SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.00519 · ICCV · 2021

Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images

Alan Yuille, Cihang Xie, Yixiao Zhang, Benjamin Van Durme, Elias Stengel-Eskin, Quan Tran, Zhuowan Li

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The cylinder that is the same size as the metallic sphere is what color? A: Purple Prog: select(sphere) filter(metallic) samesize() filter(cylinder) querycolor() Q: What does the little boy in front of the table hold? A: Toothbrush Prog: select(boy) filter(little) relate_s(table, front) query_rel_o(hold) (a) Long-tail Concept Distribution of Real Dataset Synthetic CLEVR dataset Real GQA dataset (b) Unequal Importance of Reasoning Steps Figure 1: Statistics and examples from the synthetic CLEVR dataset and the real GQA dataset. Compared to the synthetic dataset, VQA on real data needs to deal with long-tail concept distribution and uneven importance of reasoning steps.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2110.00519")
get_code_for_paper("2110.00519")
have("2110.00519")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2110.00519.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2110.00519.svg)](https://syntology.ai/paper/2110.00519)

Connect an agent — have() is free.