@inproceedings{18956,
  abstract     = {Group Activity Recognition (GAR) aims to detect the activity performed by multiple actors in a scene. Prior works model the spatio-temporal features based on the RGB, optical flow or keypoint data types. On the contrary, our hypothesis is that by only using the RGB data without temporality, the performance can be maintained with a negligible loss in accuracy. To that end, we propose a novel GAR technique for volleyball videos, DECOMPL, which consists of two complementary branches. In the visual branch, it extracts the features using attention pooling. In the coordinate branch, it considers the configuration of the players and extracts the spatial information from the box coordinates. Moreover, we analyzed the Volleyball dataset that the recent literature is mostly based on, and systematically reannotated it to emphasize the group concept. Experimental results demonstrated the effectiveness of the proposed model DECOMPL, which delivered the best/second best GAR performance with the reannotations/original annotations among the comparable state-of-the-art methods. Code and new annotations are available at GitHub: https://github.com/berkerdemirel/decompl},
  author       = {Demirel, Berker and Ozkan, Huseyin},
  booktitle    = {2024 IEEE International Conference on Image Processing},
  issn         = {2381-8549},
  location     = {Abu Dhabi, United Arab Emirates},
  pages        = {977--983},
  publisher    = {IEEE},
  title        = {{Decompl: Decompositional learning with attention pooling for group activity recognition from a single volleyball image}},
  doi          = {10.1109/icip51287.2024.10647499},
  year         = {2024},
}

@inproceedings{18256,
  abstract     = {"Beauty is in the eye of the beholder." This maxim, emphasizing the subjectivity of the perception of beauty, has enjoyed a wide consensus since ancient times. In the digital era, data-driven methods have been shown to be able to predict human-assigned beauty scores for facial images. In this work, we augment this ability and train a generative model that generates faces conditioned on a requested beauty score. In addition, we show how this trained generator can be used to "beautify" an input face image. By doing so, we achieve an unsupervised beautification model, in the sense that it relies on no ground truth target images. Our implementation is available on: https://github.com/beholdergan/Beholder-GAN.},
  author       = {Diamant, Nir and Zadok, Dean and Baskin, Chaim and Schwartz, Eli and Bronstein, Alexander},
  booktitle    = {2019 IEEE International Conference on Image Processing (ICIP)},
  isbn         = {9781538662502},
  issn         = {2381-8549},
  location     = {Taipei, Taiwan},
  publisher    = {IEEE},
  title        = {{Beholder-Gan: Generation and beautification of facial images with conditioning on their beauty level}},
  doi          = {10.1109/icip.2019.8803807},
  year         = {2019},
}

@inproceedings{18402,
  abstract     = {The increasing demand for high image quality in mobile devices brings forth the need for better computational enhancement techniques, and image denoising in particular. To this end, we propose a new fully convolutional deep neural network architecture which is simple yet powerful and achieves state-of-the-art performance for additive Gaussian noise removal. Furthermore, we claim that the personal photo-collections can usually be categorized into a small set of semantic classes. However simple, this observation has not been exploited in image denoising until now. We show that a significant boost in performance of up to 0.4dB PSNR can be achieved by making our network class-aware, namely, by fine-tuning it for images belonging to a specific semantic class. Relying on the hugely successful existing image classifiers, this research advocates for using a class-aware approach in all image enhancement tasks.},
  author       = {Remez, Tal and Litany, Or and Giryes, Raja and Bronstein, Alexander},
  booktitle    = {2017 IEEE International Conference on Image Processing (ICIP)},
  isbn         = {9781509021765},
  issn         = {2381-8549},
  location     = {Beijing, China},
  pages        = {1895 -- 1899},
  publisher    = {IEEE},
  title        = {{Deep class-aware image denoising}},
  doi          = {10.1109/icip.2017.8296611},
  year         = {2018},
}

@inproceedings{18400,
  abstract     = {We propose a method and a prototype imaging system for real-time reconstruction of volumetric piecewise-smooth scattering media. The volume is illuminated by a sequence of structured binary patterns emitted from a fan beam projector, and the scattered light is collected by a two-dimensional sensor, thus creating an under-complete set of compressed measurements. We show a fixed-complexity and latency reconstruction algorithm capable of estimating the scattering coefficients in real-time. We also show a simple greedy algorithm for learning the optimal illumination patterns. Our results demonstrate faithful reconstruction from highly compressed measurements. Furthermore, a method for compressed registration of the measured volume to a known template is presented, showing excellent alignment with just a single projection. Though our prototype system operates in visible light, the presented methodology is suitable for fast x-ray scattering imaging, in particular in real-time vascular medical imaging.},
  author       = {Menashe, Ohad and Bronstein, Alexander},
  booktitle    = {2014 IEEE International Conference on Image Processing (ICIP)},
  issn         = {2381-8549},
  location     = {Paris, France},
  publisher    = {IEEE},
  title        = {{Real-time compressed imaging of scattering volumes}},
  doi          = {10.1109/icip.2014.7025264},
  year         = {2015},
}