A
Antonio Torralba
Researcher at Massachusetts Institute of Technology
Publications - 437
Citations - 105763
Antonio Torralba is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 119, co-authored 388 publications receiving 84607 citations. Previous affiliations of Antonio Torralba include Vassar College & Nvidia.
Papers
More filters
Posted Content
MovieQA: Understanding Stories in Movies through Question-Answering
TL;DR: The MovieQA dataset, which aims to evaluate automatic story comprehension from both video and text, is introduced and existing QA techniques are extended to show that question-answering with such open-ended semantics is hard.
Proceedings ArticleDOI
Learning Aligned Cross-Modal Representations from Weakly Aligned Data
TL;DR: The experiments suggest that the scene representation can help transfer representations across modalities for retrieval and the visualizations suggest that units emerge in the shared representation that tend to activate on consistent concepts independently of the modality.
Book ChapterDOI
Assessing the Quality of Actions
TL;DR: A learning-based framework that takes steps towards assessing how well people perform actions in videos by training a regression model from spatiotemporal pose features to scores obtained from expert judges and can provide interpretable feedback on how people can improve their action.
Posted Content
Network Dissection: Quantifying Interpretability of Deep Visual Representations
TL;DR: In this article, a general framework called Network Dissection is proposed for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts.
Book ChapterDOI
Object Detection and Localization Using Local and Global Features
TL;DR: This work shows that by combining local and global features of the image, they get significantly improved detection rates and since the gist is much cheaper to compute than most local detectors, they can potentially gain a large increase in speed.