Related papers: Bridging the gap between Human Action Recognition …
Action recognition is a key problem in computer vision that labels videos with a set of predefined actions. Capturing both, semantic content and motion, along the video frames is key to achieve high accuracy performance on this task. Most…
Knowledge Distillation has been established as a highly promising approach for training compact and faster models by transferring knowledge from heavyweight and powerful models. However, KD in its conventional version constitutes an…
Although deep convolution neural networks (DCNN) have achieved excellent performance in human pose estimation, these networks often have a large number of parameters and computations, leading to the slow inference speed. For this issue, an…
Hybrid Optical Neural Networks (ONNs, typically consisting of an optical frontend and a digital backend) offer an energy-efficient alternative to fully digital deep networks for real-time, power-constrained systems. However, their adoption…
Skeleton-based action recognition is vital for comprehending human-centric videos and has applications in diverse domains. One of the challenges of skeleton-based action recognition is dealing with low-quality data, such as skeletons that…
In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from…
Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…
Online action detection (OAD) is challenging since 1) robust yet computationally expensive features cannot be straightforwardly used due to the real-time processing requirements and 2) the localization and classification of actions have to…
Action recognition has long been a fundamental and intriguing problem in artificial intelligence. The task is challenging due to the high dimensionality nature of an action, as well as the subtle motion details to be considered. Current…
High storage and computational costs obstruct deep neural networks to be deployed on resource-constrained devices. Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher…
Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to the deep structures, they still require prohibitive…
Recently, deep learning-based models have been widely studied for click-through rate (CTR) prediction and lead to improved prediction accuracy in many industrial applications. However, current research focuses primarily on building complex…
Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-aware representations of the entire image or sequence, and…
Human action recognition from well-segmented 3D skeleton data has been intensively studied and has been attracting an increasing attention. Online action detection goes one step further and is more challenging, which identifies the action…
Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of…
Knowledge distillation is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained large teacher network. As an effective teaching strategy, interactive teaching has been…
Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak…
Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each…
Efficient models for remote sensing object counting are urgently required for applications in scenarios with limited computing resources, such as drones or embedded systems. A straightforward yet powerful technique to achieve this is…
In recent years, the performance of action recognition has been significantly improved with the help of deep neural networks. Most of the existing action recognition works hold the \textit{closed-set} assumption that all action categories…