77 citations · 215 across the 34 of their papers we have counts for
46 papers
Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models
Jan Warchocki, Teodor Oprescu, Yunhan Wang +6
In temporal action localization, given an input video, the goal is to predict which actions it contains, where they begin, and where they end. Training and testing current state-of…
Video BagNet: short temporal receptive fields increase robustness in long-term action recognition
Ombretta Strafforello, Xin Liu, Klamer Schutte +1
Previous work on long-term video action recognition relies on deep 3D-convolutional models that have a large temporal receptive field (RF). We argue that these models are not alway…
Objects do not disappear: Video object detection by single-frame object location anticipation
Xin Liu, Fatemeh Karimi Nejadasl, Jan C. van Gemert +2
Objects in videos are typically characterized by continuous smooth motion. We exploit continuous smooth motion in three ways. 1) Improved accuracy by using object motion as an addi…
VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios +4
The third edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop featured four data-impaired challenges, focusing on addressing the limitation…
What Affects Learned Equivariance in Deep Image Recognition Models?
Robert-Jan Bruintjes, Tomasz Motyka, Jan van Gemert
Equivariance w.r.t. geometric transformations in neural networks improves data efficiency, parameter efficiency and robustness to out-of-domain perspective shifts. When equivarianc…
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation
Liang Zeng, Attila Lengyel, Nergis Tömen +1
In this work, we leverage estimated depth to boost self-supervised contrastive learning for segmentation of urban scenes, where unlabeled videos are readily available for training…