A survey of multi-label classification based on supervised and semi-supervised learning
M Han, H Wu, Z Chen, M Li, X Zhang - International Journal of Machine …, 2023 - Springer
Multi-label classification algorithms based on supervised learning use all the labeled data to
train classifiers. However, in real life, many of the data are unlabeled, and it is costly to label …
train classifiers. However, in real life, many of the data are unlabeled, and it is costly to label …
Modeling multi-label action dependencies for temporal action localization
Real world videos contain many complex actions with inherent relationships between action
classes. In this work, we propose an attention-based architecture that model these action …
classes. In this work, we propose an attention-based architecture that model these action …
Variational label enhancement
Label distribution covers a certain number of labels, representing the degree to which each
label describes the instance. When dealing with label ambiguity, label distribution could …
label describes the instance. When dealing with label ambiguity, label distribution could …
Efficient video classification using fewer frames
S Bhardwaj, M Srinivasan… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Recently, there has been a lot of interest in building compact models for video classification
which have a small memory footprint (< 1 GB). While these models are compact, they …
which have a small memory footprint (< 1 GB). While these models are compact, they …
The 2nd youtube-8m large-scale video understanding challenge
We hosted the 2nd YouTube-8M Large-Scale Video Understanding Kaggle Challenge and
Workshop at ECCV'18, with the task of classifying videos from frame-level and video-level …
Workshop at ECCV'18, with the task of classifying videos from frame-level and video-level …
Cifdm: continual and interactive feature distillation for multi-label stream learning
Multi-label learning algorithms have attracted more and more attention as of recent. This is
mainly because real-world data is generally associated with multiple and non-exclusive …
mainly because real-world data is generally associated with multiple and non-exclusive …
Satellite Video Multi-Label Scene Classification With Spatial and Temporal Feature Cooperative Encoding: A Benchmark Dataset and Method
W Guo, S Li, F Chen, Y Sun, Y Gu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Satellite video multi-label scene classification predicts semantic labels of multiple ground
contents to describe a given satellite observation video, which plays an important role in …
contents to describe a given satellite observation video, which plays an important role in …
Large scale video representation learning via relational graph clustering
Abstract Representation learning is widely applied for various tasks on multimedia data, eg,
retrieval and search. One approach for learning useful representation is by utilizing the …
retrieval and search. One approach for learning useful representation is by utilizing the …
Variational expectation maximization attention broad learning systems
X Hu, X Wei, Y Gao, H Liu, L Zhu - Information Sciences, 2022 - Elsevier
Recently, broad learning system (BLS) has received much attention due to its concise
network structure and strong incremental learning ability. However, as it belongs to a simple …
network structure and strong incremental learning ability. However, as it belongs to a simple …
Semi-supervised multi-label learning from crowds via deep sequential generative model
Multi-label classification (MLC) is pervasive in real-world applications. Conventional MLC
algorithms assume that enough ground truth labels are available for training a classifier …
algorithms assume that enough ground truth labels are available for training a classifier …