28 citations · 47 across the 8 of their papers we have counts for
7 papers · 1 filter
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers
Julien Denize, Mykola Liashuha, Jaonary Rabarisoa +2
We present COMEDIAN, a novel pipeline to initialize spatiotemporal transformers for action spotting, which involves self-supervised learning and knowledge distillation. Action spot…
SoccerNet 2023 Challenges Results
Anthony Cioppa, Silvio Giancola, Vladimir Somers +99
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vi…
Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning
Julien Denize, Jaonary Rabarisoa, Astrid Orcesi +1
Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive E…
Self-Supervised Pre-training of Vision Transformers for Dense Prediction Tasks
Jaonary Rabarisoa, Valentin Belissen, Florian Chabot +1
We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representa…
End-to-end Person Search Sequentially Trained on Aggregated Dataset
Angelique Loesch, Jaonary Rabarisoa, Romaric Audigier
In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) p…
Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning
Julien Denize, Jaonary Rabarisoa, Astrid Orcesi +2
Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and us…
Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image
Florian Chabot, Mohamed Chaouch, Jaonary Rabarisoa +2
In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for…