Book ChapterDOI
Recognizing Human Activities in Videos Using Improved Dense Trajectories over LSTM
Krit Karan Singh,Snehasis Mukherjee +1 more
- pp 78-88
TLDR
This work proposes a deep learning based technique to classify actions based on Long Short Term Memory networks, and extends the proposed framework with an efficient motion feature, to enable handling significant camera motion.Abstract:
We propose a deep learning based technique to classify actions based on Long Short Term Memory (LSTM) networks. The proposed scheme first learns spatial temporal features from the video, using an extension of the Convolutional Neural Networks (CNN) to 3D. A Recurrent Neural Network (RNN) is then trained to classify each sequence considering the temporal evolution of the learned features for each time step. Experimental results on the CMU MoCap, UCF 101, Hollywood 2 dataset show the efficacy of the proposed approach. We extend the proposed framework with an efficient motion feature, to enable handling significant camera motion. The proposed approach outperforms the existing deep models for each dataset.read more
Citations
More filters
Proceedings ArticleDOI
RCCNet: An Efficient Convolutional Neural Network for Histological Routine Colon Cancer Nuclei Classification
S. H. Shabbeer Basha,Soumen Ghosh,Kancharagunta Kishan Babu,Shiv Ram Dubey,Viswanath Pulabaigari,Snehasis Mukherjee +5 more
TL;DR: In this article, the authors proposed an efficient convolutional neural network (CNN) based architecture for classification of histological routine colon cancer nuclei named as RCCNet, which consists of 1, 512, 868 learnable parameters which are significantly less compared to the popular CNN models such as AlexNet, CIFAR-VGG, GoogLeNet, and WRN.
Book ChapterDOI
Human Action Recognition from 3D Landmark Points of the Performer
TL;DR: In this article, the 3D landmark points of the human pose were extracted from a single image and then used as features for action recognition by applying an autoencoder architecture followed by a regression layer.
Journal ArticleDOI
Human Activity Recognition With Low-Resolution Infrared Array Sensor Using Semi-Supervised Cross-Domain Neural Networks for Indoor Environment
TL;DR: In this article , a semi-supervised cross-domain neural network (SCDNN) based on low-resolution infrared sensor is proposed for accurately identifying human activity despite changes in the environment at a low cost.
References
More filters
Proceedings ArticleDOI
Action recognition with trajectory-pooled deep-convolutional descriptors
Limin Wang,Yu Qiao,Xiaoou Tang +2 more
TL;DR: This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted features and deep-learned features, and achieves superior performance to the state of the art on these datasets.
Book ChapterDOI
Convolutional learning of spatio-temporal features
TL;DR: A model that learns latent representations of image sequences from pairs of successive images is introduced, allowing it to scale to realistic image sizes whilst using a compact parametrization.
MoSIFT: Recognizing Human Actions in Surveillance Videos
TL;DR: This paper proposes an algorithm called MoSIFT, which detects interest points and encodes not only their local appearance but also explicitly models local motion, and introduces a bigram model to construct a correlation between local features to capture the more global structure of actions.
Proceedings ArticleDOI
First Person Action Recognition Using Deep Learned Descriptors
TL;DR: This work proposes convolutional neural networks (CNNs) for end to end learning and classification of wearer's actions and shows that the proposed network can generalize and give state of the art performance on various disparate egocentric action datasets.
Journal ArticleDOI
Semantic human activity recognition: A literature review
Maryam Ziaeefard,Robert Bergevin +1 more
TL;DR: An overview of state-of-the-art methods in activity recognition using semantic features, including a semantic space including the most popular semantic features of an action namely the human body, attributes, related objects, and scene context, is presented.