Search Results for author:
Found 5 papers, 3 papers with code
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports
In this paper, we propose a simple but effective hierarchical data sampling procedure and a centroid loss function that, when used together, increase the mean average precision (mAP) by 7 - 11. 5 and the rank-1 (R1) by 8. 8 - 14. 9 without any change in the network or hyper-parameters used.
Ranked #1 on
Person Re-Identification
on SoccerNet-v2
Semantic Labeling of Large-Area Geographic Regions Using Multi-View and Multi-Date Satellite Images and Noisy OSM Training Labels
With no human supervision, our IoU scores for the buildings and roads classes are 0. 8 and 0. 64 respectively which are better than state-of-the-art approaches that use OSM labels and that are not completely automated.
A Comparative Evaluation of SGM Variants (including a New Variant, tMGM) for Dense Stereo Matching
Our goal here is threefold: [1] To present a new dense-stereo matching algorithm, tMGM, that by combining the hierarchical logic of tSGM with the support structure of MGM achieves 6-8\% performance improvement over the baseline SGM (these performance numbers are posted under tMGM-16 in the Middlebury Benchmark V3 ); and [2] Through an exhaustive quantitative and qualitative comparative study, to compare how the major variants of the SGM approach to dense stereo matching, including the new tMGM, perform in the presence of: (a) illumination variations and shadows, (b) untextured or weakly textured regions, (c) repetitive patterns in the scene in the presence of large stereo rectification errors.
A New Stereo Benchmarking Dataset for Satellite Images
Unlike the existing benckmarking datasets, we have also carried out a quantitative evaluation of our groundtruthed disparities using human annotated points in two of the AOIs.
