Related papers: Temporal Convolutional Networks: A Unified Approac…

Graph convolution networks (GCN) have been widely used in skeleton-based action recognition. We note that existing GCN-based approaches primarily rely on prescribed graphical structures (ie., a manually defined topology of skeleton joints),…

Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features…

High level understanding of sequential visual input is important for safe and stable autonomy, especially in localization and object detection. While traditional object classification and tracking approaches are specifically designed to…

Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To…

Understanding human actions in wild videos is an important task with a broad range of applications. In this paper we propose a novel approach named Hierarchical Attention Network (HAN), which enables to incorporate static spatial…

This chapter aims to aid the development of Cyber-Physical Systems (CPS) in automated understanding of events and activities in various applications of video-surveillance. These events are mostly captured by drones, CCTVs or novice and…

Motion is a salient cue to recognize actions in video. Modern action recognition models leverage motion information either explicitly by using optical flow as input or implicitly by means of 3D convolutional filters that simultaneously…

Current state-of-the-art approaches to skeleton-based action recognition are mostly based on recurrent neural networks (RNN). In this paper, we propose a novel convolutional neural networks (CNN) based framework for both action…

Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…

Co-evolving time series appears in a multitude of applications such as environmental monitoring, financial analysis, and smart transportation. This paper aims to address the following challenges, including (C1) how to incorporate explicit…

Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause a malformed action sequence. Most existing methods borrow ideas from video generation, which naively treat…

Deep learning has achieved substantial improvement on single-channel speech enhancement tasks. However, the performance of multi-layer perceptions (MLPs)-based methods is limited by the ability to capture the long-term effective history…

The work in this paper is driven by the question how to exploit the temporal cues available in videos for their accurate classification, and for human action recognition in particular? Thus far, the vision community has focused on…

We introduce the concept of "dynamic image", a novel compact representation of videos useful for video analysis, particularly in combination with convolutional neural networks (CNNs). A dynamic image encodes temporal data such as RGB or…

Consider a set of n images of a scene with dynamic objects captured with a static or a handheld camera. Let the temporal order in which these images are captured be unknown. There can be n! possibilities for the temporal order in which…

Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial…

Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level and model temporal context with 3D ConvNets. Here, we go one step further and model spatio-temporal relations to capture the…

Action recognition has become a rapidly developing research field within the last decade. But with the increasing demand for large scale data, the need of hand annotated data for the training becomes more and more impractical. One way to…

We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between…

With the development of feed-forward models, the default model for sequence modeling has gradually evolved to replace recurrent networks. Many powerful feed-forward models based on convolutional networks and attention mechanism were…