Aniruddha Kembhavi
Allen Institute for Artificial Intelligence
- Publications
- Influence
Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been… Continue Reading
IEEE Transactions on Pattern Analysis and Machine…
Interpretation of images and videos containing humans interacting with different objects is a daunting task. It involves understanding scene or event, analyzing human movements, recognizing… Continue Reading
IEEE/CVF Conference on Computer Vision and…
A number of studies have found that today's Visual Question Answering (VQA) models are heavily driven by superficial correlations in the training data and lack sufficient image grounding. To… Continue Reading
IEEE 12th International Conference on Computer…
Significant research has been devoted to detecting people in images and videos. In this paper we describe a human detection method that augments widely used edge-based features with texture and color… Continue Reading
Diagrams are common tools for representing complex concepts, relationships and events, often when it would be difficult to portray the same information with natural images. Understanding natural… Continue Reading
IEEE Conference on Computer Vision and Pattern…
We introduce the task of Multi-Modal Machine Comprehension (M3C), which aims at answering multimodal questions given a context of text, diagrams and images. We present the Textbook Question Answering… Continue Reading
IEEE Transactions on Pattern Analysis and Machine…
Detecting vehicles in aerial images has a wide range of applications, from urban planning to visual surveillance. We describe a vehicle detector that improves upon previous approaches by… Continue Reading
IEEE/CVF Conference on Computer Vision and…
We introduce Interactive Question Answering (IQA), the task of answering questions that require an autonomous agent to interact with a dynamic visual environment. IQA presents the agent with a scene… Continue Reading
Training a neural network is synonymous with learning the values of the weights. In contrast, we demonstrate that randomly weighted neural networks contain subnetworks which achieve impressive… Continue Reading
Visual Question Answering (VQA) has received a lot of attention over the past couple of years. A number of deep learning models have been proposed for this task. However, it has been shown that these… Continue Reading