AZAmir Roshan Zamir

Amir Roshan Zamir

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Amir Roshan Zamir has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Generic 3D Representation via Pose Estimation and Matching

    by Amir R. Zamir, Tilman Wekel, Pulkit Agrawal, Colin Wei, Jitendra Malik, Silvio Savarese


  • Introduction to Large-Scale Visual Geo-localization

    by Amir R. Zamir, Asaad Hakeem, Luc Van Gool, Mubarak Shah, Richard Szeliski


  • Open Access

    Unsupervised Semantic Action Discovery from Video Collections

    by Ozan Sener, Amir Roshan Zamir, Chenxia Wu, Silvio Savarese, Ashutosh Saxena

    Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a method for parsing a video into such semantic steps in an unsupervised way. Our method is capable of providing a semantic "storyline" of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. Our method can also provide a textual description for each of the identified semantic steps and video segments. We evaluate our method on a large number of complex YouTube videos and show that our method discovers semantically correct instructions for a variety of tasks.

  • Open Access

    Structural-RNN: Deep Learning on Spatio-Temporal Graphs

    by Ashesh Jain, Amir R. Zamir, Silvio Savarese, Ashutosh Saxena

    Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level structure and can benefit from it. Spatio-temporal graphs are a popular tool for imposing such high-level intuitions in the formulation of real world problems. In this paper, we propose an approach for combining the power of high-level spatio-temporal graphs and sequence learning success of Recurrent Neural Networks~(RNNs). We develop a scalable method for casting an arbitrary spatio-temporal graph as a rich RNN mixture that is feedforward, fully differentiable, and jointly trainable. The proposed method is generic and principled as it can be used for transforming any spatio-temporal graph through employing a certain set of well defined steps. The evaluations of the proposed approach on a diverse set of problems, ranging from modeling human motion to object interactions, shows improvement over the state-of-the-art with a large margin. We expect this method to empower new approaches to problem formulation through high-level spatio-temporal graphs and Recurrent Neural Networks.


  • Open Access

    Unsupervised Semantic Parsing of Video Collections

    by Ozan Sener, Amir Zamir, Silvio Savarese, Ashutosh Saxena

    Human communication typically has an underlying structure. This is reflected in the fact that in many user generated videos, a starting point, ending, and certain objective steps between these two can be identified. In this paper, we propose a method for parsing a video into such semantic steps in an unsupervised way. The proposed method is capable of providing a semantic "storyline" of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. The proposed method can also provide a textual description for each of the identified semantic steps and video segments. We evaluate this method on a large number of complex YouTube videos and show results of unprecedented quality for this intricate and impactful problem.