418 citations · 3.5k across the 221 of their papers we have counts for
19 papers · 1 filter
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…
Data-Dependent Randomized Smoothing
Motasem Alfarra, Adel Bibi, Philip H. S. Torr +1
Randomized smoothing is a recent technique that achieves state-of-art performance in training certifiably robust deep neural networks. While the smoothing family of distributions i…
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…
SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
Adrien Deliège, Anthony Cioppa, Silvio Giancola +6
Understanding broadcast videos is a challenging task in computer vision, as it requires generic reasoning capabilities to appreciate the content offered by the video editing. In th…
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…
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
Humam Alwassel, Silvio Giancola, Bernard Ghanem
Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracte…
Boundary-sensitive Pre-training for Temporal Localization in Videos
Mengmeng Xu, Juan-Manuel Perez-Rua, Victor Escorcia +5
Many video analysis tasks require temporal localization thus detection of content changes. However, most existing models developed for these tasks are pre-trained on general video…
VLG-Net: Video-Language Graph Matching Network for Video Grounding
Mattia Soldan, Mengmeng Xu, Sisi Qu +2
Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query. The solution to this challenging task demands unde…
Robust Optimization as Data Augmentation for Large-scale Graphs
Kezhi Kong, Guohao Li, Mucong Ding +5
Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the perfor…
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…
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
Samuel Albanie, Yang Liu, Arsha Nagrani +18
We present a new video understanding pentathlon challenge, an open competition held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020.…
Learning Heat Diffusion for Network Alignment
Sisi Qu, Mengmeng Xu, Bernard Ghanem +1
Networks are abundant in the life sciences. Outstanding challenges include how to characterize similarities between networks, and in extension how to integrate information across n…
Network Moments: Extensions and Sparse-Smooth Attacks
Modar Alfadly, Adel Bibi, Emilio Botero +2
The impressive performance of deep neural networks (DNNs) has immensely strengthened the line of research that aims at theoretically analyzing their effectiveness. This has incited…
DeeperGCN: All You Need to Train Deeper GCNs
Guohao Li, Chenxin Xiong, Ali Thabet +1
Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs. Unlike Convolutional Neural Networks (CNNs), which…
Rethinking Clustering for Robustness
Motasem Alfarra, Juan C. Pérez, Adel Bibi +3
This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Trainin…
Active Speakers in Context
Juan Leon Alcazar, Fabian Caba Heilbron, Long Mai +4
Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. Although this strategy can be enough for addressing single…
Adaptive Learning of the Optimal Batch Size of SGD
Motasem Alfarra, Slavomir Hanzely, Alyazeed Albasyoni +2
Recent advances in the theoretical understanding of SGD led to a formula for the optimal batch size minimizing the number of effective data passes, i.e., the number of iterations t…
RGB-based Semantic Segmentation Using Self-Supervised Depth Pre-Training
Jean Lahoud, Bernard Ghanem
Although well-known large-scale datasets, such as ImageNet, have driven image understanding forward, most of these datasets require extensive manual annotation and are thus not eas…
On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective
Motasem Alfarra, Adel Bibi, Hasan Hammoud +2
This work tackles the problem of characterizing and understanding the decision boundaries of neural networks with piecewise linear non-linearity activations. We use tropical geomet…