Richard J. Radke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Richard J. Radke has a total of 152 co-authors. Here are the top co-authors by number of shared publications:
Srikrishna Karanam
United Imaging Intelligence Cambridge MA USA
14 shared publications- Ziyan Wu
United Imaging Intelligence
11 shared publications Yang Li
Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA
8 shared publicationsZiyan Wu
United Imaging Intelligence Cambridge MA USA
8 shared publicationsIndrani Bhattacharya
Rensselaer Polytechnic Institute, USA
6 shared publications- John T. Wen
Rensselaer Polytechnic Institute, Troy, NY, USA
5 shared publications
Latest Publications
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 284-293
Beyond Utterance: Understanding Group Problem Solving through Discussion Sequences
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 284-293
Open AccessBeyond Utterance: Understanding Group Problem Solving through Discussion Sequences
- Open Access
Detecting Contextual Anomalies by Discovering Consistent Spatial Regions
We describe a method for modeling spatial context to enable video anomaly detection. The main idea is to discover regions that share similar object-level activities by clustering joint object attributes using Gaussian mixture models. We demonstrate that this straightforward approach, using orders of magnitude fewer parameters than competing models, achieves state-of-the-art performance in the challenging spatial-context-dependent Street Scene dataset. As a side benefit, the high-resolution discovered regions learned by the model also provide explainable normalcy maps for human operators without the need for any pre-trained segmentation model.
Open AccessDetecting Contextual Anomalies by Discovering Consistent Spatial Regions
We describe a method for modeling spatial context to enable video anomaly detection. The main idea is to discover regions that share similar object-level activities by clustering joint object attributes using Gaussian mixture models. We demonstrate that this straightforward approach, using orders of magnitude fewer parameters than competing models, achieves state-of-the-art performance in the challenging spatial-context-dependent Street Scene dataset. As a side benefit, the high-resolution discovered regions learned by the model also provide explainable normalcy maps for human operators without the need for any pre-trained segmentation model.
- Open Access
- 7 November 2024
- Published by Elsevier in Computers in Human Behavior: Artificial Humans
- Vol. 2 (2)
How voice and helpfulness shape perceptions in human–agent teams
- 7 November 2024
- Published by Elsevier in Computers in Human Behavior: Artificial Humans
- Vol. 2 (2)
Open AccessHow voice and helpfulness shape perceptions in human–agent teams
- 3 October 2024
- Published by Springer Nature
- p. 286-296
Few-Shot 3D Volumetric Segmentation with Multi-surrogate Fusion
- 3 October 2024
- Published by Springer Nature
- p. 286-296
Few-Shot 3D Volumetric Segmentation with Multi-surrogate Fusion
- Open Access
Few-Shot 3D Volumetric Segmentation with Multi-Surrogate Fusion
Conventional 3D medical image segmentation methods typically require learning heavy 3D networks (e.g., 3D-UNet), as well as large amounts of in-domain data with accurate pixel/voxel-level labels to avoid overfitting. These solutions are thus extremely time- and labor-expensive, but also may easily fail to generalize to unseen objects during training. To alleviate this issue, we present MSFSeg, a novel few-shot 3D segmentation framework with a lightweight multi-surrogate fusion (MSF). MSFSeg is able to automatically segment unseen 3D objects/organs (during training) provided with one or a few annotated 2D slices or 3D sequence segments, via learning dense query-support organ/lesion anatomy correlations across patient populations. Our proposed MSF module mines comprehensive and diversified morphology correlations between unlabeled and the few labeled slices/sequences through multiple designated surrogates, making it able to generate accurate cross-domain 3D segmentation masks given annotated slices or sequences. We demonstrate the effectiveness of our proposed framework by showing superior performance on conventional few-shot segmentation benchmarks compared to prior art, and remarkable cross-domain cross-volume segmentation performance on proprietary 3D segmentation datasets for challenging entities, i.e., tubular structures, with only limited 2D or 3D labels.
Open AccessFew-Shot 3D Volumetric Segmentation with Multi-Surrogate Fusion
Conventional 3D medical image segmentation methods typically require learning heavy 3D networks (e.g., 3D-UNet), as well as large amounts of in-domain data with accurate pixel/voxel-level labels to avoid overfitting. These solutions are thus extremely time- and labor-expensive, but also may easily fail to generalize to unseen objects during training. To alleviate this issue, we present MSFSeg, a novel few-shot 3D segmentation framework with a lightweight multi-surrogate fusion (MSF). MSFSeg is able to automatically segment unseen 3D objects/organs (during training) provided with one or a few annotated 2D slices or 3D sequence segments, via learning dense query-support organ/lesion anatomy correlations across patient populations. Our proposed MSF module mines comprehensive and diversified morphology correlations between unlabeled and the few labeled slices/sequences through multiple designated surrogates, making it able to generate accurate cross-domain 3D segmentation masks given annotated slices or sequences. We demonstrate the effectiveness of our proposed framework by showing superior performance on conventional few-shot segmentation benchmarks compared to prior art, and remarkable cross-domain cross-volume segmentation performance on proprietary 3D segmentation datasets for challenging entities, i.e., tubular structures, with only limited 2D or 3D labels.
- Open Access
Context-aware Video Anomaly Detection in Long-Term Datasets
Video anomaly detection research is generally evaluated on short, isolated benchmark videos only a few minutes long. However, in real-world environments, security cameras observe the same scene for months or years at a time, and the notion of anomalous behavior critically depends on context, such as the time of day, day of week, or schedule of events. Here, we propose a context-aware video anomaly detection algorithm, Trinity, specifically targeted to these scenarios. Trinity is especially well-suited to crowded scenes in which individuals cannot be easily tracked, and anomalies are due to speed, direction, or absence of group motion. Trinity is a contrastive learning framework that aims to learn alignments between context, appearance, and motion, and uses alignment quality to classify videos as normal or anomalous. We evaluate our algorithm on both conventional benchmarks and a public webcam-based dataset we collected that spans more than three months of activity.
Open AccessContext-aware Video Anomaly Detection in Long-Term Datasets
Video anomaly detection research is generally evaluated on short, isolated benchmark videos only a few minutes long. However, in real-world environments, security cameras observe the same scene for months or years at a time, and the notion of anomalous behavior critically depends on context, such as the time of day, day of week, or schedule of events. Here, we propose a context-aware video anomaly detection algorithm, Trinity, specifically targeted to these scenarios. Trinity is especially well-suited to crowded scenes in which individuals cannot be easily tracked, and anomalies are due to speed, direction, or absence of group motion. Trinity is a contrastive learning framework that aims to learn alignments between context, appearance, and motion, and uses alignment quality to classify videos as normal or anomalous. We evaluate our algorithm on both conventional benchmarks and a public webcam-based dataset we collected that spans more than three months of activity.
- 1 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Magazine
- Vol. 41 (2) , 6-10
A Signal Processor Teaches Generative Artificial Intelligence [SP Education]
How did an “old dog” signal processing professor approach learning and teaching the “new tricks” of generative artificial intelligence (AI)? This article overviews my recent experience in preparing and delivering a new course called “Computational Creativity,” reflecting on the methods I adopted compared to a traditional equations-on-a-whiteboard course. The technical material is qualitatively different from traditional signal processing, and the types of students who took the class and their approach to learning were different too. I learned a lot from the experience but also came away with bigger questions about the role of educators in the age of generative AI.
- 1 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Magazine
- Vol. 41 (2) , 6-10
A Signal Processor Teaches Generative Artificial Intelligence [SP Education]
How did an “old dog” signal processing professor approach learning and teaching the “new tricks” of generative artificial intelligence (AI)? This article overviews my recent experience in preparing and delivering a new course called “Computational Creativity,” reflecting on the methods I adopted compared to a traditional equations-on-a-whiteboard course. The technical material is qualitatively different from traditional signal processing, and the types of students who took the class and their approach to learning were different too. I learned a lot from the experience but also came away with bigger questions about the role of educators in the age of generative AI.
- Open Access
- 1 July 2022
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 2, 1728-1735
Visual Similarity Attention
Electronic proceedings of IJCAI 2022
- 1 July 2022
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 2, 1728-1735
Open AccessVisual Similarity Attention
Electronic proceedings of IJCAI 2022
- Open Access
Visual Similarity Attention
While there has been substantial progress in learning suitable distance metrics, these techniques in general lack transparency and decision reasoning, i.e., explaining why the input set of images is similar or dissimilar. In this work, we solve this key problem by proposing the first method to generate generic visual similarity explanations with gradient-based attention. We demonstrate that our technique is agnostic to the specific similarity model type, e.g., we show applicability to Siamese, triplet, and quadruplet models. Furthermore, we make our proposed similarity attention a principled part of the learning process, resulting in a new paradigm for learning similarity functions. We demonstrate that our learning mechanism results in more generalizable, as well as explainable, similarity models. Finally, we demonstrate the generality of our framework by means of experiments on a variety of tasks, including image retrieval, person re-identification, and low-shot semantic segmentation.
Open AccessVisual Similarity Attention
While there has been substantial progress in learning suitable distance metrics, these techniques in general lack transparency and decision reasoning, i.e., explaining why the input set of images is similar or dissimilar. In this work, we solve this key problem by proposing the first method to generate generic visual similarity explanations with gradient-based attention. We demonstrate that our technique is agnostic to the specific similarity model type, e.g., we show applicability to Siamese, triplet, and quadruplet models. Furthermore, we make our proposed similarity attention a principled part of the learning process, resulting in a new paradigm for learning similarity functions. We demonstrate that our learning mechanism results in more generalizable, as well as explainable, similarity models. Finally, we demonstrate the generality of our framework by means of experiments on a variety of tasks, including image retrieval, person re-identification, and low-shot semantic segmentation.
- 1 December 2021
- Published by Elsevier in Energy and Buildings
- Vol. 252, 111390
A zone-level occupancy counting system for commercial office spaces using low-resolution time-of-flight sensors
- 1 December 2021
- Published by Elsevier in Energy and Buildings
- Vol. 252, 111390
A zone-level occupancy counting system for commercial office spaces using low-resolution time-of-flight sensors