How to keep track with the literature?

Getting started with research but overwhelmed by THOUSANDS of papers each year? How could one stay sane keeping track of the literature? 😱

Here are some tricks I found useful. 🧡
*Track the people, not the papers*

There are far fewer key people who are driving the field forward than the number of papers. Check out who the authors are when you read papers. Overtime you will recognize the important ones.
*Read papers with good related work*

A good related work section saves you so much time by providing a clear, organized view for prior work.

Side note: Please save others' time by writing a good related work
*Organize the papers*

Don't read papers individually. Think about how are they related (similar in some aspects, but different in others). It often helps to build a table with columns specifying ATTRIBUTES.

With this table, reading new papers becomes easy (just add more rows).
*Avoid reading the paper*

Instead of spending time reading the actual paper, find resources that are much easier to digest, e.g., a talk, a youtube video, teaser results, introductory video, or an overview figure.

Very often understanding the gist of the paper is all you need.
*Read with a purpose*

Before investing time on reading a paper, think about WHY you are reading it. Are you reading for the experimental setup, the organization, the story, the style, the method, or the visualization?

You almost never need to read a paper from top to bottom.
*Identify the trend*

Use your favorite tools to find what's hot/trendy, e.g.,
arxiv-sanity.com
paperswithcode.com
twitter.com
Hope this helps! What's your favorite methods for keeping up with the literature in a fast-pacing field?
Excellent points from the one and only @tzumaoli!

β€’ β€’ β€’

Missing some Tweet in this thread? You can try to force a refresh
γ€€

Keep Current with Jia-Bin Huang

Jia-Bin Huang Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @jbhuang0604

10 Aug
So You Think You Want to Apply for a PhD

The application cycle is coming up. How do I maximize my chance of getting admitted to my dream program? πŸ€”

Check out the thread below for resources/advices/tips!
*Casey Fiesler @cfiesler's videos on PhD applications*

EVERYTHING you need to know about PhD applications! These videos are beyond awesome! (I wish I know these when I applied!)

youtube.com/playlist?list=…
*It's all about research*

Do NOT spend too much time maximizing your GPAs (e.g., by taking easy courses) or the Greatly Ridiculous Exam (GRE) scores. Show your potential of doing good research!

Not sure if you love doing research yet? Then why are you applying?
Read 11 tweets
6 Aug
How to come up with research ideas?

Excited about starting doing research but have no clue?πŸ€·β€β™‚οΈπŸ€·πŸ»β€β™€οΈ Here are some simple methods that I found useful in identifying initial directions.

Check out the thread below πŸ‘‡
*Find a different dimension*

Just learn a cool idea from others? Think about how you could extend it to another dimension.

Ex: Text / audio / image / video / graph
*Relax assumptions*

Identify the underlying assumptions of existing work and try relaxing them to make it work in more unconstrained settings.
Read 9 tweets
29 Jul
Writing Cold Emails

Writing emails to a stranger could be daunting, but it's a great way to build connections, explore opportunities, and even advance your career.

How do we write an effective cold email?

Check out 🧡 below for some ideas.
*Content*

Your email should contain the following four elements.

β€’ Greeting: "Hello"
β€’ Introduction: "My name is Inigo Montoya."
β€’ Context/Connection: "You killed my father."
β€’ Call for action: "Prepare to die."
*Greeting*

Understand basic email etiquette. Do not use Miss / Mrs. particularly if you know the recipient has a PhD. Respect their expertise.

Source:
Read 10 tweets
27 Jul
How to make steady progress in my research?

I worked so damn hard but "IT JUST DOESN'T WORK!"😀
How can I unblock myself quickly and make good progress toward the goals?

Below I compiled a list of tips that I found useful. πŸ‘‡
*Imagine success*

Forget about all the technical difficulties for a moment. Imagine you finish your project successfully, would you find the outcome exciting?

If not, drop the project. Yep, just drop it. Free up your time to work on important problems.
*Work backward πŸ”™(1/2)*

Say your project involves three steps: A➑️B➑️C.

First, assume that you have perfect output of B and work on the step C.

Next, assume that you have perfect output A and work on the step B and so on.

In the end, you will have a fully working method.
Read 14 tweets
23 Jul
How to do research with my mentors effectively?

I get this question frequently in my open office hours. I am still learning as well but I hope sharing my βœŒπŸ’° may be helpful to some.

Key idea ➑️ **Help them help you!**

How? Check out the thread 🧡
*Frequent update*

Setting up weekly meeting with your mentors is great. But, do NOT stay silent during the week. Nothing is more frustrating to learn that the student got stuck 20 mins after the meeting last week in a meeting.

Your mentors want you to succeed! Help them do so!
*Manage meetings*

Before: send results/agenda whenever they are available. Give your mentors time to digest them.

In the meeting: progress update. Reserve the last 10 mins to discuss next steps.

After: Send a summary and an actionable plan to keep everyone on the same page.
Read 9 tweets
20 Jul
Example 1

Trajectory:
β€’ Learning LR-HR -> challenge: large patch space -> learning mixture of models -> learning 1D profile -> high-level feature

Relationship:
β€’ Contrastive concept: External vs. Internal (no learning)

Source: cv-foundation.org/openaccess/con…
Example 2

Trajectory:
β€’ Applications of vision-based methods for assessment.
β€’ Highlight the closest related work.

Relationship:
β€’ Building upon the methodology... BUT, use deep learning.

Source: Deep Paper Gestalt arxiv.org/abs/1812.08775
Example 3

Trajectory:
β€’ Video completion methods and their use for view synthesis.

Relationship:
β€’ Contrastive concept: \emph{screen space} vs. \emph{3D space}.

Source: arxiv.org/abs/2011.12950
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

:(