260 citations · 629 across the 9 of their papers we have counts for
12 papers · 1 filter
MAAS: Multi-modal Assignation for Active Speaker Detection
Juan León-Alcázar, Fabian Caba Heilbron, Ali Thabet +1
Active speaker detection requires a solid integration of multi-modal cues. While individual modalities can approximate a solution, accurate predictions can only be achieved by expl…
SALA: Soft Assignment Local Aggregation for Parameter Efficient 3D Semantic Segmentation
Hani Itani, Silvio Giancola, Ali Thabet +1
In this work, we focus on designing a point local aggregation function that yields parameter efficient networks for 3D point cloud semantic segmentation. We explore the idea of usi…
Video Self-Stitching Graph Network for Temporal Action Localization
Chen Zhao, Ali Thabet, Bernard Ghanem
Temporal action localization (TAL) in videos is a challenging task, especially due to the large variation in action temporal scales. Short actions usually occupy a major proportion…
MVTN: Multi-View Transformation Network for 3D Shape Recognition
Abdullah Hamdi, Silvio Giancola, Bernard Ghanem
Multi-view projection methods have demonstrated their ability to reach state-of-the-art performance on 3D shape recognition. Those methods learn different ways to aggregate informa…
LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks
Guohao Li, Mengmeng Xu, Silvio Giancola +2
Point cloud architecture design has become a crucial problem for 3D deep learning. Several efforts exist to manually design architectures with high accuracy in point cloud tasks su…
Gabor Layers Enhance Network Robustness
Juan C. Pérez, Motasem Alfarra, Guillaume Jeanneret +4
We revisit the benefits of merging classical vision concepts with deep learning models. In particular, we explore the effect on robustness against adversarial attacks of replacing…
DeepGCNs: Making GCNs Go as Deep as CNNs
Guohao Li, Matthias Müller, Guocheng Qian +4
Convolutional Neural Networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, act…
MAIN: Multi-Attention Instance Network for Video Segmentation
Juan Leon Alcazar, Maria A. Bravo, Ali K. Thabet +4
Instance-level video segmentation requires a solid integration of spatial and temporal information. However, current methods rely mostly on domain-specific information (online lear…
BAOD: Budget-Aware Object Detection
Alejandro Pardo, Mengmeng Xu, Ali Thabet +2
We study the problem of object detection from a novel perspective in which annotation budget constraints are taken into consideration, appropriately coined Budget Aware Object Dete…
DeepGCNs: Can GCNs Go as Deep as CNNs?
Guohao Li, Matthias Müller, Ali Thabet +1
Convolutional Neural Networks (CNNs) achieve impressive performance in a wide variety of fields. Their success benefited from a massive boost when very deep CNN models were able to…
RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization
Alejandro Pardo, Humam Alwassel, Fabian Caba Heilbron +2
Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent…
MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds
Ali Thabet, Humam Alwassel, Bernard Ghanem
We present a self-supervised task on point clouds, in order to learn meaningful point-wise features that encode local structure around each point. Our self-supervised network, name…