PReFIL combines LSTM question embeddings with two levels of convolutional features via 1x1 convolutions and recurrent spatial aggregation, setting new state-of-the-art accuracy on FigureQA and DVQA.
Challenges and Prospects in Vision and Language Research
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing tests, recent studies have demonstrated state-of-the-art systems are achieving good performance through flaws in datasets and evaluation procedures. We review the current state of affairs and outline a path forward.
fields
cs.CV 1years
2019 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Answering Questions about Data Visualizations using Efficient Bimodal Fusion
PReFIL combines LSTM question embeddings with two levels of convolutional features via 1x1 convolutions and recurrent spatial aggregation, setting new state-of-the-art accuracy on FigureQA and DVQA.