Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 101-110 of 111 papers
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali FarhadiECCV • 2016 We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the…You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali FarhadiCVPR • 2016 We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class…Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing
Hamid Izadinia, Fereshteh Sadeghi, Santosh Divvala, Hanna Hajishirzi, Yejin Choi, and Ali FarhadiICCV • 2015 We introduce Segment-Phrase Table (SPT), a large collection of bijective associations between textual phrases and their corresponding segmentations. Leveraging recent progress in object recognition and natural language semantics, we show how we can…Solving Geometry Problems: Combining Text and Diagram Interpretation
Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi, Oren Etzioni, and Clint MalcolmEMNLP • 2015 This paper introduces GeoS, the first automated system to solve unaltered SAT geometry questions by combining text understanding and diagram interpretation. We model the problem of understanding geometry questions as submodular optimization, and identify a…Discriminative and Consistent Similarities in Instance-Level Multiple Instance Learning
Mohammad Rastegari, Hannaneh Hajishirzi, and Ali FarhadiCVPR • 2015 In this paper we present a bottom-up method to instance level Multiple Instance Learning (MIL) that learns to discover positive instances with globally constrained reasoning about local pairwise similarities. We discover positive instances by optimizing for a…Generating Notifications for Missing Actions: Don’t forget to turn the lights off!
Bilge Soran, Ali Farhadi, and Linda ShapiroICCV • 2015 We all have experienced forgetting habitual actions among our daily activities. For example, we probably have forgotten to turn the lights off before leaving a room or turn the stove off after cooking. In this paper, we propose a solution to the problem of…Looking Beyond Text: Extracting Figures, Tables and Captions from Computer Science Papers
Christopher Clark and Santosh DivvalaAAAI • Workshop on Scholarly Big Data • 2015 Identifying and extracting figures and tables along with their captions from scholarly articles is important both as a way of providing tools for article summarization, and as part of larger systems that seek to gain deeper, semantic understanding of these…VISALOGY: Answering Visual Analogy Questions
Fereshteh Sadeghi, C. Lawrence Zitnick, and Ali FarhadiNIPS • 2015 In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the…VisKE: Visual Knowledge Extraction and Question Answering by Visual Verification of Relation Phrases
Fereshteh Sadeghi, Santosh Divvala, and Ali FarhadiCVPR • 2015 How can we know whether a statement about our world is valid. For example, given a relationship between a pair of entities e.g., 'eat(horse, hay)', how can we know whether this relationship is true or false in general. Gathering such knowledge about entities…Learning Everything about Anything: Webly-Supervised Visual Concept Learning
Santosh K. Divvala, Ali Farhadi, and Carlos GuestrinCVPR • 2014 Recognition is graduating from labs to real-world applications. While it is encouraging to see its potential being tapped, it brings forth a fundamental challenge to the vision researcher: scalability. How can we learn a model for any concept that…