IFT 6765 - Links between Computer Vision and Language
Guidelines for writing paper reviews
(Guidelines credits: Vision and Language course taught by Devi Parikh at Georgia Tech)
Due: 5.00 pm on the day before class. Late reviews will not be accepted. The two reviews with lowest scores will be dropped at the end of class. You need not submit paper reviews during the classes where you are presenting papers or leading discussions on papers. Note that you still need to submit a review for the days where you are presenting project related updates.
Submit your review on Gradescope (access code to signup on Gradescope has been shared on Studium).
Length <=1 page
11 pt Times New Roman, 1 inch margins
The review should be organized in sections as outlined below.
Summary:
What is this paper about?
What is the main contribution?
Describe the main approach & results. Just facts, no opinions yet.
Strengths:
Is there a new theoretical insight?
Or a significant empirical advance? Did they solve a standing open problem?
Or a good formulation for a new problem?
Or a faster/better solution for an existing problem?
Any good practical outcome (code, algorithm, etc)?
Are the experiments well executed?
Useful for the community in general?
Weaknesses:
What can be done better?
Any missing baselines? Missing datasets?
Any odd design choices in the algorithm not explained well? Quality of writing?
Is there sufficient novelty in what they propose? Minor variation of previous work?
Why should anyone care? Is the problem interesting and significant?
Reflections:
How does this relate to other papers we have read?
What are the next research directions in this line of work?
What (directly or indirectly related) new ideas did this paper give you? What would you be curious to try?
Most interesting thought: From your review, pull out what you believe is your most interesting thought about the paper and write it at the end in a separate section. Be very brief.
Tips on
How to write a review (this is a bit specific to systems papers, but hopefully the high-level messages are useful).
Examples of good reviews (please note that the examples may not match the recommended format exactly): Example1, Example2, Example3.