Exploiting Proximity-Aware Tasks for Embodied Social Navigation
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
CVPR Embodied AI Workshop, 2023
Weakly-Supervised Visual-Textual Grounding with Semantic Prior Refinement
British Machine Vision Conference (BMVC), 2023
TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction
IEEE Int'l Conference on Acoustics Speech and Signal Processing (ICASSP), 2023 [Oral]
Distilling Knowledge for Short-to-Long Term Trajectory Prediction
arXiv preprint: 2305.08553, 2023
Knowledge-Based Systems, in press, 2023
Online Learning of Reusable Abstract Models for Object Goal Navigation
IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2022
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting
IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction
CVPR Precognition Workshop, 2022
Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer
British Machine Vision Conference (BMVC), 2022 [Spotlight]
CVPR Workshop on Transformers for Vision (T4V), 2022
arXiv preprint Extended Abstract Poster Video Code & Dataset
Early Pedestrian Intent Prediction via Features Estimation
IEEE International Conference on Image Processing (ICIP), 2022
Vision, S.I. "Symposium on Perception and Cognition and Kanizsa Lecture", Vol. 6, No. 2:29, pp. 1-19, 2022
Aligning and linking entity mentions in image, text, and knowledge base
Data & Knowledge Engineering, Vol. 138, 2022
Conditional Variational Capsule Network for Open Set Recognition
IEEE/CVF International Conference on Computer Vision (ICCV), 2021
SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos
ICCV Workshop on Egocentric Perception Interaction and Computing (EPIC), 2021
AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction
Computer Vision and Image Understanding, Vol. 210, 2021
Am I Done? Predicting Action Progress in Videos
ACM Trans. on Multimedia Computing, Communications, and Applications (TOMM), Vol. 16, Issue 4, pp. 1-24, 2021
Exploiting Scene-specific Features for Object Goal Navigation
ECCV Workshop on Assistive Computer Vision and Robotics (ACVR), 2020
Knowledge Distillation for Action Anticipation via Label Smoothing
International Conference on Pattern Recognition (ICPR), 2020
A CNN-RNN Framework for Image Annotation from Visual Cues and Social Network Metadata
International Conference on Pattern Recognition (ICPR), 2020
On Visual-Textual-Knowledge Entity Linking
European Conference on Artificial Intelligence (ECAI), 2020 [Highlight]
IEEE International Conference on Semantic Computing (ICSC), 2020
VTKEL: A resource for Visual-Textual-Knowledge Entity Linking
ACM Symposium on Applied Computing (ACM-SAC), 2020
Social and Scene-aware Trajectory Prediction in Crowded Spaces
ICCV Workshop on Assistive Computer Vision and Robotics (ACVR), 2019
Long-term Path Prediction in Urban Scenarios using Circular Distributions
Image and Vision Computing, Vol. 69, pp. 81-91, 2018
Context-aware Trajectory Prediction
International Conference on Pattern Recognition (ICPR), 2018
Learning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition
Computer Vision and Image Understanding, Vol. 173, pp. 24-32, 2018
Localization of JPEG double compression through multi-domain convolutional neural networks
CVPR Workshop on Media Forensics (MF), 2017
Automatic Image Annotation via Label Transfer in the Semantic Space
Pattern Recognition, Vol. 71, pp. 144-157, 2017
Effective Fisher Vector Aggregation for 3D Object Retrieval
IEEE Int'l Conference on Acoustics Speech and Signal Processing (ICASSP), 2017
Knowledge Transfer for Scene-specific Motion Prediction
European Conference on Computer Vision (ECCV), 2016
Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval
ACM Computing Surveys, Vol. 49, Issue 1, pp. 1-39, 2016
Point-based path prediction from polar histograms
International Conference on Information Fusion (FUSION), 2016
Love Thy Neighbors: Image Annotation by Exploiting Image Metadata
IEEE International Conference on Computer Vision (ICCV), 2015
A data-driven approach for tag refinement and localization in web videos
Computer Vision and Image Understanding, Vol. 140, pp. 58-67, 2015
Data-driven approaches for social image and video tagging
Multimedia Tools and Applications, Vol. 74:4, pp. 1443-1468, 2015