Andreas E. Savakis

Dr. Andreas E. Savakis

Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USA
orcid

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 May 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
LYLiqi Yan
Liqi Yan
SMSiqi Ma
Siqi Ma
QWQifan Wang
Qifan Wang
YCYingjie Chen
Yingjie Chen
XZXiangyu Zhang
Xiangyu Zhang
Dongfang LiuDongfang Liu
Dongfang Liu
Video captioning is a challenging task as it needs to accurately transform visual understanding into natural language description. To date, state-of-the-art methods inadequately model global-local vision representation for sentence generation, leaving plenty of room for improvement. In this work, we approach the video captioning task from a new perspective and propose a GLR framework, namely a global-local representation granularity. Our GLR demonstrates three advantages over the prior efforts. First, we propose a simple solution, which exploits extensive vision representations from different video ranges to improve linguistic expression. Second, we devise a novel global-local encoder, which encodes different video representations including long-range, short-range and local-keyframe, to produce rich semantic vocabulary for obtaining a descriptive granularity of video contents across frames. Finally, we introduce the progressive training strategy which can effectively organize feature learning to incur optimal captioning behavior. Evaluated on the MSR-VTT and MSVD dataset, we outperform recent state-of-the-art methods including a well-tuned SA-LSTM baseline by a significant margin, with shorter training schedules. Because of its simplicity and efficacy, we hope that our GLR could serve as a strong baseline for many video understanding tasks besides video captioning. Code will be available.

5 December 2019 in Sensors
Verified
Journal Article
Open access
PDF file
Bruno ArtachoBruno Artacho
Bruno Artacho
ASAndreas E. Savakis
Andreas E. Savakis
We propose a new efficient architecture for semantic segmentation, based on a “Waterfall” Atrous Spatial Pooling architecture, that achieves a considerable accuracy increase while decreasing the number of network parameters and memory footprint. The proposed Waterfall architecture leverages the efficiency of progressive filtering in the cascade architecture while maintaining multiscale fields-of-view comparable to spatial pyramid configurations. Additionally, our method does not rely on a postprocessing stage with Conditional Random Fields, which further reduces complexity and required training time. We demonstrate that the Waterfall approach with a ResNet backbone is a robust and efficient architecture for semantic segmentation obtaining state-of-the-art results with significant reduction in the number of parameters for the Pascal VOC dataset and the Cityscapes dataset.

2 November 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
BABruno Artacho
Bruno Artacho
ASAndreas E. Savakis
Andreas E. Savakis
We propose UniPose+, a unified framework for 2D and 3D human pose estimation in images and videos. The UniPose+ architecture leverages multi-scale feature representations to increase the effectiveness of backbone feature extractors, with no significant increase in network size and no postprocessing. Current pose estimation methods heavily rely on statistical postprocessing or predefined anchor poses for joint localization. The UniPose+ framework incorporates contextual information across scales and joint localization with Gaussian heatmap modulation at the decoder output to estimate 2D and 3D human pose in a single stage with state-of-the-art accuracy, without relying on predefined anchor poses. The multi-scale representations allowed by the waterfall module in the UniPose+ framework leverage the efficiency of progressive filtering in the cascade architecture, while maintaining multi-scale fields-of-view comparable to spatial pyramid configurations. Our results on multiple datasets demonstrate that UniPose+, with a HRNet, ResNet or SENet backbone and waterfall module, is a robust and efficient architecture for single person 2D and 3D pose estimation in single images and videos.

4 October 2018 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
PMPanos P. Markopoulos
Panos P. Markopoulos
MDMayur Dhanaraj
Mayur Dhanaraj
ASAndreas E. Savakis
Andreas E. Savakis
L1-norm Principal-Component Analysis (L1-PCA) is known to attain sturdy resistance against faulty points (outliers) among the processed data. However, computing the L1-PCA of large datasets, with high number of measurements and/or dimensions, may be computationally impractical; in such cases, incremental solutions could be preferred. At the same time, in many applications it is desired to track the signal subspace via principal component adaptation. In this work, we present new methods for both incremental and adaptive L1-PCA. Our first algorithm computes L1-PCA incrementally, processing one measurement at a time and performing online rejection of possible outliers; due to its low computational and storage cost, this algorithm is appropriate for application to both large and streaming datasets. Our second algorithm combines the merits of the first one with the additional ability to track changes in the nominal signal subspace. The proposed algorithms are evaluated with experimental studies on subspace estimation/tracking, video surveillance, image conditioning, and direction-of-arrival (DoA) estimation/tracking.

4 January 2023 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
ATAbu Md Niamul Taufique
Abu Md Niamul Taufique
CJChowdhury Sadman Jahan
Chowdhury Sadman Jahan
ASAndreas E. Savakis
Andreas E. Savakis
Domain Adaptation (DA) techniques aim to overcome the domain shift between the source domain used for training and the target domain where testing takes place. However, current DA methods assume that the entire target domain is available during adaptation, which may not hold in practice. We introduce a new, data-constrained DA paradigm where unlabeled target samples are received in batches and adaptation is performed continually. We propose a novel source-free method for continual unsupervised domain adaptation that utilizes a buffer for selective replay of previously seen samples. In our continual DA framework, we selectively mix samples from incoming batches with data stored in a buffer using buffer management strategies and use the combination to incrementally update our model. We evaluate and compare the classification performance of the continual DA approach with state-of-the-art (SOTA) DA methods based on the entire target domain. Our results on three popular DA datasets demonstrate the benefits of our method when operating in data constrained environments. We further extend our experiments to adapting over multiple target domains and our method performs favorably with the SOTA methods.

11 November 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Udit SharmaUdit Sharma
Udit Sharma
Bruno ArtachoBruno Artacho
Bruno Artacho
ASAndreas E. Savakis
Andreas E. Savakis
We propose GourmetNet, a single-pass, end-to-end trainable network for food segmentation that achieves state-of-the-art performance. Food segmentation is an important problem as the first step for nutrition monitoring, food volume and calorie estimation. Our novel architecture incorporates both channel attention and spatial attention information in an expanded multi-scale feature representation using our advanced Waterfall Atrous Spatial Pooling module. GourmetNet refines the feature extraction process by merging features from multiple levels of the backbone through the two attention modules. The refined features are processed with the advanced multi-scale waterfall module that combines the benefits of cascade filtering and pyramid representations without requiring a separate decoder or post-processing. Our experiments on two food datasets show that GourmetNet significantly outperforms existing current state-of-the-art methods.