Related papers: Semantic Image Networks for Human Action Recogniti…

Most of the semantic segmentation approaches have been developed for single image segmentation, and hence, video sequences are currently segmented by processing each frame of the video sequence separately. The disadvantage of this is that…

In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…

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…

This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations…

Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural-looking motions, most data-driven approaches require considerable efforts of pre-processing, including motion…

In this work, we aim for temporally consistent semantic segmentation throughout frames in a video. Many semantic segmentation algorithms process images individually which leads to an inconsistent scene interpretation due to illumination…

Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion…

Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored…

Human actions captured in video sequences are three-dimensional signals characterizing visual appearance and motion dynamics. To learn action patterns, existing methods adopt Convolutional and/or Recurrent Neural Networks (CNNs and RNNs).…

This paper presents a novel method to involve both spatial and temporal features for semantic video segmentation. Current work on convolutional neural networks(CNNs) has shown that CNNs provide advanced spatial features supporting a very…

Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…

This paper proposes a simple yet effective method for human action recognition in video. The proposed method separately extracts local appearance and motion features using state-of-the-art three-dimensional convolutional neural networks…

Spatio-temporal contexts are crucial in understanding human actions in videos. Recent state-of-the-art Convolutional Neural Network (ConvNet) based action recognition systems frequently involve 3D spatio-temporal ConvNet filters, chunking…

Semantic Segmentation combines two sub-tasks: the identification of pixel-level image masks and the application of semantic labels to those masks. Recently, so-called Foundation Models have been introduced; general models trained on very…

Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework…

3D skeleton-based motion prediction and activity recognition are two interwoven tasks in human behaviour analysis. In this work, we propose a motion context modeling methodology that provides a new way to combine the advantages of both…

Online action recognition is an important task for human centered intelligent services, which is still difficult to achieve due to the varieties and uncertainties of spatial and temporal scales of human actions. In this paper, we propose…

In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment…

We propose a novel scheme for human action recognition in videos, using a 3-dimensional Convolutional Neural Network (3D CNN) based classifier. Traditionally in deep learning based human activity recognition approaches, either a few random…

We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We show how the parameters of a function that has been fit to the…