Related papers: Late Temporal Modeling in 3D CNN Architectures wit…

Nowadays, Transformers and Graph Convolutional Networks (GCNs) are the prevailing techniques for 3D human pose estimation. However, Transformer-based methods either ignore the spatial neighborhood relationships between the joints when used…

End-to-end learning models using raw waveforms as input have shown superior performances in many audio recognition tasks. However, most model architectures are based on convolutional neural networks (CNN) which were mainly developed for…

Recently, three dimensional (3D) convolutional neural networks (CNNs) have emerged as dominant methods to capture spatiotemporal representations in videos, by adding to pre-existing 2D CNNs a third, temporal dimension. Such 3D CNNs,…

In this paper we explore the parameter efficiency of BERT arXiv:1810.04805 on version 2.0 of the Stanford Question Answering dataset (SQuAD2.0). We evaluate the parameter efficiency of BERT while freezing a varying number of final…

Deep ConvNets have shown its good performance in image classification tasks. However it still remains as a problem in deep video representation for action recognition. The problem comes from two aspects: on one hand, current video ConvNets…

Action segmentation as a milestone towards building automatic systems to understand untrimmed videos has received considerable attention in the recent years. It is typically being modeled as a sequence labeling problem but contains…

We address the problem of temporal activity detection in continuous, untrimmed video streams. This is a difficult task that requires extracting meaningful spatio-temporal features to capture activities, accurately localizing the start and…

With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn…

For pursuing accurate skeleton-based action recognition, most prior methods use the strategy of combining Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete…

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for visual recognition problems. Nevertheless, the convolutional filters in these networks are local operations while ignoring the large-range dependency.…

Much progress has been made recently on text classification with methods based on neural networks. In particular, models using attention mechanism such as BERT have shown to have the capability of capturing the contextual information within…

Age estimation from facial images is a complex and multifaceted challenge in computer vision. In this study, we present a novel hybrid architecture that combines ConvNeXt, a state-of-the-art advancement of convolutional neural networks…

In this paper, we propose to use deep 3-dimensional convolutional networks (3D CNNs) in order to address the challenge of modelling spectro-temporal dynamics for speech emotion recognition (SER). Compared to a hybrid of Convolutional Neural…

Most action recognition models today are highly parameterized, and evaluated on datasets with appearance-wise distinct classes. It has also been shown that 2D Convolutional Neural Networks (CNNs) tend to be biased toward texture rather than…

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…

We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…

We introduce a novel approach for temporal activity segmentation with timestamp supervision. Our main contribution is a graph convolutional network, which is learned in an end-to-end manner to exploit both frame features and connections…

From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years. However, current methods suffer from the confusion caused by partial…

The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally,…

In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…