59 citations · 81 across the 4 of their papers we have counts for
6 papers
Predictive Coding Networks Meet Action Recognition
Xia Huang, Hossein Mousavi, Gemma Roig
Action recognition is a key problem in computer vision that labels videos with a set of predefined actions. Capturing both, semantic content and motion, along the video frames is k…
Efficient Convolutional Neural Network with Binary Quantization Layer
Mahdyar Ravanbakhsh, Hossein Mousavi, Moin Nabi +2
In this paper we introduce a novel method for segmentation that can benefit from general semantics of Convolutional Neural Network (CNN). Our segmentation proposes visually and sem…
Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection
Mahdyar Ravanbakhsh, Moin Nabi, Hossein Mousavi +2
Most of the crowd abnormal event detection methods rely on complex hand-crafted features to represent the crowd motion and appearance. Convolutional Neural Networks (CNN) have show…
CNN-aware Binary Map for General Semantic Segmentation
Mahdyar Ravanbakhsh, Hossein Mousavi, Moin Nabi +2
In this paper we introduce a novel method for general semantic segmentation that can benefit from general semantics of Convolutional Neural Network (CNN). Our segmentation proposes…
Emotion-Based Crowd Representation for Abnormality Detection
Hamidreza Rabiee, Javad Haddadnia, Hossein Mousavi +3
In crowd behavior understanding, a model of crowd behavior need to be trained using the information extracted from video sequences. Since there is no ground-truth available in crow…
Action Recognition with Image Based CNN Features
Mahdyar Ravanbakhsh, Hossein Mousavi, Mohammad Rastegari +2
Most of human actions consist of complex temporal compositions of more simple actions. Action recognition tasks usually relies on complex handcrafted structures as features to repr…