• Grad-CAM

  • Referenced in 23 articles [sw35098]
  • shelf image classification, captioning, and visual question answering (VQA) models, including ResNet-based architectures ... context of image classification models, our visualizations (a) lend insights into their failure modes...
  • CLEVR

  • Referenced in 7 articles [sw42503]
  • systems that can reason and answer questions about visual data, we need diagnostic tests ... discover shortcomings. Existing benchmarks for visual question answering can help, but have strong biases that ... models can exploit to correctly answer questions without reasoning. They also conflate multiple sources ... diagnostic dataset that tests a range of visual reasoning abilities. It contains minimal biases...
  • CLEVR dataset

  • Referenced in 6 articles [sw35085]
  • systems that can reason and answer questions about visual data, we need diagnostic tests ... discover shortcomings. Existing benchmarks for visual question answering can help, but have strong biases that ... models can exploit to correctly answer questions without reasoning. They also conflate multiple sources ... diagnostic dataset that tests a range of visual reasoning abilities. It contains minimal biases...
  • VQA

  • Referenced in 7 articles [sw36506]
  • Visual Question Answering. VQA is a new dataset containing open-ended questions about images. These...
  • Visual Genome

  • Referenced in 6 articles [sw32601]
  • Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. Despite progress in perceptual ... tasks such as image description and question answering. Cognition is core to tasks that involve ... just recognizing, but reasoning about our visual world. However, models used to tackle the rich ... noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations...
  • ViLBERT

  • Referenced in 2 articles [sw42498]
  • multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring expressions...
  • RUBi

  • Referenced in 1 article [sw42505]
  • RUBi: Reducing Unimodal Biases in Visual Question Answering. Visual Question Answering (VQA) is the task...
  • UNITER

  • Referenced in 1 article [sw42622]
  • tasks (over nine datasets), including Visual Question Answering, Image-Text Retrieval, Referring Expression Comprehension, Visual...
  • LXMERT

  • Referenced in 1 article [sw42494]
  • language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment ... classification), cross-modality matching, and image question answering. These tasks help in learning both intra ... results on two visual question answering datasets (i.e., VQA and GQA). We also show ... model by adapting it to a challenging visual-reasoning task, NLVR2, and improve the previous...
  • VisKE

  • Referenced in 1 article [sw36517]
  • VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases ... problem of visual verification of relation phrases and developed a Visual Knowledge Extraction system called ... recall, but also augment open-domain question-answer reasoning...
  • AI2-THOR

  • Referenced in 1 article [sw38436]
  • imitation learning, learning by interaction, planning, visual question answering, unsupervised representation learning, object detection ... THOR is to facilitate building visually intelligent models and push the research forward in this...
  • VL-InterpreT

  • Referenced in 1 article [sw42504]
  • Commonsense Reasoning (VCR) and WebQA, two visual question answering benchmarks. Furthermore, we also present...
  • MDETR

  • Referenced in 1 article [sw42502]
  • approach can be easily extended for visual question answering, achieving competitive performance...
  • MetaVis

  • Referenced in 1 article [sw29859]
  • Actionable Visualization. Software visualization can be very useful for answering complex questions that arise ... identify a suitable visualization technique to answer their particular development question, and to (2) implement...
  • FiLM

  • Referenced in 3 articles [sw35859]
  • highly effective for visual reasoning - answering image-related questions which require a multi-step, high ... explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve...
  • WhyLine

  • Referenced in 3 articles [sw38508]
  • even why didn’t questions directly about their program’s runtime failures. The Whyline ... visualizes answers in terms of runtime events directly relevant to a programmer’s question. Comparisons...
  • GANDissect

  • Referenced in 3 articles [sw42344]
  • understood. How does a GAN represent our visual world internally? What causes the artifacts ... architectural choices affect GAN learning? Answering such questions could enable us to develop new insights ... work, we present an analytic framework to visualize and understand GANs at the unit-, object...
  • Turf.js

  • Referenced in 1 article [sw29753]
  • transform data to visualize it in new ways and answer advanced questions. This guide provides...
  • MathEdit

  • Referenced in 2 articles [sw08717]
  • MathEdit is an interactive visual mathematical expression editor. Running in a Web browser, it allows ... easily enter mathematical expressions as answers to questions in mathematics lesson pages for example...
  • SYNTHIA Dataset

  • Referenced in 8 articles [sw35060]
  • advent of reliable classifiers to perform such visual tasks. However, DCNNs require learning of many ... pixel-level annotations. Then, we address the question of how useful such data ... using a DCNN paradigm. In order to answer this question we have generated a synthetic...