2025
Masked Generative Nested Transformers with Decode Time Scaling.
CoRR, February, 2025
Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025
2024
Mixture of Nested Experts: Adaptive Processing of Visual Tokens.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
LookupViT: Compressing Visual Information to a Limited Number of Tokens.
Proceedings of the Computer Vision - ECCV 2024, 2024
2023
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition.
IEEE Trans. Pattern Anal. Mach. Intell., December, 2023
Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering.
CoRR, 2023
Is it an i or an l: Test-time Adaptation of Text Line Recognition Models.
CoRR, 2023
Test-time Adaptation with Slot-Centric Models.
Proceedings of the International Conference on Machine Learning, 2023
Weakly Supervised Information Extraction from Inscrutable Handwritten Document Images.
Proceedings of the Document Analysis and Recognition - ICDAR 2023, 2023
2022
Novel Class Discovery Without Forgetting.
Proceedings of the Computer Vision, 2022
Spacing Loss for Discovering Novel Categories.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022
2021
Learning Person Re-Identification Models From Videos With Weak Supervision.
IEEE Trans. Image Process., 2021
Unsupervised Adaptation of Semantic Segmentation Models without Source Data.
CoRR, 2021
SITA: Single Image Test-time Adaptation.
CoRR, 2021
Learning Few-shot Open-set Classifiers using Exemplar Reconstruction.
CoRR, 2021
Cross-domain Imitation from Observations.
Proceedings of the 38th International Conference on Machine Learning, 2021
Unsupervised Multi-Source Domain Adaptation Without Access to Source Data.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
2020
Learning with Limited Supervision for Static and Dynamic Tasks.
PhD thesis, 2020
Context-Aware Query Selection for Active Learning in Event Recognition.
IEEE Trans. Pattern Anal. Mach. Intell., 2020
Adversarial Knowledge Transfer from Unlabeled Data.
Proceedings of the MM '20: The 28th ACM International Conference on Multimedia, 2020
Domain Adaptive Semantic Segmentation Using Weak Labels.
Proceedings of the Computer Vision - ECCV 2020, 2020
2019
Exploiting Typicality for Selecting Informative and Anomalous Samples in Videos.
IEEE Trans. Image Process., 2019
Learning from Trajectories via Subgoal Discovery.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Stealthy Adversarial Perturbations Against Real-Time Video Classification Systems.
Proceedings of the 26th Annual Network and Distributed System Security Symposium, 2019
Weakly Supervised Video Moment Retrieval From Text Queries.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
2018
Trajectory-based Learning for Ball-in-Maze Games.
CoRR, 2018
Adversarial Perturbations Against Real-Time Video Classification Systems.
CoRR, 2018
Incorporating Scalability in Unsupervised Spatio- Temporal Feature Learning.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018
W-TALC: Weakly-Supervised Temporal Activity Localization and Classification.
Proceedings of the Computer Vision - ECCV 2018, 2018
Exploiting Transitivity for Learning Person Re-Identification Models on a Budget.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018
2017
Full C-band tunable MEMS-VCSEL for next generation G.metro mobile front- and backhauling.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Optical Fiber Communications Conference and Exhibition, 2017
Non-uniform Subset Selection for Active Learning in Structured Data.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
The Impact of Typicality for Informative Representative Selection.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
2016
Multi-Exposure and Multi-Focus Image Fusion in Gradient Domain.
J. Circuits Syst. Comput., 2016
Efficient selection of informative and diverse training samples with applications in scene classification.
Proceedings of the 2016 IEEE International Conference on Image Processing, 2016
Online Adaptation for Joint Scene and Object Classification.
Proceedings of the Computer Vision - ECCV 2016, 2016
2015
Simultaneous feature selection and weighting - An evolutionary multi-objective optimization approach.
Pattern Recognit. Lett., 2015
Rough-Fuzzy Collaborative Multi-level Image Thresholding: A Differential Evolution Approach.
Proceedings of the Mendel 2015, 2015
Up to 12-Gbps transmission over 6.3-km SMF using a directly modulated bulk micromachined MEMS tunable VCSEL.
Proceedings of the European Conference on Optical Communication, 2015
2014
A Fuzzy Entropy Based Multi-Level Image Thresholding Using Differential Evolution.
Proceedings of the Swarm, Evolutionary, and Memetic Computing, 2014
2013
A Differential Evolution Approach to Multi-level Image Thresholding Using Type II Fuzzy Sets.
Proceedings of the Swarm, Evolutionary, and Memetic Computing, 2013
Multi-level image segmentation based on fuzzy - Tsallis entropy and differential evolution.
Proceedings of the FUZZ-IEEE 2013, 2013