Filters








189 Hits in 4.6 sec

STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits [article]

Uttaran Bhattacharya and Trisha Mittal and Rohan Chandra and Tanmay Randhavane and Aniket Bera and Dinesh Manocha
2019 arXiv   pre-print
We present a novel classifier network called STEP, to classify perceived human emotion from gaits, based on a Spatial Temporal Graph Convolutional Network (ST-GCN) architecture.  ...  We use hundreds of annotated real-world gait videos and augment them with thousands of annotated synthetic gaits generated using a novel generative network called STEP-Gen, built on an ST-GCN based Conditional  ...  The main contributions include: A novel end-to-end Spatial Temporal Graph Convolution-Based Network (STEP), which implicitly extracts a person's gait from a walking video to predict their emotion.  ... 
arXiv:1910.12906v1 fatcat:lkmwd5kidfcmfbpfbde6rrkq5u

STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits

Uttaran Bhattacharya, Trisha Mittal, Rohan Chandra, Tanmay Randhavane, Aniket Bera, Dinesh Manocha
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We present a novel classifier network called STEP, to classify perceived human emotion from gaits, based on a Spatial Temporal Graph Convolutional Network (ST-GCN) architecture.  ...  We train STEP on annotated real-world gait videos, augmented with annotated synthetic gaits generated using a novel generative network called STEP-Gen, built on an ST-GCN based Conditional Variational  ...  A novel end-to-end Spatial Temporal Graph Convolution-Based Network (STEP), which implicitly extracts a person's gait from a walking video to predict their emotion.  ... 
doi:10.1609/aaai.v34i02.5490 fatcat:tsawfmzfm5cv7ay7ojhyxvise4

Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping [article]

Uttaran Bhattacharya, Christian Roncal, Trisha Mittal, Rohan Chandra, Kyra Kapsaskis, Kurt Gray, Aniket Bera, Dinesh Manocha
2020 arXiv   pre-print
We outperform current state-of-art algorithms for both emotion recognition and action recognition from 3D gaits by 7%--23% on the absolute.  ...  For the annotated data, we also train a classifier to map the latent embeddings to emotion labels.  ...  We also compare with STEP [9] , which trains a spatial-temporal graph convolution-based network with gait inputs and affective features obtained from the gaits, and then fine-tunes the network with data  ... 
arXiv:1911.08708v2 fatcat:p74fnpengjb5jcyjw6rkji7xwe

TNTC: two-stream network with transformer-based complementarity for gait-based emotion recognition [article]

Chuanfei Hu, Weijie Sheng, Bo Dong, Xinde Li
2021 arXiv   pre-print
Meanwhile, the long range dependencies in both spatial and temporal domains of the gait sequence are scarcely considered.  ...  The popular pipeline is to first extract affective features from joint skeletons, and then aggregate the skeleton joint and affective features as the feature vector for classifying the emotion.  ...  The insight of graph based-methods is to utilize Spatial Temporal Graph Convolutional Network (ST-GCN) to represent the inherent relationship between joints, since the skeleton is naturally structured  ... 
arXiv:2110.13708v1 fatcat:keqs4d7svjf5xn6ni5tbbmgxri

EWareNet: Emotion Aware Human Intent Prediction and Adaptive Spatial Profile Fusion for Social Robot Navigation [article]

Venkatraman Narayanan and Bala Murali Manoghar and Rama Prashanth RV and Aniket Bera
2020 arXiv   pre-print
We outperform current state-of-art algorithms for intent prediction from 3D gaits.  ...  Our approach predicts the trajectory-based pedestrian intent from historical gaits, which is then used for intent-guided navigation taking into account social and proxemic constraints.  ...  [24] use a Graph Convolution method to predict the trajectories and showed that Temporal Graph Convolutions are much better at predicting the human trajectories compared to recurrent networks.  ... 
arXiv:2011.09438v3 fatcat:b3x2pdzlq5er5gqpxhwps4ddea

Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders [article]

Abhishek Banerjee, Uttaran Bhattacharya, Aniket Bera
2021 arXiv   pre-print
We present a novel generalized zero-shot algorithm to recognize perceived emotions from gestures. Our task is to map gestures to novel emotion categories not encountered in training.  ...  This improves the performance of current state-of-the-art algorithms for generalized zero-shot learning by 25–27% on the absolute.  ...  Recent work by (Bhattacharya et al. 2020 ) has leveraged spatial-temporal graph convolution networks (ST-GCN) (Yan, Xiong, and Lin 2018) to capture pose dynamics and generate a mapping between the extracted  ... 
arXiv:2009.08906v2 fatcat:riebcb2mr5c5rpqgyw7c3mssum

Emotion Recognition from Multiple Modalities: Fundamentals and Methodologies [article]

Sicheng Zhao, Guoli Jia, Jufeng Yang, Guiguang Ding, Kurt Keutzer
2021 arXiv   pre-print
adaptation for MER.  ...  Furthermore, we present some representative approaches on representation learning of each affective modality, feature fusion of different affective modalities, classifier optimization for MER, and domain  ...  ., SVM or random forest (RF)) to predict emotions. Recently, another popular network used in gait emotion prediction is the spatial-temporal graph convolutional network (ST-GCN).  ... 
arXiv:2108.10152v1 fatcat:hwnq7hoiqba3pdf6aakcxjq33i

The Liar's Walk: Detecting Deception with Gait and Gesture [article]

Tanmay Randhavane, Uttaran Bhattacharya, Kyra Kapsaskis, Kurt Gray, Aniket Bera, Dinesh Manocha
2020 arXiv   pre-print
Based on the gait and gesture data, we train an LSTM-based deep neural network to obtain deep features.  ...  We present a data-driven deep neural algorithm for detecting deceptive walking behavior using nonverbal cues like gaits and gestures.  ...  We compare with approaches that use spatial-temporal graph convolution networks for emotion (STEP [11] ) and action recognition (ST-GCN [72] ).  ... 
arXiv:1912.06874v3 fatcat:vlsvc7qvojafthncoj4yradfgu

Generating Emotive Gaits for Virtual Agents Using Affect-Based Autoregression [article]

Uttaran Bhattacharya and Nicholas Rewkowski and Pooja Guhan and Niall L. Williams and Trisha Mittal and Aniket Bera and Dinesh Manocha
2020 arXiv   pre-print
We also use our network to augment existing gait datasets with emotive gaits and will release this augmented dataset for future research in emotion prediction and emotive gait synthesis.  ...  Given the 3D pose sequences of a gait, our network extracts pertinent movement features and affective features from the gait.  ...  We used 80% of our gait dataset for training our network, 10% for validation, and kept the remaining 10% of the dataset for testing the emotional-expressiveness and trajectory-following performances.  ... 
arXiv:2010.01615v1 fatcat:ljl45tsxizbwjh6vree6ddon2u

Emotion Recognition from Physiological Channels Using Graph Neural Network

Tomasz Wierciński, Mateusz Rock, Robert Zwierzycki, Teresa Zawadzka, Michał Zawadzki
2022 Sensors  
One of the newest trends observed is the utilization of graph neural networks (GNNs) to recognize emotions. The study presented in the paper follows this trend.  ...  The novelty of this research is not only the utilization of a GNN network with GraphSleepNet architecture for emotion recognition, but also the analysis of the potential of emotion recognition based on  ...  The graph neural network model used is based heavily on the GraphSleepNet model [3] , which is used to classify sleep stages with the use of both spatial-temporal convolution and spatial-temporal attention  ... 
doi:10.3390/s22082980 pmid:35458965 pmcid:PMC9025566 fatcat:77ctahcwp5a4tftpnrcfoz2g4e

A Multi-View Gait Recognition Method Using Deep Convolutional Neural Network and Channel Attention Mechanism

Jiabin Wang, Kai Peng
2020 CMES - Computer Modeling in Engineering & Sciences  
Therefore, the combination of convolutional neural network and channel attention mechanism is of great value for gait recognition.  ...  As can be shown from the comparative experimental results, the proposed method has better recognition effect than several other newer convolutional neural network methods.  ...  [16] proposed an invariant gait recognition method based on 3D convolutional neural network, which extracts spatial and temporal information by learning viewpoint-invariant features to improve model  ... 
doi:10.32604/cmes.2020.011046 fatcat:rxe3csrog5gxbo7ih2qxa6y5gm

Representation, Analysis, and Recognition of 3D Humans

Stefano Berretti, Mohamed Daoudi, Pavan Turaga, Anup Basu
2018 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
At large, the contra-position is between hand-crafted and learned features: these can capture the spatial information only or also account for the temporal dimension.  ...  Spatial and temporal representations have been used in a variety of analysis and recognition tasks (see Section 3).  ...  [46] proposed a gait analysis method from depth sequences by analyzing separately each step so as to be robust to gait duration and incomplete cycles.  ... 
doi:10.1145/3182179 fatcat:ds55t4md2na2tibtyg4llerf3q

Application of Artificial Intelligence in the MRI Classification Task of Human Brain Neurological and Psychiatric Diseases: A Scoping Review

Zhao Zhang, Guangfei Li, Yong Xu, Xiaoying Tang
2021 Diagnostics  
Artificial intelligence (AI) for medical imaging is a technology with great potential.  ...  This review first summarizes recent research advances in ML and DL techniques for classifying human brain magnetic resonance images.  ...  Other possible symptoms include perception, sleep, and emotional problems [90] . As for ML methods, Solana-Lavalle et al.  ... 
doi:10.3390/diagnostics11081402 fatcat:mmouz5fb2ngzbe7jj2fyi5xpsy

Integrating Sensing and Communication in Cellular Networks via NR Sidelink [article]

Dariush Salami, Ramin Hasibi, Stefano Savazzi, Tom Michoel, Stephan Sigg
2021 arXiv   pre-print
To process the distributed data, we propose a graph based encoder to capture spatio-temporal features of the data and propose four approaches for multi-angle learning.  ...  Such communications and sensing convergence is envisioned for future communication networks.  ...  To process the generated graph, an Edge Convolution Network (ECN) [39] is applied and a vector of gesture representations is gathered.  ... 
arXiv:2109.07253v1 fatcat:23qdss4mgfhszmhtntmlfv2z4e

Human Action Recognition and Prediction: A Survey [article]

Yu Kong, Yun Fu
2022 arXiv   pre-print
Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state.  ...  Many attempts have been devoted in the last a few decades in order to build a robust and effective framework for action recognition and prediction.  ...  [324] recently proposed to introduce the graph convolutional neural networks (GCN) for temporal action localization. Song et al.  ... 
arXiv:1806.11230v3 fatcat:2a2d7fuezbdqzfgrjwkcuqvmbu
« Previous Showing results 1 — 15 out of 189 results