Papers › TallyQA: Answering Complex Counting Questions

TallyQA: Answering Complex Counting Questions

29 Oct 2018arXiv:1810.12440archive 2025-07-28

Manoj Acharya, Kushal Kafle, Christopher Kanan

Most counting questions in visual question answering (VQA) datasets are simple and require no more than object detection. Here, we study algorithms for complex counting questions that involve relationships between objects, attribute identification, reasoning, and more. To do this, we created TallyQA, the world's largest dataset for open-ended counting. We propose a new algorithm for counting that uses relation networks with region proposals. Our method lets relation networks be efficiently used with high-resolution imagery. It yields state-of-the-art results compared to baseline and recent systems on both TallyQA and the HowMany-QA benchmark.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

manoja328/tallyqacode officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeObject CountingObject DetectionQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)object-detection

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

TallyQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Counting HowMany-QA RCN Accuracy 60.3 #3 of 3 Archive leaderboard report
Object Counting HowMany-QA RCN RMSE 2.35 #3 of 3 Archive leaderboard report
Object Counting TallyQA-Complex RCN Accuracy 56.2 #5 of 6 Archive leaderboard report
Object Counting TallyQA-Complex RCN RMSE 1.43 #5 of 6 Archive leaderboard report
Object Counting TallyQA-Simple RCN Accuracy 71.8 #5 of 6 Archive leaderboard report
Object Counting TallyQA-Simple RCN RMSE 1.13 #5 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections