Ali Farhadi
University of Washington
248 Papers
2.3K Citations
Ali Farhadi is an academic researcher from University of Washington. The author has contributed to research in topics: Computer science & Context (language use). The author has an hindex of 63, co-authored 234 publications. Previous affiliations of Ali Farhadi include University of Illinois at Urbana–Champaign & Lorestan University of Medical Sciences.
Chat about Author
Papers
Grounded Situation Recognition
Sarah M Pratt,Mark Yatskar,Luca Weihs,Ali Farhadi,Aniruddha Kembhavi,Aniruddha Kembhavi +5 more
- 23 Aug 2020
TL;DR: In this article, the authors introduce Grounded Situation Recognition (GSR), a task that requires producing structured semantic summaries of images describing: the primary activity, entities engaged in the activity with their roles, and bounding-box groundings of entities.
73
ELASTIC: Improving CNNs With Dynamic Scaling Policies
Huiyu Wang,Aniruddha Kembhavi,Ali Farhadi,Alan L. Yuille,Mohammad Rastegari +4 more
- 01 Jun 2019
TL;DR: Elastic as mentioned in this paper proposes to learn a dynamic scale policy from data by formulating the scaling policy as a non-linear function inside the network's structure that is instance specific, does not add extra computation and can be applied on any network architecture.
•Posted Content
Query-Reduction Networks for Question Answering
TL;DR: QRN as discussed by the authors considers the context sentences as a sequence of state-changing triggers, and reduces the original query to a more informed query as it observes each trigger (context sentence) through time.
70
•Posted Content
Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
TL;DR: This paper proposed an actor-critic model whose policy is a function of the goal as well as the current state, which allows the model to better generalize to new target goals.
68
•Posted Content
Re3 : Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects
TL;DR: Re3 as mentioned in this paper is a real-time deep object tracker capable of incorporating temporal information into its model by pre-training a generic tracker on a large variety of objects and efficiently updating on the fly.
66