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

Relation-aware Video Reading Comprehension for Temporal Language Grounding


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

* 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 León Alcázar, Ali Thabet, Bernard Ghanem

* 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


  Access Paper or Ask Questions

Learning to Cut by Watching Movies


Aug 09, 2021
Alejandro Pardo, Fabian Caba Heilbron, Juan León Alcázar, Ali Thabet, Bernard Ghanem

* 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. Pérez, Motasem Alfarra, Guillaume Jeanneret, Laura Rueda, Ali Thabet, Bernard Ghanem, Pablo Arbeláez


  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

* 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

* 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 Müller, Bernard Ghanem, Vladlen Koltun

* 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


  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


  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 Deliège, Floriane Magera, Silvio Giancola, Olivier Barnich, Bernard Ghanem, Marc Van Droogenbroeck

* 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

* 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

* 10 pages, 2 figures 

  Access Paper or Ask Questions

Combating Adversaries with Anti-Adversaries


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

* 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


  Access Paper or Ask Questions

MAAS: Multi-modal Assignation for Active Speaker Detection


Jan 11, 2021
Juan León-Alcázar, Fabian Caba Heilbron, Ali Thabet, Bernard Ghanem


  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


  Access Paper or Ask Questions

Video Self-Stitching Graph Network for Temporal Action Localization


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


  Access Paper or Ask Questions

Data Dependent Randomized Smoothing


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

* 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 Deliège, Anthony Cioppa, Silvio Giancola, Meisam J. Seikavandi, Jacob V. Dueholm, Kamal Nasrollahi, Bernard Ghanem, Thomas B. Moeslund, Marc Van Droogenbroeck

* 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

* 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

* 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


  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

* 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


  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

* 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