TallyQA: Answering Complex Counting Questions

29 Oct 2018 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... (read more)

PDF Abstract

Datasets


Introduced in the Paper:

TallyQA

Mentioned in the Paper:

Visual Question Answering CLEVR COCO-QA TDIUC
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Visual Question Answering 100 sleep nights of 8 caregivers TallyQA 14 gestures accuracy 10.0 # 1
Visual Question Answering HowmanyQA RCN (Ours) Accuracy 60.3 # 1
Visual Question Answering TallyQA RCN (Ours) Accuracy 71.8 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet