List

How to invent the nXet great thing when you meet something, X, great?

創意如何延伸發想?
當看到某樣令人讚嘆的成果,那下一個創意在那裡?

我們的工作受惠於近年來形形色色攝影裝置的快速增長、大量的影音視訊資料,所以各種偵測、分析、搜尋、探勘的機器智慧能力應運而生。但是創意在那裡?

幾年前聽過MIT教授Ramesh Raskar的 “Idea Hexagon” (創意六角型)。發現跟自己在系統性創意發想的步驟十分類似。

摘要如下,希望對大家有幫助,如果有更好的想法,也希望不吝分享。

The “Idea Hexagon” by Prof. Ramesh Raskar, MIT Media Lab, did help me a lot in the past years. I believe it will be a big help for many friends who strive for innovation both in products or researches.

X = Idea you just heard

What’s the neXt?

  1. X^d: Extend it to next (or some other) dimension
  2. X + Y: Fusion of the dissimilar
  3. Do exactly the opposite
  4. Given a cool solution/technique/opportunity, then find other problems
  5. Given a problem, find other solutions
  6. adjective + X: Pick your adjective; making it faster, better, cheaper, etc.

For examples, my first representative work is “image reranking“, which yields more than 500 citations in Google scholar. It’s actually the “X^d” case as the ranking concept is originally from the text domain and I am the first to extend it (but solving certain constraints) in imager ranking.

For (4), we observed the utilities of facial attribute detection, so we enable them for a brand new solution in consume photo search.

 

 

  Posts

1 2 3 6
June 7th, 2018

First Place (#1) in Disguised Face Recognition in CVPR 2018

January 6th, 2019

意想不到的科技部「AI投資潛力獎第一名」

December 16th, 2018

Keep Recruiting for Machine Learning Research Partners for Numerous Visual Sensors

December 16th, 2018

FutureTech Demo and Breakthrough Award (未來科技突破獎)

October 12th, 2018

結合虛與實的試鞋生成網路 (Virtual Try-On Shoe with Generative Neural Networks)

我們都有這樣的困擾,在電子購物的時候,看到一雙好看的鞋子,想買。但是卻又拿不定主意自己穿起來好看嗎?或是搭配某件褲子適合嗎?怎麼讓網路虛擬商城的鞋子,可以有效試在自己的腳上呢? 這個工作的挑戰在於如何使用單張鞋子商品的照片,很自然的合成在使用者的腳上,而且腳可能會有各種姿勢、角度。如何客服這個問題? 很高興大學部專題生(EE) 周晁德 完成了這個 PIVTONS 的虛擬鞋子試穿生成網路,試著解決這個困擾大家很久的問題。 這個有趣的工作也將於十二月初,在澳洲珀斯舉辦 Asian Conference on Computer Vision (ACCV) 2018 以大會演說 (Oral) 的方式跟大家分享這個工作。接下來全新的測試資料集將會公開讓大家使用,如果可以的話,我們也將試試看將整個試穿生成系統上線,讓大家體驗虛擬試鞋的樂趣 — 可以多試穿,多省錢。 我們鼓勵high-risk的研究工作。令人慶幸的是,這工作的發想、資料收集都是專題生獨立完成。當然在過程當中遇到很多GAN生成的問題,網路設計、訓練的問題,幾乎放棄了,還好團隊成員一起想辦法解決,關關難過,關關過(甚至免費擔任model),讓這個兼具技術深度以及商業價值的系統,可以順利完成。 我們也一直努力,讓智能生成(或是辨識)系統,賦予更有意義的應用 […]

September 13th, 2018

Finalist (Top 3) in 2018 IEEE Signal Processing Society Video and Image Processing (VIP) Cup

July 29th, 2018

信手拈來的3D模型搜尋 (Cross-View and Cross-Domain 3D Model Search)

July 27th, 2018

低解析人臉辨識跟解析度放大 (Very Low-Resolution Face Hallucination and Recognition)

June 18th, 2018

Winning Third Place in CVPR 2018 Video Recognition Challenge — Moments in Time

June 13th, 2018

[Video Report] National Investment for the GPU Supercomputer?

June 9th, 2018

Amazing Crowd Size and Positive Feedbacks in the Deep Learning Lecture for GTC 2018 Taipei