Simple Baseline for Visual Question Answering
نویسندگان
چکیده
We describe a very simple bag-of-words baseline for visual question answering. This baseline concatenates the word features from the question and CNN features from the image to predict the answer. When evaluated on the challenging VQA dataset [2], it shows comparable performance to many recent approaches using recurrent neural networks. To explore the strength and weakness of the trained model, we also provide an interactive web demo1, and open-source code2.
منابع مشابه
Two can play this Game: Visual Dialog with Discriminative Question Generation and Answering
Human conversation is a complex mechanism with subtle nuances. It is hence an ambitious goal to develop artificial intelligence agents that can participate fluently in a conversation. While we are still far from achieving this goal, recent progress in visual question answering, image captioning, and visual question generation shows that dialog systems may be realizable in the not too distant fu...
متن کاملShow, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering
This paper presents a new baseline for visual question answering task. Given an image and a question in natural language, our model produces accurate answers according to the content of the image. Our model, while being architecturally simple and relatively small in terms of trainable parameters, sets a new state of the art on both unbalanced and balanced VQA benchmark. On VQA 1.0 [2] open ende...
متن کاملExploring Models and Data for Image Question Answering
This work aims to address the problem of image-based question-answering (QA) with new models and datasets. In our work, we propose to use neural networks and visual semantic embeddings, without intermediate stages such as object detection and image segmentation, to predict answers to simple questions about images. Our model performs 1.8 times better than the only published results on an existin...
متن کاملRecurrent and Contextual Models for Visual Question Answering
We propose a series of recurrent and contextual neural network models for multiple choice visual question answering on the Visual7W dataset. Motivated by divergent trends in model complexities in the literature, we explore the balance between model expressiveness and simplicity by studying incrementally more complex architectures. We start with LSTM-encoding of input questions and answers; buil...
متن کاملSQuAD Question Answering Dataset: CS224N Assn 4
We solve the contextual question answering problem, which is an essential part in many automated question-answering datasets. Recently the SQuAD dataset [1] was uploaded and there were several deep learning approaches proposed to solve this. We implement a modified version of one of them, the Dynamic Coattention model as well as simple baseline.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1512.02167 شماره
صفحات -
تاریخ انتشار 2015