Related papers: Two-Stream Convolutional Networks for Action Recog…
Standard methods for video recognition use large CNNs designed to capture spatio-temporal data. However, training these models requires a large amount of labeled training data, containing a wide variety of actions, scenes, settings and…
In recent years, a number of approaches based on 2D or 3D convolutional neural networks (CNN) have emerged for video action recognition, achieving state-of-the-art results on several large-scale benchmark datasets. In this paper, we carry…
This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that…
We propose an action recognition framework using Gen- erative Adversarial Networks. Our model involves train- ing a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without la- bel information.…
Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location. Accurate and efficient estimation of actionness is important in video analysis and may benefit other relevant tasks such as…
Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted…
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…
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. The temporal relation is complex in those datasets, including challenges like composite action, and co-occurring action.…
3D convolutional networks is a good means to perform tasks such as video segmentation into coherent spatio-temporal chunks and classification of them with regard to a target taxonomy. In the chapter we are interested in the classification…
Recently, 3D convolutional networks (3D ConvNets) yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but…
We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are…
With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important. In this paper, we address the problem of video scene recognition, whose goal is to learn a…
Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works well remains to be a mystery. In this work we move a small step…
Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition. How to effectively apply ConvNets to sequence-based data is still an open problem. This…
This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…
This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based…
Deep Convolutional Neural Networks (CNNs) are powerful models that have achieved excellent performance on difficult computer vision tasks. Although CNNs perform well whenever large labeled training samples are available, they work badly on…
Existing conditional video prediction approaches train a network from large databases and generalize to previously unseen data. We take the opposite stance, and introduce a model that learns from the first frames of a given video and…
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…
Recent advances of semantic image segmentation greatly benefit from deeper and larger Convolutional Neural Network (CNN) models. Compared to image segmentation in the wild, properties of both medical images themselves and of existing…