Bernard Ghanem

Latest

• SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
• KAUST Conference on Artificial Intelligence
• Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
• SeedQuant: A deep learning-based tool for assessing stimulant and inhibitor activity on root parasitic seeds
• Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts
• SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
• SALA: Soft Assignment Local Aggregation for 3D Semantic Segmentation
• MVTN: Multi-View Transformation Network for 3D Shape Recognition
• TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
• LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks
• Crash Course - 3D Deep Learning
• Impact Acceleration Funding Grant
• A Context-Aware Loss Function for Action Spotting in Soccer Videos
• PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement
• Efficient Tracking Proposals using 2D-3D Siamese Networks on LIDAR
• Leveraging Shape Completion for 3D Siamese Tracking
• TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking
• Teaching Cars to Drive
• Integration of Absolute Orientation Measurements in the KinectFusion Reconstruction pipeline
• SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos