Search Results for author: Behrooz Mahasseni

Found 6 papers, 1 papers with code

Budget-Aware Activity Detection with A Recurrent Policy Network

no code implementations30 Nov 2017 Behrooz Mahasseni, Xiaodong Yang, Pavlo Molchanov, Jan Kautz

In this paper, we address the challenging problem of efficient temporal activity detection in untrimmed long videos.

Action Detection Activity Detection

Budget-Aware Deep Semantic Video Segmentation

no code implementations CVPR 2017 Behrooz Mahasseni, Sinisa Todorovic, Alan Fern

In this work, we study a poorly understood trade-off between accuracy and runtime costs for deep semantic video segmentation.

Action Detection Activity Detection +4

Fine-Grained Recognition as HSnet Search for Informative Image Parts

no code implementations CVPR 2017 Michael Lam, Behrooz Mahasseni, Sinisa Todorovic

This motivates us to formulate our problem as a sequential search for informative parts over a deep feature map produced by a deep Convolutional Neural Network (CNN).

Fine-Grained Image Classification Informativeness

Unsupervised Video Summarization With Adversarial LSTM Networks

1 code implementation CVPR 2017 Behrooz Mahasseni, Michael Lam, Sinisa Todorovic

The summarizer is the autoencoder long short-term memory network (LSTM) aimed at, first, selecting video frames, and then decoding the obtained summarization for reconstructing the input video.

Unsupervised Video Summarization

Approximate Policy Iteration for Budgeted Semantic Video Segmentation

no code implementations26 Jul 2016 Behrooz Mahasseni, Sinisa Todorovic, Alan Fern

Our second contribution is the algorithm for learning a policy for the sparse selection of supervoxels and their descriptors for budgeted CRF inference.

Video Segmentation Video Semantic Segmentation

Regularizing Long Short Term Memory With 3D Human-Skeleton Sequences for Action Recognition

no code implementations CVPR 2016 Behrooz Mahasseni, Sinisa Todorovic

This paper argues that large-scale action recognition in video can be greatly improved by providing an additional modality in training data -- namely, 3D human-skeleton sequences -- aimed at complementing poorly represented or missing features of human actions in the training videos.

Action Recognition Temporal Action Localization

Cannot find the paper you are looking for? You can Submit a new open access paper.