• Publications
  • Influence
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
TLDR
This work proposes a technique for producing ‘visual explanations’ for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent and explainable, and shows that even non-attention based models learn to localize discriminative regions of input image. Expand
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to aExpand
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
TLDR
This work combines existing fine-grained visualizations to create a high-resolution class-discriminative visualization, Guided Grad-CAM, and applies it to image classification, image captioning, and visual question answering (VQA) models, including ResNet-based architectures. Expand
Hierarchical Question-Image Co-Attention for Visual Question Answering
TLDR
This paper presents a novel co-attention model for VQA that jointly reasons about image and question attention in a hierarchical fashion via a novel 1-dimensional convolution neural networks (CNN). Expand
Habitat: A Platform for Embodied AI Research
TLDR
The comparison between learning and SLAM approaches from two recent works are revisited and evidence is found -- that learning outperforms SLAM if scaled to an order of magnitude more experience than previous investigations, and the first cross-dataset generalization experiments are conducted. Expand
Visual Dialog
TLDR
A retrieval-based evaluation protocol for Visual Dialog where the AI agent is asked to sort a set of candidate answers and evaluated on metrics such as mean-reciprocal-rank of human response, and a family of neural encoder-decoder models, which outperform a number of sophisticated baselines. Expand
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
TLDR
GVQA explicitly disentangles the recognition of visual concepts present in the image from the identification of plausible answer space for a given question, enabling the model to more robustly generalize across different distributions of answers. Expand
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
TLDR
A new framework for evaluating story understanding and script learning: the `Story Cloze Test’, which requires a system to choose the correct ending to a four-sentence story, and a new corpus of 50k five- Sentence commonsense stories, ROCStories, to enable this evaluation. Expand
Joint Unsupervised Learning of Deep Representations and Image Clusters
TLDR
A recurrent framework for joint unsupervised learning of deep representations and image clusters by integrating two processes into a single model with a unified weighted triplet loss function and optimizing it end-to-end can obtain not only more powerful representations, but also more precise image clusters. Expand
iCoseg: Interactive co-segmentation with intelligent scribble guidance
TLDR
iCoseg, an automatic recommendation system that intelligently recommends where the user should scribble next, is proposed, and users following these recommendations can achieve good quality cutouts with significantly lower time and effort than exhaustively examining all cutouts. Expand
...
1
2
3
4
5
...