Publications
This is a list of my publications in the last 6 years. For a full list please see Google Scholar.
2023
Heterogeneous Graph Learning for Acoustic Event Classification
A Shirian, M Ahmadian, K Somandepalli and T Guha
Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Rhodes, Greece, June 2023.
Robust Multiview Multimodal Driver Monitoring System using Masked Multihead Self Attention
Y Ma, V Sanchez, S Nikan, D Upadhyay, B Atote and T Guha
Int. Conf. on Computer Vision and Pattern Recognition Workshops (CVPR-W), Vancouver, Canada, June 2023.
2022
Multi-camera Trajectory Forecasting with Trajectory Tensors
O Styles, T Guha and V Sanchez
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44(11), pp. 8482-8491, November 2022.
Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data
A Shirian, K Somandepalli and T Guha
IEEE Journal of Selected Topics in Signal Processing, vol. 26(6), pp. 1391-1401, October 2022.
Dynamic Emotion Modeling with Learnable Graphs and Graph Inception Network
A Shirian, S Tripathi and T Guha
IEEE Transactions on Multimedia, vol. 24, pp. 780-790, February 2022.
Learning Long-Term Spatio-Temporal Graphs for Active Speaker Detection
K Min, S Roy, S Tripathi, T Guha and S Majumdar
European Conf. on Computer VIsion (ECCV), Tel Aviv, Israel, October 2022.
FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion
Y Ma, T Guha and V Sanchez
Int. Conf. on Image Processing (ICIP), Bordeaux, France, October 2022.
Self-supervised Frontalization and Rotation GAN with Random Swap for Pose-invariant Face Recognition
J Liao, T Guha and V Sanchez
Int. Conf. on Image Processing (ICIP), Bordeaux, France, October 2022.
Visually-aware Acoustic Event Detection using Heterogeneous Graphs
A Shirian, K Somandepalli, V Sanchez and T Guha
INTERSPEECH, Incheon, Korea, September 2022.
Graph-based Transform based on 3D Convolutional Neural Network for Intraprediction of Imaging Data
D Roy, T Guha and V Sanchez
Data Compression Conference (DCC), Snowbird, US, March 2022.
2021
Computational Media Intelligence: Human-centered Machine Analysis of Media
K Somandepalli, T Guha, V Martinez, N Kumar, H Adam and S S Narayanan
Proceedings of the IEEE, vol. 109(5), pp. 891 - 910, May 2021.
Emotion Sensing from Head Motion Capture
A Samanta and T Guha
IEEE Sensors Journal, vol. 21(4), pp. 5035 - 5043, February 2021.
In Defense of Scene Graphs for Image Captioning
K Nguyen, S Tripathi, B Du, T Guha and T Nguyen
Int. Conf. on Computer Vision (ICCV), Virtual, October 2021.
Head Matters: Explainable Human-centered Trait Prediction from Head Motion Dynamics
S Madan, M Gahalawat, T Guha and R Subramanian
Int. Conf. on Multimodal Interaction (ICMI), Virtual, October 2021.
Towards Autism Screening through Emotion-guided Eye Gaze Response
S Ghosh and T Guha
Int. Conf. on IEEE Engineering in Medicine and Biology Society (EMBC), Virtual, October 2021.
Compact Graph Architecture for Speech Emotion Recognition
A Shirian and T Guha
Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Virtual, June 2021.
GBT based on Graph Neural Network for Predictive Transform Coding
D Roy, T Guha and V Sanchez
Data Compression Conference (DCC), Virtual, March 2021. (Extended abstract)
2020
Dynamic Character Graph via Online Face Clustering for Movie Analysis
P Kulshreshtha and T Guha
Multimedia Tools and Applications, vol. 79(43-44), pp. 33103 - 33116, November 2020.
Attention-selective Network for Face Synthesis and Pose-invariant Face Recognition
J Liao, A Kot, T Guha and V Sanchez
Int. Conf. on Image Processing (ICIP), Virtual, October 2020.
Multi-camera Trajectory Forecasting: Pedestrian Trajectory Prediction in a Network of Cameras
O Styles, T Guha, V Sanchez and A Kot
Int. Conf. on Computer Vision and Pattern Recognition Workshops (CVPR-W), Virtual, June 2020.
PDF Database **Best student paper award**
Ensemble Network for Ranking Images based on Visual Appeal
S Singh, V Sanchez and T Guha
Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Virtual, May 2020.
Variational Recurrent Sequence-to-Sequence Retrieval for Stepwise Illustration
V Batra, A Halder, Y He, G Vogiatzis, H Ferhatosmanoglu and T Guha
European Conference on Information Retrieval (ECIR), Lisbon, Portugal, April 2020.
Multiple Object Forecasting: Predicting Future Object Locations in Diverse Environments
O Styles, T Guha and V Sanchez
Winter Conf. on Applications of Computer Vision (WACV), Aspen, US, March 2020.
Coordinated Joint Multimodal Embeddings for Generalized Audio-visual Zero-shot Classification
K K Parida, N Matiyali, T Guha and G Sharma
Winter Conf. on Applications of Computer Vision (WACV), Aspen, US, March 2020.
2019
Dirichlet Latent Variable Model: A Dynamic Model based on Dirichlet Prior for Audio Processing
A Kumar, T Guha and P K Ghosh
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27(5), pp. 919-931, March 2019.
Motion-capture Patterns of Voluntarily Mimicked Dynamic Facial Expressions in Children and Adolescents with and without ASD
E Zane, Z Yang, L Pozzan, T Guha, S S Narayanan and R Grossman
Journal of Autism and Developmental Disorder, vol. 49(3), pp. 1062 - 1079, March 2019.
Learning Affective Correspondence between Music and Image
G Verma, E G Dhekane and T Guha
Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, May 2019.
Computational Analysis of Gaze Behavior in Autism during Interaction with Virtual Agents
Z Akhtar and T Guha
Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, May 2019.
GBT with Weighted Self-loops for Predictive Transform Coding based on Template Matching
D Roy, T Guha and V Sanchez
Data Compression Conference (DCC), Snowbird, US, March 2019.
2018
A Computational Study of Expressive Facial Dynamics in Children with Autism
T Guha, Z Yang, R Grossman and S S Narayanan
IEEE Transactions on Affective Computing, vol. 9 (1), pp. 14-20, Jan-March 2018.
Unsupervised Discovery of Character Dictionaries in Animation Movies
K Somandepalli, N Kumar, T Guha and S S Narayanan
IEEE Transactions on Multimedia, vol. 20 (3), pp. 539-551, 2018.
Learning Spontaneity to Improve Emotion Recognition in Speech
K Mangalam and T Guha
INTERSPEECH, Hyderabad, India, September 2018.
An Online Algorithm for Constrained Face Clustering in Videos
P Kulshreshtha and T Guha
Int. Conf. on Image Processing (ICIP), Athens, Greece, October 2018.
A Dynamic Latent Variable Model for Source Separation
A Kumar, T Guha and P K Ghosh
Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada, April 2018.
Multichannel Attention Network for Analyzing Visual Behavior in Public Speaking
R Sharma, T Guha and G Sharma
Winter Conf. on Applications of Computer Vision (WACV), Lake Tahoe, US, March 2018.
2017 and Older
Please see Google Scholar