Related papers: 2D or not 2D? Adaptive 3D Convolution Selection fo…

Motivated by the success of data-driven convolutional neural networks (CNNs) in object recognition on static images, researchers are working hard towards developing CNN equivalents for learning video features. However, learning video…

Standard 3D convolution operations require much larger amounts of memory and computation cost than 2D convolution operations. The fact has hindered the development of deep neural nets in many 3D vision tasks. In this paper, we investigate…

It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video…

3D convolution is powerful for video classification but often computationally expensive, recent studies mainly focus on decomposing it on spatial-temporal and/or channel dimensions. Unfortunately, most approaches fail to achieve a…

Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost. To address this challenge, we propose a new…

Video Anomaly Detection(VAD) has been traditionally tackled in two main methodologies: the reconstruction-based approach and the prediction-based one. As the reconstruction-based methods learn to generalize the input image, the model merely…

Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels…

A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large datasets and allowing them to discover the optimal…

Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.…

Anomalous activity recognition deals with identifying the patterns and events that vary from the normal stream. In a surveillance paradigm, these events range from abuse to fighting and road accidents to snatching, etc. Due to the sparse…

Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of computation to a task-relevant subset of frames or the most…

During the last years, many advances have been made in tasks like3D model retrieval, 3D model classification, and 3D model segmentation.The typical 3D representations such as point clouds, voxels, and poly-gon meshes are mostly suitable for…

Recognizing human actions in untrimmed videos is an important challenging task. An effective 3D motion representation and a powerful learning model are two key factors influencing recognition performance. In this paper we introduce a new…

Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context.…

Scene flow estimation is the task to predict the point-wise or pixel-wise 3D displacement vector between two consecutive frames of point clouds or images, which has important application in fields such as service robots and autonomous…

Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of…

There have been considerable debates over 2D and 3D representation learning on 3D medical images. 2D approaches could benefit from large-scale 2D pretraining, whereas they are generally weak in capturing large 3D contexts. 3D approaches are…

Convolutional networks are successful due to their equivariance/invariance under translations. However, rotatable data such as images, volumes, shapes, or point clouds require processing with equivariance/invariance under rotations in cases…

Convolutional Neural Networks achieve state-of-the-art accuracy in object detection tasks. However, they have large computational and energy requirements that challenge their deployment on resource-constrained edge devices. Object detection…

Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data,…