Deep learning for computer vision: A brief review
Over the last years deep learning methods have been shown to outperform previous state‐of‐
the‐art machine learning techniques in several fields, with computer vision being one of the …
the‐art machine learning techniques in several fields, with computer vision being one of the …
A review of human activity recognition methods
Recognizing human activities from video sequences or still images is a challenging task due
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …
On-device training under 256kb memory
On-device training enables the model to adapt to new data collected from the sensors by
fine-tuning a pre-trained model. Users can benefit from customized AI models without having …
fine-tuning a pre-trained model. Users can benefit from customized AI models without having …
Visual saliency transformer
Existing state-of-the-art saliency detection methods heavily rely on CNN-based
architectures. Alternatively, we rethink this task from a convolution-free sequence-to …
architectures. Alternatively, we rethink this task from a convolution-free sequence-to …
Vision-based human activity recognition: a survey
Human activity recognition (HAR) systems attempt to automatically identify and analyze
human activities using acquired information from various types of sensors. Although several …
human activities using acquired information from various types of sensors. Although several …
Graph convolutional networks for temporal action localization
Most state-of-the-art action localization systems process each action proposal individually,
without explicitly exploiting their relations during learning. However, the relations between …
without explicitly exploiting their relations during learning. However, the relations between …
Tsm: Temporal shift module for efficient video understanding
The explosive growth in video streaming gives rise to challenges on performing video
understanding at high accuracy and low computation cost. Conventional 2D CNNs are …
understanding at high accuracy and low computation cost. Conventional 2D CNNs are …
Group-aware label transfer for domain adaptive person re-identification
Abstract Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims at
adapting the model trained on a labeled source-domain dataset to a target-domain dataset …
adapting the model trained on a labeled source-domain dataset to a target-domain dataset …
Tinytl: Reduce memory, not parameters for efficient on-device learning
Efficient on-device learning requires a small memory footprint at training time to fit the tight
memory constraint. Existing work solves this problem by reducing the number of trainable …
memory constraint. Existing work solves this problem by reducing the number of trainable …
Grad-cam: Visual explanations from deep networks via gradient-based localization
RR Selvaraju, M Cogswell, A Das… - Proceedings of the …, 2017 - openaccess.thecvf.com
We propose a technique for producing'visual explanations' for decisions from a large class
of Convolutional Neural Network (CNN)-based models, making them more transparent. Our …
of Convolutional Neural Network (CNN)-based models, making them more transparent. Our …