Bernard Ghanem

research

∙ 09/11/2023

Learning Semantic Segmentation with Query Points Supervision on Aerial Images

Semantic segmentation is crucial in remote sensing, where high-resolutio...

0 Santiago Rivier, et al. ∙

research

∙ 08/28/2023

Learning to Read Analog Gauges from Synthetic Data

Manually reading and logging gauge data is time inefficient, and the eff...

0 Juan Leon Alcazar, et al. ∙

research

∙ 08/22/2023

ShadowNet for Data-Centric Quantum System Learning

Understanding the dynamics of large quantum systems is hindered by the c...

0 Yuxuan Du, et al. ∙

research

∙ 08/03/2023

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

How to enable learnability for new classes while keeping the capability ...

0 Yibo Yang, et al. ∙

research

∙ 06/15/2023

Enhancing Neural Rendering Methods with Image Augmentations

Faithfully reconstructing 3D geometry and generating novel views of scen...

11 Juan C. Pérez, et al. ∙

research

∙ 05/28/2023

Just a Glimpse: Rethinking Temporal Information for Video Continual Learning

Class-incremental learning is one of the most important settings for the...

0 Lama Alssum, et al. ∙

research

∙ 05/16/2023

Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?

We revisit the common practice of evaluating adaptation of Online Contin...

0 Hasan Abed Al Kader Hammoud, et al. ∙

research

∙ 04/24/2023

Large-capacity and Flexible Video Steganography via Invertible Neural Network

Video steganography is the art of unobtrusively concealing secret data i...

0 Chong Mou, et al. ∙

research

∙ 04/10/2023

Revisiting Test Time Adaptation under Online Evaluation

This paper proposes a novel online evaluation protocol for Test Time Ada...

9 Motasem Alfarra, et al. ∙

research

∙ 04/06/2023

Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions

Deep neural networks have been critical in the task of Visual Question A...

0 Jia-Hong Huang, et al. ∙

research

∙ 04/06/2023

Boundary-Denoising for Video Activity Localization

Video activity localization aims at understanding the semantic content i...

0 Mengmeng Xu, et al. ∙

research

∙ 03/23/2023

Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs

In this paper we investigate the frequency sensitivity of Deep Neural Ne...

0 Hasan Abed Al Kader Hammoud, et al. ∙

research

∙ 03/20/2023

Computationally Budgeted Continual Learning: What Does Matter?

Continual Learning (CL) aims to sequentially train models on streams of ...

0 Ameya Prabhu, et al. ∙

research

∙ 03/17/2023

A Unified Continual Learning Framework with General Parameter-Efficient Tuning

The "pre-training → downstream adaptation" presents both new opportuniti...

0 Qiankun Gao, et al. ∙

research

∙ 03/17/2023

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

Recently, conditional diffusion models have gained popularity in numerou...

0 Jiwen Yu, et al. ∙

research

∙ 03/15/2023

Re-ReND: Real-time Rendering of NeRFs across Devices

This paper proposes a novel approach for rendering a pre-trained Neural ...

4 Sara Rojas, et al. ∙

research

∙ 02/26/2023

Localizing Moments in Long Video Via Multimodal Guidance

The recent introduction of the large-scale long-form MAD dataset for lan...

0 Wayner Barrios, et al. ∙

research

∙ 02/02/2023

Real-Time Evaluation in Online Continual Learning: A New Paradigm

Current evaluations of Continual Learning (CL) methods typically assume ...

5 Yasir Ghunaim, et al. ∙

research

∙ 01/03/2023

Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition

Deep neural networks (DNNs) are vulnerable to a class of attacks called ...

0 Hasan Abed Al Kader Hammoud, et al. ∙

research

∙ 12/09/2022

PIVOT: Prompting for Video Continual Learning

Modern machine learning pipelines are limited due to data availability, ...

8 Andrés Villa, et al. ∙

research

∙ 11/29/2022

SimCS: Simulation for Online Domain-Incremental Continual Segmentation

Continual Learning is a step towards lifelong intelligence where models ...

6 Motasem Alfarra, et al. ∙

research

∙ 11/29/2022

On Robust Learning from Noisy Labels: A Permutation Layer Approach

The existence of label noise imposes significant challenges (e.g., poor ...

0 Salman Alsubaihi, et al. ∙

research

∙ 11/27/2022

Multi-Modal Few-Shot Temporal Action Detection

Few-shot (FS) and zero-shot (ZS) learning are two different approaches f...

0 Sauradip Nag, et al. ∙

research

∙ 11/25/2022

Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization

Temporal action localization (TAL) requires long-form reasoning to predi...

0 Chen Zhao, et al. ∙

research

∙ 11/21/2022

SegNeRF: 3D Part Segmentation with Neural Radiance Fields

Recent advances in Neural Radiance Fields (NeRF) boast impressive perfor...

0 Jesus Zarzar, et al. ∙

research

∙ 11/18/2022

Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization

This paper deals with the problem of localizing objects in image and vid...

0 Mengmeng Xu, et al. ∙

research

∙ 09/29/2022

Generalizability of Adversarial Robustness Under Distribution Shifts

Recent progress in empirical and certified robustness promises to delive...

20 Kumail Alhamoud, et al. ∙

research

∙ 08/03/2022

Negative Frames Matter in Egocentric Visual Query 2D Localization

The recently released Ego4D dataset and benchmark significantly scales a...

0 Mengmeng Xu, et al. ∙

research

∙ 06/09/2022

PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

PointNet++ is one of the most influential neural architectures for point...

19 Guocheng Qian, et al. ∙

research

∙ 06/06/2022

Certified Robustness in Federated Learning

Federated learning has recently gained significant attention and popular...

3 Motasem Alfarra, et al. ∙

research

∙ 05/14/2022

ETAD: A Unified Framework for Efficient Temporal Action Detection

Untrimmed video understanding such as temporal action detection (TAD) of...

4 Shuming Liu, et al. ∙

research

∙ 04/26/2022

Contrastive Language-Action Pre-training for Temporal Localization

Long-form video understanding requires designing approaches that are abl...

2 Mengmeng Xu, et al. ∙

research

∙ 04/12/2022

3DeformRS: Certifying Spatial Deformations on Point Clouds

3D computer vision models are commonly used in security-critical applica...

0 Gabriel Pérez S., et al. ∙

research

∙ 04/05/2022

Real-time Hyperspectral Imaging in Hardware via Trained Metasurface Encoders

Hyperspectral imaging has attracted significant attention to identify sp...

12 Maksim Makarenko, et al. ∙

research

∙ 03/27/2022

End-to-End Active Speaker Detection

Recent advances in the Active Speaker Detection (ASD) problem build upon...

5 Juan Leon Alcazar, et al. ∙

research

∙ 03/24/2022

R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning

Class-Incremental Learning (CIL) struggles with catastrophic forgetting ...

1 Qiankun Gao, et al. ∙

research

∙ 03/03/2022

SegTAD: Precise Temporal Action Detection via Semantic Segmentation

Temporal action detection (TAD) is an important yet challenging task in ...

2 Chen Zhao, et al. ∙

research

∙ 02/10/2022

Towards Assessing and Characterizing the Semantic Robustness of Face Recognition

Deep Neural Networks (DNNs) lack robustness against imperceptible pertur...

2 Juan C. Pérez, et al. ∙

research

∙ 02/10/2022

OWL (Observe, Watch, Listen): Localizing Actions in Egocentric Video via Audiovisual Temporal Context

Temporal action localization (TAL) is an important task extensively expl...

7 Merey Ramazanova, et al. ∙

research

∙ 01/31/2022

On the Robustness of Quality Measures for GANs

This work evaluates the robustness of quality measures of generative mod...

5 Motasem Alfarra, et al. ∙

research

∙ 01/23/2022

vCLIMB: A Novel Video Class Incremental Learning Benchmark

Continual learning (CL) is under-explored in the video domain. The few e...

5 Andrés Villa, et al. ∙

research

∙ 12/09/2021

Spatio-temporal Relation Modeling for Few-shot Action Recognition

We propose a novel few-shot action recognition framework, STRM, which en...

6 Anirudh Thatipelli, et al. ∙

research

∙ 12/01/2021

MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions

The recent and increasing interest in video-language research has driven...

0 Mattia Soldan, et al. ∙

research

∙ 10/12/2021

Relation-aware Video Reading Comprehension for Temporal Language Grounding

Temporal language grounding in videos aims to localize the temporal span...

4 Jialin Gao, et al. ∙

research

∙ 09/12/2021

MovieCuts: A New Dataset and Benchmark for Cut Type Recognition

Understanding movies and their structural patterns is a crucial task to ...

0 Alejandro Pardo, et al. ∙

research

∙ 09/12/2021

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

Deep Neural Networks (DNNs) have been utilized in various applications r...

10 Hasan Abed Al Kader Hammoud, et al. ∙

research

∙ 08/09/2021

Learning to Cut by Watching Movies

Video content creation keeps growing at an incredible pace; yet, creatin...

9 Alejandro Pardo, et al. ∙

research

∙ 07/29/2021

Enhancing Adversarial Robustness via Test-time Transformation Ensembling

Deep learning models are prone to being fooled by imperceptible perturba...

25 Juan C. Pérez, et al. ∙

research

∙ 07/09/2021

ANCER: Anisotropic Certification via Sample-wise Volume Maximization

Randomized smoothing has recently emerged as an effective tool that enab...

3 Francisco Eiras, et al. ∙

research

∙ 07/02/2021

DeformRS: Certifying Input Deformations with Randomized Smoothing

Deep neural networks are vulnerable to input deformations in the form of...

6 Motasem Alfarra, et al. ∙

Bernard Ghanem

Featured Co-authors