Pages

Opportunities

IVUL Openings

Postdoctoral Fellows The IVUL group at KAUST is looking for a top postdoctoral researcher with expertise in computer vision, machine learning, and/or optimization. The researcher for this opening will work at KAUST to investigate and develop principled computational methods for highly effective, scalable, and robust video modeling and analytics (e.g. action recognition, tracking, video registration, an object recognition in video), 3D understanding from RGBD, or deep learning (e.g. theory, methods, applications, and insight). Please send a full CV with a complete list of your publications and

Research

A Benchmark and Simulator for UAV Tracking (Simulator)

UAV Simulator: You can download the complete project binaries including a free demo world here.

Activity Net

In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple actions and movements occurring on manually trimmed videos. We introduce ActivityNet, a new large-scale video benchmark for human activity understanding.

IVUL Publications

2024: GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering, Abdullah Hamdi, Luke Melas-Kyriazi, Jinjie Mai, Guocheng Qian, Ruoshi Liu, Carl Vondrick, Bernard Ghanem, Andrea Vedaldi, Conference on Computer Vision and Pattern Recognition (CVPR 2024), ( Link) Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning, Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam, Jitendra Malik, Bernard Ghanem, Conference on Computer Vision and Pattern Recognition (CVPR 2024) SPAD: Spatially Aware Multiview

IVUL Research Group Collaborators

University of Amsterdam The University of Amsterdam (abbreviated as UvA, Dutch: Universiteit van Amsterdam) is a prestigious public university located in Amsterdam, Netherlands. Established in 1632 by municipal authorities and later renamed for the city of Amsterdam, the University of Amsterdam is the third-oldest university in the Netherlands. It is the largest university in the Netherlands by enrollment. Collaborators: Prof. Cees Snoek UC Merced UC Merced opened Sept. 5, 2005, as the newest campus in the University of California system and the first American research university of the

TrackingNet

Despite the numerous developments in object tracking, further improvement of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, data-hungry trackers based on deep-learning currently rely on object detection datasets due to the scarcity of dedicated large-scale tracking datasets. In this work, we present TrackingNet, the first large-scale dataset, and benchmark for object tracking in the wild. We provide more than 30K videos with more than 14 million dense bounding box annotations.

Info

IVUL Contacts

Resources

A Benchmark and Simulator for UAV Tracking (Dataset)

Video captured from low-altitude UAVs is inherently different from video in popular tracking datasets like OTB50, OTB100, VOT2014, VOT2015, TC128, and ALOV300++. Therefore, we propose a new dataset (UAV123) with sequences from an aerial viewpoint, a subset of which is meant for long-term aerial tracking (UAV20L). Our new UAV123 dataset contains a total of 123 video sequences and more than 110K frames making it the second-largest object tracking dataset after ALOV300++. All sequences are fully annotated with upright bounding boxes.

Datasets

Memorability scores for all 3,412 objects and 850 images from the PASCAL-S dataset Memorability maps corresponding to each of the 850 PASCAL-S images All original 850 PASCAL-S images and object segmentations used for the experiment For details, kindly refer to the publication titled SAR: Stroke Authorship Recognition.

Dyntex++ Dataset

The UCLA dataset has been the benchmark for DT recognition for several years, even though a much larger and more diverse database (the DynTex database) exists.

SAR Dataset

Two new sketch datasets for Stroke Authorship Recognition collected from experienced artists. For details, kindly refer to the publication titled SAR: Stroke Authorship Recognition.

SoccerNet

In this work, we introduce SoccerNet, a benchmark for action spotting in soccer videos. The dataset is composed of 500 complete soccer games from six main European leagues, covering three seasons from 2014 to 2017 and a total duration of 764 hours. A total of 6,637 temporal annotations are automatically parsed from online match reports at a one-minute resolution for three main classes of events (Goal, Yellow/Red Card, and Substitution). As such, the dataset is easily scalable.

Front Page

Image and Video Understanding Lab Research Group

Image and Video Understanding Lab Interested in joining the Image and Video Understanding Lab? Apply to KAUST Welcome to the Image and Video Understanding Lab (IVUL) at KAUST! At IVUL, we focus on interesting research problems in computer vision, including activity recognition/detection, robust representations of objects for tracking and recognition, scene understanding from 3D data, image annotation, etc. Since we aim to make sense of images and videos, especially at large scales, we often develop new machine learning and optimization methods to help us achieve this goal. We always seek