اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدVision Skills Needed to Answer Visual Questions
139
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The task of answering questions about images has garnered attention as a practical service for assisting populations with visual impairments as well as a visual Turing test for the artificial intelligence community. Our first aim is to identify the common vision skills needed for both scenarios. To do so, we analyze the need for four vision skills---object recognition, text recognition, color recognition, and counting---on over 27,000 visual questions from two datasets representing both scenarios. We next quantify the difficulty of these skills for both humans and computers on both datasets. Finally, we propose a novel task of predicting what vision skills are needed to answer a question about an image. Our results reveal (mis)matches between aims of real users of such services and the focus of the AI community. We conclude with a discussion about future directions for addressing the visual question answering task.
قيم البحث
اقرأ أيضاً
Visual attention in Visual Question Answering (VQA) targets at locating the right image regions regarding the answer prediction. However, recent studies have pointed out that the highlighted image regions from the visual attention are often irrelevan
t to the given question and answer, leading to model confusion for correct visual reasoning. To tackle this problem, existing methods mostly resort to aligning the visual attention weights with human attentions. Nevertheless, gathering such human data is laborious and expensive, making it burdensome to adapt well-developed models across datasets. To address this issue, in this paper, we devise a novel visual attention regularization approach, namely AttReg, for better visual grounding in VQA. Specifically, AttReg firstly identifies the image regions which are essential for question answering yet unexpectedly ignored (i.e., assigned with low attention weights) by the backbone model. And then a mask-guided learning scheme is leveraged to regularize the visual attention to focus more on these ignored key regions. The proposed method is very flexible and model-agnostic, which can be integrated into most visual attention-based VQA models and require no human attention supervision. Extensive experiments over three benchmark datasets, i.e., VQA-CP v2, VQA-CP v1, and VQA v2, have been conducted to evaluate the effectiveness of AttReg. As a by-product, when incorporating AttReg into the strong baseline LMH, our approach can achieve a new state-of-the-art accuracy of 59.92% with an absolute performance gain of 6.93% on the VQA-CP v2 benchmark dataset. In addition to the effectiveness validation, we recognize that the faithfulness of the visual attention in VQA has not been well explored in literature. In the light of this, we propose to empirically validate such property of visual attention and compare it with the prevalent gradient-based approaches.
In the task of factoid question answering over knowledge base, many questions have more than one plausible interpretation. Previous works on SimpleQuestions assume only one interpretation as the ground truth for each question, so they lack the abilit
y to answer ambiguous questions correctly. In this paper, we present a new way to utilize the dataset that takes into account the existence of ambiguous questions. Then we introduce a simple and effective model which combines local knowledge subgraph with attention mechanism. Our experimental results show that our approach achieves outstanding performance in this task.
For a variety of inter-related cultural, organizational, and political reasons, progress in climate science and the actual solution of scientific problems in this field have moved at a much slower rate than would normally be possible. Not all these f
actors are unique to climate science, but the heavy influence of politics has served to amplify the role of the other factors. Such factors as the change in the scientific paradigm from a dialectic opposition between theory and observation to an emphasis on simulation and observational programs, the inordinate growth of administration in universities and the consequent increase in importance of grant overhead, and the hierarchical nature of formal scientific organizations are cosidered. This paper will deal with the origin of the cultural changes and with specific examples of the operation and interaction of these factors. In particular, we will show how political bodies act to control scientific institutions, how scientists adjust both data and even theory to accommodate politically correct positions, and how opposition to these positions is disposed of.
Collecting supporting evidence from large corpora of text (e.g., Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA, scattered evidence pieces are required to be gathered together to sup
port the answer extraction. In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering. Specifically, the hop in this paper is defined as the combination of a hyperlink and the corresponding outbound link document. The hyperlink is encoded as the mention embedding which models the structured knowledge of how the outbound link entity is mentioned in the textual context, and the corresponding outbound link document is encoded as the document embedding representing the unstructured knowledge within it. Accordingly, we build HopRetriever which retrieves hops over Wikipedia to answer complex questions. Experiments on the HotpotQA dataset demonstrate that HopRetriever outperforms previously published evidence retrieval methods by large margins. Moreover, our approach also yields quantifiable interpretations of the evidence collection process.
Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propose to avoid manual annotation a
nd generate a large-scale training dataset for video question answering making use of automatic cross-modal supervision. We leverage a question generation transformer trained on text data and use it to generate question-answer pairs from transcribed video narrations. Given narrated videos, we then automatically generate the HowToVQA69M dataset with 69M video-question-answer triplets. To handle the open vocabulary of diverse answers in this dataset, we propose a training procedure based on a contrastive loss between a video-question multi-modal transformer and an answer transformer. We introduce the zero-shot VideoQA task and show excellent results, in particular for rare answers. Furthermore, we demonstrate our method to significantly outperform the state of the art on MSRVTT-QA, MSVD-QA, ActivityNet-QA and How2QA. Finally, for a detailed evaluation we introduce iVQA, a new VideoQA dataset with reduced language biases and high-quality redundant manual annotations. Our code, datasets and trained models are available at https://antoyang.github.io/just-ask.html.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
