Location
CN
Badges
Activity
Ratings Progression
Challenge Categories
Challenges Entered
Completed
Amazon Search
Shopping Session Dataset
Latest submissions
AIcrowd
Intelligent Environments Lab
Using AI For Building’s Energy Management
Latest submissions
IGLU Team
Interactive embodied agents for Human-AI collaboration
Latest submissions
| Participant | Rating |
|---|
| Participant | Rating |
|---|
ESCI Challenge for Improving Product Search
📝 Announcing Community Contribution Prizes 🚁🥽
Almost 2 years agoIn the " ESCI Challenge for Improving Product Search", one of my post got 3.7k views (this was the most viewed post in this contest) and another of my post got 30 likes (this is the most liked post among unofficial posts). Will this support me with community prizes?
[Uni] Our competition experience
Almost 2 years agoI’m yrqUni from the Uni team, and in our solution, we only used the training set of task2, which should be amazing.
Can we crawl the pictures of query and product as information?
Almost 2 years agoThis is very critical and urgent for us, please give the official answer as soon as possible! ! !
:rotating_light: Emergency! ! ! We found that git mentioned the conference which caused the automation to fail, and no errors were displayed in the log
Almost 2 years agoWe found that git mentioned the assembly which caused the automation to fail, and no errors were shown in the log. What is the size limit for git commits? I didn’t find any information in the official statement and the official reply is too slow. We’re concerned about not being able to submit submissions on time! ! !
Code submit questions :boom:
Almost 2 years agoWe would like to know two. The first is whether the submitted code has restrictions on the model, such as the limit on the number of single model parameters or the total number of models; the second is when our code submission will be opened, and in what way should we to submit.
Regarding the data leakage of the public list of Task2 and 3
Almost 2 years agoThe current public rankings of Task2 and 3 confuse me. Since 30% of the data in the public rankings test set of Task2 and 3 appears in the training set of Task1, the scores of the current public rankings of Task2 and 3 are relatively high, which makes I can’t judge the actual ranking level. Can the official provide a “Clean” score column achieved by sampling for Task2 and 3 like Task1? I’m sorry to ask such a question, but I think it’s important to me.
📢 Important Message for the Participants regarding Task-1 📢
Almost 2 years agoHello, I’m the yrqUni(yrqUni@gmail.com) who sent the “Extremely serious data breach issue report!!!” email to the organizer in the first place. As I wrote in the email, the data breach has also severely affected task2 and task3, and we also hope that task2 and task3 will provide a valid “clean” version (no leak version) ranking. 
讨论组 Experience exchange discussion group
Almost 2 years agoUnofficial experience exchange discussion group
非官方经验交流讨论群
微信：
Telegram：
Can we crawl the pictures of query and product as information?
Almost 2 years agoCan we crawl the pictures of query and product as information?
When to release the baseline
About 2 years agoWhen will the baseline code be released? where can i find it?
🚨🚨🚨 Dataset update - `v0.2` released!
About 2 years agoExcuse me, relative to v0.1, does v0.2 update only Task1’s dataset without making changes to other task datasets?
👋 Welcome to Amazon KDD Cup '22!
About 2 years agoWelcome to AIcrowd Forum — thanks for contributing!
ALL IN
【Solution ZhichunRoad】 5th@task1, 7th@task2 and 8th@task3
Over 1 year agoNice work! But in our experiment. pre-train with MLM task is useless. Bro, have you done any vigorous ablation experiments on this?