Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

Two Body Problem: Collaborative Visual Task Completion

Unnat JainLuca WeihsEric KolveAniruddha Kembhavi
2019
CVPR

Collaboration is a necessary skill to perform tasks that are beyond one agent's capabilities. Addressed extensively in both conventional and modern AI, multi-agent collaboration has often been… 

ELASTIC: Improving CNNs by Instance Specific Scaling Policies

Huiyu WangAniruddha KembhaviAli FarhadiMohammad Rastegari
2019
CVPR

Scale variation has been a challenge from traditional to modern approaches in computer vision. Most solutions to scale issues have similar theme: a set of intuitive and manually designed policies… 

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Mitchell WortsmanKiana EhsaniMohammad RastegariRoozbeh Mottaghi
2019
CVPR

Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. After we learn a task, we keep learning about it while… 

OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge

Kenneth MarinoMohammad RastegariAli FarhadiRoozbeh Mottaghi
2019
CVPR

Visual Question Answering (VQA) in its ideal form lets us study reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most VQA… 

ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

Sachin MehtaMohammad RastegariLinda ShapiroHannaneh Hajishirzi
2019
CVPR

We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2 , for modeling visual and sequential data. Our network uses group point-wise and depth-wise… 

From Recognition to Cognition: Visual Commonsense Reasoning

Rowan ZellersYonatan BiskAli FarhadiYejin Choi
2019
CVPR

Visual understanding goes well beyond object recognition. With one glance at an image, we can effortlessly imagine the world beyond the pixels: for instance, we can infer people’s actions, goals,… 

Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph

Yao-Hung TsaiSantosh DivvalaLouis-Philippe MorencyRuslan Salakhutdinov and Ali Farhadi
2019
CVPR

Visual relationship reasoning is a crucial yet challenging task for understanding rich interactions across visual concepts. For example, a relationship \{man, open, door\} involves a complex… 

Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors

Mohammad Mahdi DerakhshaniSaeed MasoudniaAmir Hossein ShakerBabak N. Araabi
2019
CVPR

We present a simple and effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefully feed in… 

Sentence Mover's Similarity: Automatic Evaluation for Multi-Sentence Texts

Elizabeth ClarkAsli ÇelikyilmazNoah A. Smith
2019
ACL

For evaluating machine-generated texts, automatic methods hold the promise of avoiding collection of human judgments, which can be expensive and time-consuming. The most common automatic metrics,… 

Barack's Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling

Robert L. Logan IVNelson F. LiuMatthew E. PetersSameer Singh
2019
ACL

Modeling human language requires the ability to not only generate fluent text but also encode factual knowledge. However, traditional language models are only capable of remembering facts seen at…