Rank pooling for action recognition
We propose a function-based temporal pooling method that captures the latent structure of
the video sequence data-eg, how frame-level features evolve over time in a video. We show …
the video sequence data-eg, how frame-level features evolve over time in a video. We show …
Deeppermnet: Visual permutation learning
R Santa Cruz, B Fernando… - Proceedings of the …, 2017 - openaccess.thecvf.com
We present a principled approach to uncover the structure of visual data by solving a novel
deep learning task coined visual permutation learning. The goal of this task is to find the …
deep learning task coined visual permutation learning. The goal of this task is to find the …
Sodeep: a sorting deep net to learn ranking loss surrogates
M Engilberge, L Chevallier… - Proceedings of the …, 2019 - openaccess.thecvf.com
Several tasks in machine learning are evaluated using non-differentiable metrics such as
mean average precision or Spearman correlation. However, their non-differentiability …
mean average precision or Spearman correlation. However, their non-differentiability …
Breast cancer detection in thermal infrared images using representation learning and texture analysis methods
Nowadays, breast cancer is one of the most common cancers diagnosed in women.
Mammography is the standard screening imaging technique for the early detection of breast …
Mammography is the standard screening imaging technique for the early detection of breast …
Visual permutation learning
We present a principled approach to uncover the structure of visual data by solving a deep
learning task coined visual permutation learning. The goal of this task is to find the …
learning task coined visual permutation learning. The goal of this task is to find the …
SPANet: Generalized permutationless set assignment for particle physics using symmetry preserving attention
The creation of unstable heavy particles at the Large Hadron Collider is the most direct way
to address some of the deepest open questions in physics. Collisions typically produce …
to address some of the deepest open questions in physics. Collisions typically produce …
Reliable and rapid traffic congestion detection approach based on deep residual learning and motion trajectories
Traffic congestion detection systems help manage traffic in crowded cities by analyzing
videos of vehicles. Existing systems largely depend on texture and motion features. Such …
videos of vehicles. Existing systems largely depend on texture and motion features. Such …
Active ordinal querying for tuplewise similarity learning
Many machine learning tasks such as clustering, classification, and dataset search benefit
from embedding data points in a space where distances reflect notions of relative similarity …
from embedding data points in a space where distances reflect notions of relative similarity …
Plackett-luce regression mixture model for heterogeneous rankings
M Tkachenko, HW Lauw - Proceedings of the 25th ACM International on …, 2016 - dl.acm.org
Learning to rank is an important problem in many scenarios, such as information retrieval,
natural language processing, recommender systems, etc. The objective is to learn a function …
natural language processing, recommender systems, etc. The objective is to learn a function …
Robust traffic congestion recognition in videos based on deep Multi-Stream LSTM
MA Abdelwahab - SVU-International Journal of Engineering …, 2022 - svusrc.journals.ekb.eg
Cities with high population density have a serious problem with traffic congestion. Intelligent
transportation systems try to overcome these problems by finding smart ways to detect traffic …
transportation systems try to overcome these problems by finding smart ways to detect traffic …