Related papers: Depthwise Spatio-Temporal STFT Convolutional Neura…

Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the involved humans and objects. Inspired by the success of convolutional neural networks…

Convolutional networks are one of the most widely employed architectures in computer vision and machine learning. In order to leverage their ability to learn complex functions, large amounts of data are required for training. Training a…

Simulating the long-term dynamics of multi-scale and multi-physics systems poses a significant challenge in understanding complex phenomena across science and engineering. The complexity arises from the intricate interactions between scales…

Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One…

Convolutional neural network (CNN) slides a kernel over the whole image to produce an output map. This kernel scheme reduces the number of parameters with respect to a fully connected neural network (NN). While CNN has proven to be an…

Recent research in deep learning (DL) has investigated the use of the Fast Fourier Transform (FFT) to accelerate the computations involved in Convolutional Neural Networks (CNNs) by replacing spatial convolution with element-wise…

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…

The inverse short-time Fourier transform network (iSTFTNet) has garnered attention owing to its fast, lightweight, and high-fidelity speech synthesis. It obtains these characteristics using a fast and lightweight 1D CNN as the backbone and…

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for image recognition problems. Nevertheless, it is not trivial when utilizing a CNN for learning spatio-temporal video representation. A few studies have…

Convolutional Neural Networks (CNN) have been successful in processing data signals that are uniformly sampled in the spatial domain (e.g., images). However, most data signals do not natively exist on a grid, and in the process of being…

Convolutional Neural Networks (CNNs) are very effective for many pattern recognition tasks. However, training deep CNNs needs extensive computation and large training data. In this paper we propose Bank of Filter-Trees (BFT) as a trans- fer…

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large…

Non-uniformed 3D sparse data, e.g., point clouds or voxels in different spatial positions, make contribution to the task of 3D object detection in different ways. Existing basic components in sparse convolutional networks (Sparse CNNs)…

The video based CNN works have focused on effective ways to fuse appearance and motion networks, but they typically lack utilizing temporal information over video frames. In this work, we present a novel spatio-temporal fusion network…

Image pre-training, the current de-facto paradigm for a wide range of visual tasks, is generally less favored in the field of video recognition. By contrast, a common strategy is to directly train with spatiotemporal convolutional neural…

Analyzing spatio-temporal data like video is a challenging task that requires processing visual and temporal information effectively. Convolutional Neural Networks have shown promise as baseline fixed feature extractors through transfer…

Recently, video classification attracts intensive research efforts. However, most existing works are based on framelevel visual features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In…

Convolutional Neural Networks (CNNs) have become the method of choice for learning problems involving 2D planar images. However, a number of problems of recent interest have created a demand for models that can analyze spherical images.…

Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability. However, the extremely intensive requirements on memory…

Deep convolutional neural networks have achieved remarkable progress in recent years. However, the large volume of intermediate results generated during inference poses a significant challenge to the accelerator design for…