Related papers: Dilated Temporal Fully-Convolutional Network for S…

The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc. There is…

Models based on deep convolutional neural networks (CNN) have significantly improved the performance of semantic segmentation. However, learning these models requires a large amount of training images with pixel-level labels, which are very…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…

Robot perception systems need to perform reliable image segmentation in real-time on noisy, raw perception data. State-of-the-art segmentation approaches use large CNN models and carefully constructed datasets; however, these models focus…

Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years. Most of the…

Most machine vision tasks (e.g., semantic segmentation) are based on images encoded and decoded by image compression algorithms (e.g., JPEG). However, these decoded images in the pixel domain introduce distortion, and they are optimized for…

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 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…

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…

This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…

For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take into considerations the correlations in the video sequence,…

Cardiac motion estimation and segmentation play important roles in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In this paper, we propose a novel deep learning method for joint estimation of motion and…

Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation,…

Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and intelligent transportation. Lots of benchmark datasets are…

Sequence prediction on temporal data requires the ability to understand compositional structures of multi-level semantics beyond individual and contextual properties. The task of temporal action segmentation, which aims at translating an…

Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence. Previous works usually exploit accurate optical flow to leverage the temporal relations, which suffer much from heavy…

Deep neural networks for time series must capture complex temporal patterns, to effectively represent dynamic data. Self- and semi-supervised learning methods show promising results in pre-training large models, which -- when finetuned for…

Comprehensive scene understanding is a critical enabler of robot autonomy. Semantic segmentation is one of the key scene understanding tasks which is pivotal for several robotics applications including autonomous driving, domestic service…

Semantic Segmentation using deep convolutional neural network pose more complex challenge for any GPU intensive task. As it has to compute million of parameters, it results to huge memory consumption. Moreover, extracting finer features and…