Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Bernard Ghanem

Bernard Ghanem

Relation-aware Video Reading Comprehension for Temporal Language Grounding


Oct 12, 2021
Jialin Gao, Xin Sun, Mengmeng Xu, Xi Zhou, Bernard Ghanem

Figure 1 for Relation-aware Video Reading Comprehension for Temporal Language Grounding
Figure 2 for Relation-aware Video Reading Comprehension for Temporal Language Grounding
Figure 3 for Relation-aware Video Reading Comprehension for Temporal Language Grounding
Figure 4 for Relation-aware Video Reading Comprehension for Temporal Language Grounding
* Accepted by EMNLP-21 
  Access Paper or Ask Questions

MovieCuts: A New Dataset and Benchmark for Cut Type Recognition


Sep 19, 2021
Alejandro Pardo, Fabian Caba Heilbron, Juan Le贸n Alc谩zar, Ali Thabet, Bernard Ghanem

Figure 1 for MovieCuts: A New Dataset and Benchmark for Cut Type Recognition
Figure 2 for MovieCuts: A New Dataset and Benchmark for Cut Type Recognition
Figure 3 for MovieCuts: A New Dataset and Benchmark for Cut Type Recognition
Figure 4 for MovieCuts: A New Dataset and Benchmark for Cut Type Recognition
* Paper's website: https://www.alejandropardo.net/publication/moviecuts/ 
  Access Paper or Ask Questions

Check Your Other Door! Establishing Backdoor Attacks in the Frequency Domain


Sep 12, 2021
Hasan Abed Al Kader Hammoud, Bernard Ghanem

Figure 1 for Check Your Other Door! Establishing Backdoor Attacks in the Frequency Domain
Figure 2 for Check Your Other Door! Establishing Backdoor Attacks in the Frequency Domain
Figure 3 for Check Your Other Door! Establishing Backdoor Attacks in the Frequency Domain
Figure 4 for Check Your Other Door! Establishing Backdoor Attacks in the Frequency Domain

  Access Paper or Ask Questions

Learning to Cut by Watching Movies


Aug 09, 2021
Alejandro Pardo, Fabian Caba Heilbron, Juan Le贸n Alc谩zar, Ali Thabet, Bernard Ghanem

Figure 1 for Learning to Cut by Watching Movies
Figure 2 for Learning to Cut by Watching Movies
Figure 3 for Learning to Cut by Watching Movies
Figure 4 for Learning to Cut by Watching Movies
* Accepted at ICCV2021. Paper website: https://alejandropardo.net/publication/learning-to-cut/ 
  Access Paper or Ask Questions

Enhancing Adversarial Robustness via Test-time Transformation Ensembling


Jul 29, 2021
Juan C. P茅rez, Motasem Alfarra, Guillaume Jeanneret, Laura Rueda, Ali Thabet, Bernard Ghanem, Pablo Arbel谩ez

Figure 1 for Enhancing Adversarial Robustness via Test-time Transformation Ensembling
Figure 2 for Enhancing Adversarial Robustness via Test-time Transformation Ensembling
Figure 3 for Enhancing Adversarial Robustness via Test-time Transformation Ensembling
Figure 4 for Enhancing Adversarial Robustness via Test-time Transformation Ensembling

  Access Paper or Ask Questions

ANCER: Anisotropic Certification via Sample-wise Volume Maximization


Jul 20, 2021
Francisco Eiras, Motasem Alfarra, M. Pawan Kumar, Philip H. S. Torr, Puneet K. Dokania, Bernard Ghanem, Adel Bibi

Figure 1 for ANCER: Anisotropic Certification via Sample-wise Volume Maximization
Figure 2 for ANCER: Anisotropic Certification via Sample-wise Volume Maximization
Figure 3 for ANCER: Anisotropic Certification via Sample-wise Volume Maximization
Figure 4 for ANCER: Anisotropic Certification via Sample-wise Volume Maximization
* First two authors and the last one contributed equally to this work 
  Access Paper or Ask Questions

DeformRS: Certifying Input Deformations with Randomized Smoothing


Jul 02, 2021
Motasem Alfarra, Adel Bibi, Naeemullah Khan, Philip H. S. Torr, Bernard Ghanem

Figure 1 for DeformRS: Certifying Input Deformations with Randomized Smoothing
Figure 2 for DeformRS: Certifying Input Deformations with Randomized Smoothing
Figure 3 for DeformRS: Certifying Input Deformations with Randomized Smoothing
Figure 4 for DeformRS: Certifying Input Deformations with Randomized Smoothing
* First two authors contributed equally to this work 
  Access Paper or Ask Questions

Training Graph Neural Networks with 1000 Layers


Jun 17, 2021
Guohao Li, Matthias M眉ller, Bernard Ghanem, Vladlen Koltun

Figure 1 for Training Graph Neural Networks with 1000 Layers
Figure 2 for Training Graph Neural Networks with 1000 Layers
Figure 3 for Training Graph Neural Networks with 1000 Layers
Figure 4 for Training Graph Neural Networks with 1000 Layers
* Accepted at ICML'2021. Code available at https://www.deepgcns.org/arch/gnn1000. Work done during Guohao Li's internship at Intel Intelligent Systems Lab 
  Access Paper or Ask Questions

APES: Audiovisual Person Search in Untrimmed Video


Jun 03, 2021
Juan Leon Alcazar, Long Mai, Federico Perazzi, Joon-Young Lee, Pablo Arbelaez, Bernard Ghanem, Fabian Caba Heilbron

Figure 1 for APES: Audiovisual Person Search in Untrimmed Video
Figure 2 for APES: Audiovisual Person Search in Untrimmed Video
Figure 3 for APES: Audiovisual Person Search in Untrimmed Video
Figure 4 for APES: Audiovisual Person Search in Untrimmed Video

  Access Paper or Ask Questions

SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation


Jun 02, 2021
Bing Li, Cheng Zheng, Silvio Giancola, Bernard Ghanem

Figure 1 for SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Figure 2 for SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Figure 3 for SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Figure 4 for SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation

  Access Paper or Ask Questions

Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting


Apr 19, 2021
Anthony Cioppa, Adrien Deli猫ge, Floriane Magera, Silvio Giancola, Olivier Barnich, Bernard Ghanem, Marc Van Droogenbroeck

Figure 1 for Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
Figure 2 for Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
Figure 3 for Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
Figure 4 for Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
* Paper accepted at the CVsports workshop at CVPR2021 
  Access Paper or Ask Questions

Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts


Apr 14, 2021
Silvio Giancola, Bernard Ghanem

Figure 1 for Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts
Figure 2 for Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts
Figure 3 for Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts
Figure 4 for Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts
* 8 pages, Camera-Ready for CVSports 2021 (CVPRW) 
  Access Paper or Ask Questions

Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization


Mar 30, 2021
Mengmeng Xu, Juan-Manuel Perez-Rua, Xiatian Zhu, Bernard Ghanem, Brais Martinez

Figure 1 for Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
Figure 2 for Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
Figure 3 for Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
Figure 4 for Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
* 10 pages, 2 figures 
  Access Paper or Ask Questions

Combating Adversaries with Anti-Adversaries


Mar 26, 2021
Motasem Alfarra, Juan C. P茅rez, Ali Thabet, Adel Bibi, Philip H. S. Torr, Bernard Ghanem

Figure 1 for Combating Adversaries with Anti-Adversaries
Figure 2 for Combating Adversaries with Anti-Adversaries
Figure 3 for Combating Adversaries with Anti-Adversaries
Figure 4 for Combating Adversaries with Anti-Adversaries
* 15 pages, 5 figures, 7 tables 
  Access Paper or Ask Questions

AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation


Feb 24, 2021
Bing Li, Yuanlue Zhu, Yitong Wang, Chia-Wen Lin, Bernard Ghanem, Linlin Shen

Figure 1 for AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
Figure 2 for AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
Figure 3 for AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
Figure 4 for AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation

  Access Paper or Ask Questions

MAAS: Multi-modal Assignation for Active Speaker Detection


Jan 11, 2021
Juan Le贸n-Alc谩zar, Fabian Caba Heilbron, Ali Thabet, Bernard Ghanem

Figure 1 for MAAS: Multi-modal Assignation for Active Speaker Detection
Figure 2 for MAAS: Multi-modal Assignation for Active Speaker Detection
Figure 3 for MAAS: Multi-modal Assignation for Active Speaker Detection
Figure 4 for MAAS: Multi-modal Assignation for Active Speaker Detection

  Access Paper or Ask Questions

SALA: Soft Assignment Local Aggregation for 3D Semantic Segmentation


Dec 29, 2020
Hani Itani, Silvio Giancola, Ali Thabet, Bernard Ghanem

Figure 1 for SALA: Soft Assignment Local Aggregation for 3D Semantic Segmentation
Figure 2 for SALA: Soft Assignment Local Aggregation for 3D Semantic Segmentation
Figure 3 for SALA: Soft Assignment Local Aggregation for 3D Semantic Segmentation
Figure 4 for SALA: Soft Assignment Local Aggregation for 3D Semantic Segmentation

  Access Paper or Ask Questions

Video Self-Stitching Graph Network for Temporal Action Localization


Dec 13, 2020
Chen Zhao, Ali Thabet, Bernard Ghanem

Figure 1 for Video Self-Stitching Graph Network for Temporal Action Localization
Figure 2 for Video Self-Stitching Graph Network for Temporal Action Localization
Figure 3 for Video Self-Stitching Graph Network for Temporal Action Localization
Figure 4 for Video Self-Stitching Graph Network for Temporal Action Localization

  Access Paper or Ask Questions

Data Dependent Randomized Smoothing


Dec 08, 2020
Motasem Alfarra, Adel Bibi, Philip H. S. Torr, Bernard Ghanem

Figure 1 for Data Dependent Randomized Smoothing
Figure 2 for Data Dependent Randomized Smoothing
Figure 3 for Data Dependent Randomized Smoothing
Figure 4 for Data Dependent Randomized Smoothing
* First two authors contributed equally to this work 
  Access Paper or Ask Questions

SoccerNet-v2 : A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos


Nov 26, 2020
Adrien Deli猫ge, Anthony Cioppa, Silvio Giancola, Meisam J. Seikavandi, Jacob V. Dueholm, Kamal Nasrollahi, Bernard Ghanem, Thomas B. Moeslund, Marc Van Droogenbroeck

Figure 1 for SoccerNet-v2 : A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
Figure 2 for SoccerNet-v2 : A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
Figure 3 for SoccerNet-v2 : A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
Figure 4 for SoccerNet-v2 : A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
* This document contains 8 pages + references + supplementary material 
  Access Paper or Ask Questions

MVTN: Multi-View Transformation Network for 3D Shape Recognition


Nov 26, 2020
Abdullah Hamdi, Silvio Giancola, Bing Li, Ali Thabet, Bernard Ghanem

Figure 1 for MVTN: Multi-View Transformation Network for 3D Shape Recognition
Figure 2 for MVTN: Multi-View Transformation Network for 3D Shape Recognition
Figure 3 for MVTN: Multi-View Transformation Network for 3D Shape Recognition
Figure 4 for MVTN: Multi-View Transformation Network for 3D Shape Recognition
* preprint 
  Access Paper or Ask Questions

Boundary-sensitive Pre-training for Temporal Localization in Videos


Nov 24, 2020
Mengmeng Xu, Juan-Manuel Perez-Rua, Victor Escorcia, Brais Martinez, Xiatian Zhu, Li Zhang, Bernard Ghanem, Tao Xiang

Figure 1 for Boundary-sensitive Pre-training for Temporal Localization in Videos
Figure 2 for Boundary-sensitive Pre-training for Temporal Localization in Videos
Figure 3 for Boundary-sensitive Pre-training for Temporal Localization in Videos
Figure 4 for Boundary-sensitive Pre-training for Temporal Localization in Videos
* 11 pages, 4 figures 
  Access Paper or Ask Questions

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks


Nov 23, 2020
Humam Alwassel, Silvio Giancola, Bernard Ghanem

Figure 1 for TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
Figure 2 for TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
Figure 3 for TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
Figure 4 for TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

  Access Paper or Ask Questions

VLG-Net: Video-Language Graph Matching Network for Video Grounding


Nov 19, 2020
Sisi Qu, Mattia Soldan, Mengmeng Xu, Jesper Tegner, Bernard Ghanem

Figure 1 for VLG-Net: Video-Language Graph Matching Network for Video Grounding
Figure 2 for VLG-Net: Video-Language Graph Matching Network for Video Grounding
Figure 3 for VLG-Net: Video-Language Graph Matching Network for Video Grounding
Figure 4 for VLG-Net: Video-Language Graph Matching Network for Video Grounding
* 12 pages, 5 figures 
  Access Paper or Ask Questions

FLAG: Adversarial Data Augmentation for Graph Neural Networks


Oct 19, 2020
Kezhi Kong, Guohao Li, Mucong Ding, Zuxuan Wu, Chen Zhu, Bernard Ghanem, Gavin Taylor, Tom Goldstein

Figure 1 for FLAG: Adversarial Data Augmentation for Graph Neural Networks
Figure 2 for FLAG: Adversarial Data Augmentation for Graph Neural Networks
Figure 3 for FLAG: Adversarial Data Augmentation for Graph Neural Networks
Figure 4 for FLAG: Adversarial Data Augmentation for Graph Neural Networks

  Access Paper or Ask Questions

LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks


Aug 24, 2020
Guohao Li, Mengmeng Xu, Silvio Giancola, Ali Thabet, Bernard Ghanem

Figure 1 for LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks
Figure 2 for LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks
Figure 3 for LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks
Figure 4 for LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks
* Originally submitted to ECCV'2020 but rejected. This work was filed with the United States Patent and Trademark Office (USPTO) on May 19, 2020 and assigned Serial No. 63/027,241 
  Access Paper or Ask Questions