---
OA_place: repository
OA_type: green
_id: '18956'
abstract:
- lang: eng
  text: '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'
article_processing_charge: No
arxiv: 1
author:
- first_name: Berker
  full_name: Demirel, Berker
  id: 8b4bc47f-3200-11ee-973b-8f0e7be21a9f
  last_name: Demirel
- first_name: Huseyin
  full_name: Ozkan, Huseyin
  last_name: Ozkan
citation:
  ama: 'Demirel B, Ozkan H. Decompl: Decompositional learning with attention pooling
    for group activity recognition from a single volleyball image. In: <i>2024 IEEE
    International Conference on Image Processing</i>. IEEE; 2024:977-983. doi:<a href="https://doi.org/10.1109/icip51287.2024.10647499">10.1109/icip51287.2024.10647499</a>'
  apa: 'Demirel, B., &#38; Ozkan, H. (2024). Decompl: Decompositional learning with
    attention pooling for group activity recognition from a single volleyball image.
    In <i>2024 IEEE International Conference on Image Processing</i> (pp. 977–983).
    Abu Dhabi, United Arab Emirates: IEEE. <a href="https://doi.org/10.1109/icip51287.2024.10647499">https://doi.org/10.1109/icip51287.2024.10647499</a>'
  chicago: 'Demirel, Berker, and Huseyin Ozkan. “Decompl: Decompositional Learning
    with Attention Pooling for Group Activity Recognition from a Single Volleyball
    Image.” In <i>2024 IEEE International Conference on Image Processing</i>, 977–83.
    IEEE, 2024. <a href="https://doi.org/10.1109/icip51287.2024.10647499">https://doi.org/10.1109/icip51287.2024.10647499</a>.'
  ieee: 'B. Demirel and H. Ozkan, “Decompl: Decompositional learning with attention
    pooling for group activity recognition from a single volleyball image,” in <i>2024
    IEEE International Conference on Image Processing</i>, Abu Dhabi, United Arab
    Emirates, 2024, pp. 977–983.'
  ista: 'Demirel B, Ozkan H. 2024. Decompl: Decompositional learning with attention
    pooling for group activity recognition from a single volleyball image. 2024 IEEE
    International Conference on Image Processing. ICIP: International Conference on
    Image Processing, 977–983.'
  mla: 'Demirel, Berker, and Huseyin Ozkan. “Decompl: Decompositional Learning with
    Attention Pooling for Group Activity Recognition from a Single Volleyball Image.”
    <i>2024 IEEE International Conference on Image Processing</i>, IEEE, 2024, pp.
    977–83, doi:<a href="https://doi.org/10.1109/icip51287.2024.10647499">10.1109/icip51287.2024.10647499</a>.'
  short: B. Demirel, H. Ozkan, in:, 2024 IEEE International Conference on Image Processing,
    IEEE, 2024, pp. 977–983.
conference:
  end_date: 2024-10-30
  location: Abu Dhabi, United Arab Emirates
  name: 'ICIP: International Conference on Image Processing'
  start_date: 2024-10-27
corr_author: '1'
date_created: 2025-01-29T12:22:24Z
date_published: 2024-11-01T00:00:00Z
date_updated: 2025-09-09T12:13:12Z
day: '01'
department:
- _id: FrLo
doi: 10.1109/icip51287.2024.10647499
external_id:
  arxiv:
  - '2303.06439'
  isi:
  - '001442947000143'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.48550/arXiv.2303.06439
month: '11'
oa: 1
oa_version: Preprint
page: 977-983
publication: 2024 IEEE International Conference on Image Processing
publication_identifier:
  eisbn:
  - '9798350349399'
  eissn:
  - 2381-8549
publication_status: published
publisher: IEEE
quality_controlled: '1'
related_material:
  link:
  - relation: software
    url: https://github.com/berkerdemirel/decompl
status: public
title: 'Decompl: Decompositional learning with attention pooling for group activity
  recognition from a single volleyball image'
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
year: '2024'
...
---
_id: '18256'
abstract:
- lang: eng
  text: '"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.'
article_number: '8803807'
article_processing_charge: No
arxiv: 1
author:
- first_name: Nir
  full_name: Diamant, Nir
  last_name: Diamant
- first_name: Dean
  full_name: Zadok, Dean
  last_name: Zadok
- first_name: Chaim
  full_name: Baskin, Chaim
  last_name: Baskin
- first_name: Eli
  full_name: Schwartz, Eli
  last_name: Schwartz
- first_name: Alexander
  full_name: Bronstein, Alexander
  id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
  last_name: Bronstein
  orcid: 0000-0001-9699-8730
citation:
  ama: 'Diamant N, Zadok D, Baskin C, Schwartz E, Bronstein AM. Beholder-Gan: Generation
    and beautification of facial images with conditioning on their beauty level. In:
    <i>2019 IEEE International Conference on Image Processing (ICIP)</i>. IEEE; 2019.
    doi:<a href="https://doi.org/10.1109/icip.2019.8803807">10.1109/icip.2019.8803807</a>'
  apa: 'Diamant, N., Zadok, D., Baskin, C., Schwartz, E., &#38; Bronstein, A. M. (2019).
    Beholder-Gan: Generation and beautification of facial images with conditioning
    on their beauty level. In <i>2019 IEEE International Conference on Image Processing
    (ICIP)</i>. Taipei, Taiwan: IEEE. <a href="https://doi.org/10.1109/icip.2019.8803807">https://doi.org/10.1109/icip.2019.8803807</a>'
  chicago: 'Diamant, Nir, Dean Zadok, Chaim Baskin, Eli Schwartz, and Alex M. Bronstein.
    “Beholder-Gan: Generation and Beautification of Facial Images with Conditioning
    on Their Beauty Level.” In <i>2019 IEEE International Conference on Image Processing
    (ICIP)</i>. IEEE, 2019. <a href="https://doi.org/10.1109/icip.2019.8803807">https://doi.org/10.1109/icip.2019.8803807</a>.'
  ieee: 'N. Diamant, D. Zadok, C. Baskin, E. Schwartz, and A. M. Bronstein, “Beholder-Gan:
    Generation and beautification of facial images with conditioning on their beauty
    level,” in <i>2019 IEEE International Conference on Image Processing (ICIP)</i>,
    Taipei, Taiwan, 2019.'
  ista: 'Diamant N, Zadok D, Baskin C, Schwartz E, Bronstein AM. 2019. Beholder-Gan:
    Generation and beautification of facial images with conditioning on their beauty
    level. 2019 IEEE International Conference on Image Processing (ICIP). 26th IEEE
    International Conference on Image Processing, 8803807.'
  mla: 'Diamant, Nir, et al. “Beholder-Gan: Generation and Beautification of Facial
    Images with Conditioning on Their Beauty Level.” <i>2019 IEEE International Conference
    on Image Processing (ICIP)</i>, 8803807, IEEE, 2019, doi:<a href="https://doi.org/10.1109/icip.2019.8803807">10.1109/icip.2019.8803807</a>.'
  short: N. Diamant, D. Zadok, C. Baskin, E. Schwartz, A.M. Bronstein, in:, 2019 IEEE
    International Conference on Image Processing (ICIP), IEEE, 2019.
conference:
  end_date: 2019-09-25
  location: Taipei, Taiwan
  name: 26th IEEE International Conference on Image Processing
  start_date: 2019-09-22
date_created: 2024-10-08T13:07:32Z
date_published: 2019-08-26T00:00:00Z
date_updated: 2024-12-05T15:59:29Z
day: '26'
doi: 10.1109/icip.2019.8803807
extern: '1'
external_id:
  arxiv:
  - '1902.02593'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.48550/arXiv.1902.02593
month: '08'
oa: 1
oa_version: Preprint
publication: 2019 IEEE International Conference on Image Processing (ICIP)
publication_identifier:
  eissn:
  - 2381-8549
  isbn:
  - '9781538662502'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Beholder-Gan: Generation and beautification of facial images with conditioning
  on their beauty level'
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2019'
...
---
_id: '18402'
abstract:
- lang: eng
  text: 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.
article_processing_charge: No
author:
- first_name: Tal
  full_name: Remez, Tal
  last_name: Remez
- first_name: Or
  full_name: Litany, Or
  last_name: Litany
- first_name: Raja
  full_name: Giryes, Raja
  last_name: Giryes
- first_name: Alexander
  full_name: Bronstein, Alexander
  id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
  last_name: Bronstein
  orcid: 0000-0001-9699-8730
citation:
  ama: 'Remez T, Litany O, Giryes R, Bronstein AM. Deep class-aware image denoising.
    In: <i>2017 IEEE International Conference on Image Processing (ICIP)</i>. IEEE;
    2018:1895-1899. doi:<a href="https://doi.org/10.1109/icip.2017.8296611">10.1109/icip.2017.8296611</a>'
  apa: 'Remez, T., Litany, O., Giryes, R., &#38; Bronstein, A. M. (2018). Deep class-aware
    image denoising. In <i>2017 IEEE International Conference on Image Processing
    (ICIP)</i> (pp. 1895–1899). Beijing, China: IEEE. <a href="https://doi.org/10.1109/icip.2017.8296611">https://doi.org/10.1109/icip.2017.8296611</a>'
  chicago: Remez, Tal, Or Litany, Raja Giryes, and Alex M. Bronstein. “Deep Class-Aware
    Image Denoising.” In <i>2017 IEEE International Conference on Image Processing
    (ICIP)</i>, 1895–99. IEEE, 2018. <a href="https://doi.org/10.1109/icip.2017.8296611">https://doi.org/10.1109/icip.2017.8296611</a>.
  ieee: T. Remez, O. Litany, R. Giryes, and A. M. Bronstein, “Deep class-aware image
    denoising,” in <i>2017 IEEE International Conference on Image Processing (ICIP)</i>,
    Beijing, China, 2018, pp. 1895–1899.
  ista: Remez T, Litany O, Giryes R, Bronstein AM. 2018. Deep class-aware image denoising.
    2017 IEEE International Conference on Image Processing (ICIP). 24th IEEE International
    Conference on Image Processing, 1895–1899.
  mla: Remez, Tal, et al. “Deep Class-Aware Image Denoising.” <i>2017 IEEE International
    Conference on Image Processing (ICIP)</i>, IEEE, 2018, pp. 1895–99, doi:<a href="https://doi.org/10.1109/icip.2017.8296611">10.1109/icip.2017.8296611</a>.
  short: T. Remez, O. Litany, R. Giryes, A.M. Bronstein, in:, 2017 IEEE International
    Conference on Image Processing (ICIP), IEEE, 2018, pp. 1895–1899.
conference:
  end_date: 2017-09-20
  location: Beijing, China
  name: 24th IEEE International Conference on Image Processing
  start_date: 2017-09-17
date_created: 2024-10-15T11:20:54Z
date_published: 2018-02-22T00:00:00Z
date_updated: 2024-12-05T14:00:53Z
day: '22'
doi: 10.1109/icip.2017.8296611
extern: '1'
language:
- iso: eng
month: '02'
oa_version: None
page: 1895 - 1899
publication: 2017 IEEE International Conference on Image Processing (ICIP)
publication_identifier:
  eissn:
  - 2381-8549
  isbn:
  - '9781509021765'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Deep class-aware image denoising
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2018'
...
---
_id: '18400'
abstract:
- lang: eng
  text: 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.
article_number: '7025264'
article_processing_charge: No
author:
- first_name: Ohad
  full_name: Menashe, Ohad
  last_name: Menashe
- first_name: Alexander
  full_name: Bronstein, Alexander
  id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
  last_name: Bronstein
  orcid: 0000-0001-9699-8730
citation:
  ama: 'Menashe O, Bronstein AM. Real-time compressed imaging of scattering volumes.
    In: <i>2014 IEEE International Conference on Image Processing (ICIP)</i>. IEEE;
    2015. doi:<a href="https://doi.org/10.1109/icip.2014.7025264">10.1109/icip.2014.7025264</a>'
  apa: 'Menashe, O., &#38; Bronstein, A. M. (2015). Real-time compressed imaging of
    scattering volumes. In <i>2014 IEEE International Conference on Image Processing
    (ICIP)</i>. Paris, France: IEEE. <a href="https://doi.org/10.1109/icip.2014.7025264">https://doi.org/10.1109/icip.2014.7025264</a>'
  chicago: Menashe, Ohad, and Alex M. Bronstein. “Real-Time Compressed Imaging of
    Scattering Volumes.” In <i>2014 IEEE International Conference on Image Processing
    (ICIP)</i>. IEEE, 2015. <a href="https://doi.org/10.1109/icip.2014.7025264">https://doi.org/10.1109/icip.2014.7025264</a>.
  ieee: O. Menashe and A. M. Bronstein, “Real-time compressed imaging of scattering
    volumes,” in <i>2014 IEEE International Conference on Image Processing (ICIP)</i>,
    Paris, France, 2015.
  ista: Menashe O, Bronstein AM. 2015. Real-time compressed imaging of scattering
    volumes. 2014 IEEE International Conference on Image Processing (ICIP). IEEE International
    Conference on Image Processing, 7025264.
  mla: Menashe, Ohad, and Alex M. Bronstein. “Real-Time Compressed Imaging of Scattering
    Volumes.” <i>2014 IEEE International Conference on Image Processing (ICIP)</i>,
    7025264, IEEE, 2015, doi:<a href="https://doi.org/10.1109/icip.2014.7025264">10.1109/icip.2014.7025264</a>.
  short: O. Menashe, A.M. Bronstein, in:, 2014 IEEE International Conference on Image
    Processing (ICIP), IEEE, 2015.
conference:
  end_date: 2014-10-30
  location: Paris, France
  name: IEEE International Conference on Image Processing
  start_date: 2014-10-27
date_created: 2024-10-15T11:20:54Z
date_published: 2015-01-29T00:00:00Z
date_updated: 2024-12-04T13:56:28Z
day: '29'
doi: 10.1109/icip.2014.7025264
extern: '1'
language:
- iso: eng
month: '01'
oa_version: None
publication: 2014 IEEE International Conference on Image Processing (ICIP)
publication_identifier:
  eisbn:
  - '9781479957514'
  eissn:
  - 2381-8549
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Real-time compressed imaging of scattering volumes
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2015'
...