• Grad-CAM

  • Referenced in 23 articles [sw35098]
  • image classification, captioning, and visual question answering (VQA) models, including ResNet-based architectures ... identifying dataset bias. For captioning and VQA, we show that even non-attention based models...
  • VQA

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

  • Referenced in 3 articles [sw26530]
  • QADailyMail, CBT, bAbI Dialog, Ubuntu, OpenSubtitles and VQA. Several models are integrated, including neural models...
  • RUBi

  • Referenced in 1 article [sw42505]
  • Visual Question Answering. Visual Question Answering (VQA) is the task of answering questions about ... image. Some VQA models often exploit unimodal biases to provide the correct answer without using ... learning strategy to reduce biases in any VQA model. It reduces the importance ... image. It implicitly forces the VQA model to use the two input modalities instead...
  • VisualBERT

  • Referenced in 2 articles [sw42500]
  • four vision-and-language tasks including VQA, VCR, NLVR2, and Flickr30K show that VisualBERT outperforms...
  • LXMERT

  • Referenced in 1 article [sw42494]
  • visual question answering datasets (i.e., VQA and GQA). We also show the generalizability...
  • COCO

  • Referenced in 60 articles [sw06390]
  • Continuation Core and Toolboxes (COCO). Toolboxes for parameter...
  • ConceptNet

  • Referenced in 31 articles [sw10660]
  • ConceptNet: a practical commonsense reasoning toolkit. ConceptNet is...
  • Caffe

  • Referenced in 79 articles [sw17850]
  • Caffe is a deep learning framework made with...
  • ImageNet

  • Referenced in 695 articles [sw21105]
  • ImageNet is an image dataset organized according to...
  • CIDEr

  • Referenced in 5 articles [sw26599]
  • CIDEr: Consensus-based Image Description Evaluation. Automatically describing...
  • NEIL

  • Referenced in 2 articles [sw36514]
  • NEIL: Extracting Visual Knowledge from Web Data. We...
  • Midge

  • Referenced in 1 article [sw36515]
  • Midge: generating image descriptions from computer vision detections...
  • MCTest

  • Referenced in 2 articles [sw36516]
  • MCTest: A Challenge Dataset for the Open-Domain...
  • VisKE

  • Referenced in 1 article [sw36517]
  • VisKE: Visual knowledge extraction and question answering by...