 MatMul ↳ Multiply T and I matrices. ↳ This is equivalent to taking dot product between every pair of image and text vectors. ↳ The purpose is to use dot product to estimate the similarity between a pair of image-text. [10] 🟦 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [11] 🟦 Softmax: ∑ ↳ Sum each row for 🟩 image→🟪 text ↳ Sum each column for 🟪 text→ 🟩 image [12] 🟦 Softmax: 1 / sum ↳ Divide each element by the column sum to obtain a similarity matrix for 🟪 text→🟩 image ↳ Divide each element by the row sum to obtain a similarity matrix for 🟩 image→🟪 text [13] 🟥 Loss Gradients ↳ The "Targets" for the similarity matrices are Identity Matrices. ↳ Why? If I and T come from the same pair (i=j), we want the highest value, which is 1, and 0 otherwise. ↳ Apply the simple equation of [Similarity - Target] to compute gradients of for both directions. ↳ Why so simple? Because when Softmax and Cross-Entropy Loss are used together, the math magically works out that way. ↳ These gradients kick off the backpropagation process to update weights and biases of the encoders and projection layers (red borders).

Tom Yeh

67,874 просмотров • 2 лет назад

A little update for those that are remotely interested in the hair colour of some random woman on social media. Enjoy my stunning accent (sarcasm by the way)

A little update for those that are remotely interested in the hair colour of some random woman on social media. Enjoy my stunning accent (sarcasm by the way)

fecklessfox

12,062 просмотров • 10 месяцев назад

This is definitely on the fringes but I'm curious what people think about the whole Maui Fires Blue Conspiracy that claims the fires were started by space-based lasers (which tbf are 100% real) and that a certain blue colour was used by those in the know... Thoughts?

This is definitely on the fringes but I'm curious what people think about the whole Maui Fires Blue Conspiracy that claims the fires were started by space-based lasers (which tbf are 100% real) and that a certain blue colour was used by those in the know... Thoughts?

Jay Anderson

51,129 просмотров • 2 лет назад

A gentle pace of life, just 5 years after the war. Visiting the village store for an ice cream, walking the dogs, and fishing by the river. A beautiful colour film of England in 1950.

A gentle pace of life, just 5 years after the war. Visiting the village store for an ice cream, walking the dogs, and fishing by the river. A beautiful colour film of England in 1950.

Bobbie

98,235 просмотров • 4 месяцев назад

History made. 🤸 #OnThisDay, a year ago at #Paris2024, Carlos Yulo made his country proud by winning the first medal of any colour for the Philippines in gymnastics! #Olympics | World Gymnastics

History made. 🤸 #OnThisDay, a year ago at #Paris2024, Carlos Yulo made his country proud by winning the first medal of any colour for the Philippines in gymnastics! #Olympics | World Gymnastics

The Olympic Games

157,495 просмотров • 1 год назад

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS Contributions: • LangSplatV2 achieves real-time performance with 476.2 FPS for high-dimensional feature splatting and 384.6 FPS for 3D open-vocabulary text querying. • Delivers a 42× speedup and 47× boost in performance compared to LangSplat. • Improves query accuracy while drastically reducing inference time. • Replaces the heavyweight decoder in LangSplat with a sparse coefficient field, removing the main performance bottleneck. • Introduces a CUDA-optimized sparse coefficient splatting method, enabling fast and high-quality rendering of high-dimensional features. • Enables scalable 3D language interaction in complex scenes, opening up real-time applications previously not possible with LangSplat.

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS Contributions: • LangSplatV2 achieves real-time performance with 476.2 FPS for high-dimensional feature splatting and 384.6 FPS for 3D open-vocabulary text querying. • Delivers a 42× speedup and 47× boost in performance compared to LangSplat. • Improves query accuracy while drastically reducing inference time. • Replaces the heavyweight decoder in LangSplat with a sparse coefficient field, removing the main performance bottleneck. • Introduces a CUDA-optimized sparse coefficient splatting method, enabling fast and high-quality rendering of high-dimensional features. • Enables scalable 3D language interaction in complex scenes, opening up real-time applications previously not possible with LangSplat.

MrNeRF

14,261 просмотров • 1 год назад

CLIP by hand ✍️ ~ 13 steps walkthrough below CLIP, Contrastive Language-Image Pre-training, is OpenAI's answer to a question that sounds impossible: how do you put a sentence and a picture in the same space? CLIP shipped when OpenAI was still open, and those embeddings were shared far and wide. Almost every multimodal model you use today descends from them. How does it work? Goal: learn one shared embedding space for text and images. = 1. Given = A mini batch of three text-image pairs. OpenAI trained the original on 400 million. = 2. Text to vectors = Let us look up each word with word2vec. = 3. Image to vectors = We cut each image into two patches and flatten them. Now text and pixels are both just numbers. = 4. The other pairs = Repeat steps 2 and 3 for the rest of the batch. = 5. Encode = Let us push both sides through their encoders, a linear layer and a ReLU. In practice these are transformers, but the shape of the operation is the same. = 6. Mean pooling = We average across the columns, so each image and each sentence collapses to a single vector. = 7. Projection = The text vectors are 3D and the image vectors are 4D, so they cannot be compared at all. A linear layer projects both to 2D. That 2D space is the shared embedding space, and getting here is the whole point of the model. = 8. Prepare for matmul = Let us copy the text vectors down and the transposed image vectors across. = 9. MatMul = We multiply, which takes the dot product of every text vector with every image vector. Each cell is one estimate of how well a sentence matches a picture. = 10. Softmax, e to the power = Raise e to each cell. To keep it hand sized we approximate e with 3. = 11. Softmax, sum = Sum each row for image to text, each column for text to image. = 12. Softmax, normalize = Divide, and out come two similarity matrices, one per direction. = 13. Loss gradients = The targets are identity matrices: a pair that belongs together should score 1, every other cell 0. Subtract the target from the similarity and you have the gradients, in both directions. The takeaway: pairing a picture with a sentence comes down to a single dot product. Everything before step 9 is the work of getting them into one shared space, so that the dot product finally means something. 💾 Save this post!

CLIP by hand ✍️ ~ 13 steps walkthrough below CLIP, Contrastive Language-Image Pre-training, is OpenAI's answer to a question that sounds impossible: how do you put a sentence and a picture in the same space? CLIP shipped when OpenAI was still open, and those embeddings were shared far and wide. Almost every multimodal model you use today descends from them. How does it work? Goal: learn one shared embedding space for text and images. = 1. Given = A mini batch of three text-image pairs. OpenAI trained the original on 400 million. = 2. Text to vectors = Let us look up each word with word2vec. = 3. Image to vectors = We cut each image into two patches and flatten them. Now text and pixels are both just numbers. = 4. The other pairs = Repeat steps 2 and 3 for the rest of the batch. = 5. Encode = Let us push both sides through their encoders, a linear layer and a ReLU. In practice these are transformers, but the shape of the operation is the same. = 6. Mean pooling = We average across the columns, so each image and each sentence collapses to a single vector. = 7. Projection = The text vectors are 3D and the image vectors are 4D, so they cannot be compared at all. A linear layer projects both to 2D. That 2D space is the shared embedding space, and getting here is the whole point of the model. = 8. Prepare for matmul = Let us copy the text vectors down and the transposed image vectors across. = 9. MatMul = We multiply, which takes the dot product of every text vector with every image vector. Each cell is one estimate of how well a sentence matches a picture. = 10. Softmax, e to the power = Raise e to each cell. To keep it hand sized we approximate e with 3. = 11. Softmax, sum = Sum each row for image to text, each column for text to image. = 12. Softmax, normalize = Divide, and out come two similarity matrices, one per direction. = 13. Loss gradients = The targets are identity matrices: a pair that belongs together should score 1, every other cell 0. Subtract the target from the similarity and you have the gradients, in both directions. The takeaway: pairing a picture with a sentence comes down to a single dot product. Everything before step 9 is the work of getting them into one shared space, so that the dot product finally means something. 💾 Save this post!

Tom Yeh

20,750 просмотров • 29 дней назад

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

MTS

11,641 просмотров • 3 месяцев назад

For 3,000 years, only the rich wore colour. Red was a beetle crushed by the thousand. Blue was a plant rotted in urine. Purple was a sea snail, and you needed 12,000 of them for the hem of one robe. Colour was not a taste. It was a rank. Then at Easter 1856, an 18 year old in Shadwell was trying to make malaria medicine out of gasworks sludge. He failed. He went to wash out the flask. And it came out purple. The colour emperors killed for... In a sink in the East End. The reason it worked is the part nobody believes. He was 18. He patented it that August, walked out of college, borrowed his father's money and built a factory. Within 2 years Britain had gone purple, the price collapsed, and a servant could wear a colour an empress had worn. Look at what you are wearing. Nobody dived for it. Nobody counted shells for it. Because a boy in Shadwell got it wrong. And instead of washing his mistake away, he gave the world colour. That spirit was handed down. It is still in you. Help us hand it to the next generation. Everything we make is free. It stays that way because of people like you: 🙏 Be part of us. Be Proud Of Us. 🇬🇧

For 3,000 years, only the rich wore colour. Red was a beetle crushed by the thousand. Blue was a plant rotted in urine. Purple was a sea snail, and you needed 12,000 of them for the hem of one robe. Colour was not a taste. It was a rank. Then at Easter 1856, an 18 year old in Shadwell was trying to make malaria medicine out of gasworks sludge. He failed. He went to wash out the flask. And it came out purple. The colour emperors killed for... In a sink in the East End. The reason it worked is the part nobody believes. He was 18. He patented it that August, walked out of college, borrowed his father's money and built a factory. Within 2 years Britain had gone purple, the price collapsed, and a servant could wear a colour an empress had worn. Look at what you are wearing. Nobody dived for it. Nobody counted shells for it. Because a boy in Shadwell got it wrong. And instead of washing his mistake away, he gave the world colour. That spirit was handed down. It is still in you. Help us hand it to the next generation. Everything we make is free. It stays that way because of people like you: 🙏 Be part of us. Be Proud Of Us. 🇬🇧

Proudofus.uk

306,631 просмотров • 3 дней назад

Footage from the Thomas Francis Meagher 178th Anniversary Tricolour Celebration in Waterford earlier today. On the 7th of March 1848, Thomas Francis Meagher flew a Tricolour flag at the Wolf Tone Club 33 The Mall, Waterford City, where it flew continuously for eight days and nights before being removed by the authorities. The Tricolour was presented as a gift in 1848 to Thomas Francis Meagher from a small group of French women sympathetic to the Irish cause was intended to symbolise the inclusion and hoped-for union between Roman Catholics (symbolised by the green colour) and Protestants (symbolised by the orange colour).

Footage from the Thomas Francis Meagher 178th Anniversary Tricolour Celebration in Waterford earlier today. On the 7th of March 1848, Thomas Francis Meagher flew a Tricolour flag at the Wolf Tone Club 33 The Mall, Waterford City, where it flew continuously for eight days and nights before being removed by the authorities. The Tricolour was presented as a gift in 1848 to Thomas Francis Meagher from a small group of French women sympathetic to the Irish cause was intended to symbolise the inclusion and hoped-for union between Roman Catholics (symbolised by the green colour) and Protestants (symbolised by the orange colour).

MichaeloKeeffe

18,702 просмотров • 5 месяцев назад

Colour films are incredibly rare in the 1920s, which makes this 26-part travelogue of the UK truly exceptional. Filmed in colour in 1924 by Claude Friese-Greene using his father's own bespoke colour film process, it utilised an ingenious camera with red and green spinning filters. The full colour travelogue runs for 180 minutes. The pioneering film tours the UK just 5 years after the end of WWI. In this preview, it visits Aberdeen, Liverpool, Cardiff, Stirling and London amongst others. I've edited this little trailer for you using the jaunty title music from the 'Jeeves & Wooster' TV series. A section of the travelogue (running 64 minutes) is available on a DVD entitled "The Open Road", restored by the BFI. (Claude Friese-Greene's famous grandson is the English musician, songwriter, and record producer Tim Friese-Greene, best known the new-wave/synth-pop band Talk Talk)

Colour films are incredibly rare in the 1920s, which makes this 26-part travelogue of the UK truly exceptional. Filmed in colour in 1924 by Claude Friese-Greene using his father's own bespoke colour film process, it utilised an ingenious camera with red and green spinning filters. The full colour travelogue runs for 180 minutes. The pioneering film tours the UK just 5 years after the end of WWI. In this preview, it visits Aberdeen, Liverpool, Cardiff, Stirling and London amongst others. I've edited this little trailer for you using the jaunty title music from the 'Jeeves & Wooster' TV series. A section of the travelogue (running 64 minutes) is available on a DVD entitled "The Open Road", restored by the BFI. (Claude Friese-Greene's famous grandson is the English musician, songwriter, and record producer Tim Friese-Greene, best known the new-wave/synth-pop band Talk Talk)

BabelColour

90,005 просмотров • 1 месяц назад