Monthly Archives: August 2021

Image annotation and 2-modality image retrieval

Image annotation is to build a ML model to auto annotate image using predefined tag set. It is a multiple label problem. In 2006, I start working image annotation and content understanding. Also attend benchmark evaluation on image retrieval (CLEF & TREC-VIDEO). Refer to https://aisengtech.com/project#image-tag.

Music summary

Music summary is to extract a short clip from music recording to represent music content, which is used to engage consumer to buy music recording. A simple way is to use the beginning of audio. But it may not characterize the most engaging part of the music. I developed a music structure analysis and repeated pattern identification algorithm. The repeated pattern or segment may reflect the most engaging content in the recording, which is used as music summary. Refer to https://aisengtech.com/project#music-summary.

Learn a metric oriented classifier

Objective function is the mathematical formulation of how to estimate classifier parameters. The classical objective function is derived from maximal log-likelihood function on training samples for the proposed classifier. Classifier parameters are estimated by solving the objective function. But log-likelihood is not directly related to performance metric, e.g. training on likelihood, and preferred evaluation metric maybe F1, accuracy or ranking. This criteria gap between training and evaluating causes the classifier trained on log-likelihood is not optimal for F1 , classification error or ranking. This is the intention of our work on MFoM based classifier learning. Updated the work on https://aisengtech.com/project#mfom. Hereafter MFoM, there are many research papers on learning classifier for specified metric in research community, in which learn-to-rank is most famous, and learn-to-rank is now a core module for modern search engine.

家庭版- 辣子鸡丁

辣子鸡丁已经成了家里周六的必备菜。每到周末,问儿子周六想吃啥,总要辣子鸡丁,换换菜目也不要。外面饭店里吃辣子鸡丁,是在红红的 辣椒丛中,翻捡着一粒粒的肌肉块,还没过瘾,肉没了,只能望椒叹口水。

家庭做辣子鸡丁,尽可以奢侈点。肉食动物的我们,要的的是麻辣的味道,不是一堆堆的辣椒。家里做辣子鸡,主要工序在腌制和过油炸鸡丁。下面介绍家庭版辣子鸡的制作过程。

  1. 材料准备:
    • 肌腿肉去骨切小块:在坡县巴刹购买鸡腿肉,可以要求去骨。然后冲洗去除多余的血水和脏污,控干水份,切小块,放入盐、白胡椒粉、五香粉、料酒、孜然粉、糖、酱清,一切适量即可。用手抓匀,然后加入干玉米粉,拌匀。玉米粉锁住了肉的水份,炸后的鸡块会多汁,柔软。最后,加入油,抓匀,油一方面锁住水份,另一方面,肌肉块不会因为玉米粉的加入最后成为一坨,到油炸的时候分不开。
    • 腌制30分钟或更长,都OK。
  2. 油炸:
    • 第一次炸:锅里放适量油,加热,等插入筷子,看到筷子周围起泡,放入鸡肉块,等稍微定型,不断翻动肌肉,使得炸的更均匀,等颜色金黄,就差不多了。捞起控油。如果油烟过大,炸的颜色太深,说明油温过大,减小火。
    • 复炸:等所有的都炸完,还没有结束,还需要复炸一次,保证更焦脆。起大火,油温升起,倒入肌肉块,快速翻转,3,4秒后快速捞起控油。一定要高油温,快速复炸。时间一长就炸过了。
  3. 炒制:
    • 准备干小米辣,适量,我一般2个鸡腿放3个干辣椒。新鲜小米辣1个。切段,去籽。麻花椒和青花椒可以多些,香叶,桂皮,八角适量就行。葱姜切碎,蒜头几个切碎。
    • 起油锅,如果是刚才炸鸡肉的油锅,仅放一点点油,譬如一小勺就行。放入除葱姜蒜的外其他料,小火慢慢炒出味道,等空气中弥漫了麻辣味(呛死了),放入葱姜蒜炒出味道,接着放入炸好的肌肉块,中小火炒匀,让麻辣的味道进入肌肉,几分钟后放入熟芝麻,炒匀。辣子鸡就大功告成了。

Audio/music search

In around 2013, music search is becoming hot application in internet industry with the increasing coverage of mobile phone. Its intention is to provide music / song search experience using a music clip recorded by mobile phone anywhere anytime. Its challenges are robust (diverse noise e.g. town hall, road, audio edit, pitch shift) & compact audio fingerprint extraction and quick response to support real-time search. Fortunately I developed audio landmark binary feature as fingerprint and inverted document index framework for audio search (C++). Interests to learn more, please refer to https://aisengtech.com/project#speech-recognition

简单即美味 – 酸辣萝卜皮

在坡县一年四季炎热的夏天,酸辣可口的凉拌菜开开胃。坡县常见的白萝卜,本地人一般用来顿萝卜排骨汤。我们家喜欢生吃,买到好的白萝卜,皮切除,萝卜心切条,冰箱冰凉,微辣,爽脆。

萝卜皮不要丢掉,切丝,放糖盐,喜欢吃辣,放几个小米辣,用手抓挤拌匀,腌制30分钟左右。然后捞出,双手挤出水分,几乎变成干萝卜条。

后续两种处理。简单点,放些白醋,切碎的小米辣,常常味道,如果不够,在加些糖盐。然后放冰箱保存即可。复杂点,切些干小米辣、香葱,萝卜条放些芝麻,做些热的辣葱油,一浇,拌匀,冰箱保存即可。

原本辛辣难吃的萝卜条,成为夏季开胃凉菜。