Related papers: DenseImage Network: Video Spatial-Temporal Evoluti…

Semantic labeling (or pixel-level land-cover classification) in ultra-high resolution imagery (< 10cm) requires statistical models able to learn high level concepts from spatial data, with large appearance variations. Convolutional Neural…

Object detection in video and image surveillance is a well-established yet rapidly evolving task, strongly influenced by recent deep learning advancements. This review summarises modern techniques by examining architectural innovations,…

We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features…

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to…

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…

Deep Neural Networks have been successfully applied in hyperspectral image classification. However, most of prior works adopt general deep architectures while ignore the intrinsic structure of the hyperspectral image, such as the physical…

3D convolution is powerful for video classification but often computationally expensive, recent studies mainly focus on decomposing it on spatial-temporal and/or channel dimensions. Unfortunately, most approaches fail to achieve a…

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…

Recently, deep learning approach, especially deep Convolutional Neural Networks (ConvNets), have achieved overwhelming accuracy with fast processing speed for image classification. Incorporating temporal structure with deep ConvNets for…

We present a new model DrNET that learns disentangled image representations from video. Our approach leverages the temporal coherence of video and a novel adversarial loss to learn a representation that factorizes each frame into a…

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…

There is an inherent need for autonomous cars, drones, and other robots to have a notion of how their environment behaves and to anticipate changes in the near future. In this work, we focus on anticipating future appearance given the…

In parallel with the success of CNNs to solve vision problems, there is a growing interest in developing methodologies to understand and visualize the internal representations of these networks. How the responses of a trained CNN encode the…

Speech enhancement in the time domain is becoming increasingly popular in recent years, due to its capability to jointly enhance both the magnitude and the phase of speech. In this work, we propose a dense convolutional network (DCN) with…

Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based…

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional…

The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack…

An important aspect of video understanding is the ability to predict the evolution of its content in the future. This paper presents a future frame semantic segmentation technique for predicting semantic masks of the current and future…

Deep learning's great success motivates many practitioners and students to learn about this exciting technology. However, it is often challenging for beginners to take their first step due to the complexity of understanding and applying…

Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and…