Related papers: Deep Architectures and Ensembles for Semantic Vide…

Maintaining or improving the performance of Deep Neural Networks (DNNs) through fine-tuning requires labeling newly collected inputs, a process that is often costly and time-consuming. To alleviate this problem, input selection approaches…

Recent studies on multi-label image classification have focused on designing more complex architectures of deep neural networks such as the use of attention mechanisms and region proposal networks. Although performance gains have been…

Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously…

Accurate classification of medical images is critical for detecting abnormalities in the gastrointestinal tract, a domain where misclassification can significantly impact patient outcomes. We propose an ensemble-based approach to improve…

We present a unified framework called deep dependency networks (DDNs) that combines dependency networks and deep learning architectures for multi-label classification, with a particular emphasis on image and video data. The primary…

It is well observed that in deep learning and computer vision literature, visual data are always represented in a manually designed coding scheme (eg., RGB images are represented as integers ranging from 0 to 255 for each channel) when they…

We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the problem as a structured prediction problem on sequential data, our main idea is to use Long Short-Term…

Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate bounding box annotations…

Temporal localization remains an important challenge in video understanding. In this work, we present our solution to the 3rd YouTube-8M Video Understanding Challenge organized by Google Research. Participants were required to build a…

Event classification is inherently sequential and multimodal. Therefore, deep neural models need to dynamically focus on the most relevant time window and/or modality of a video. In this study, we propose the Multi-level Attention Fusion…

At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on recurrent neural networks and older fundamental theoretical…

Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many different models and then aggregate their predictions. This is…

An ensemble method that fuses the output decision vectors of multiple feedforward-designed convolutional neural networks (FF-CNNs) to solve the image classification problem is proposed in this work. To enhance the performance of the…

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly developed for a single…

Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex…

In semantic video segmentation the goal is to acquire consistent dense semantic labelling across image frames. To this end, recent approaches have been reliant on manually arranged operations applied on top of static semantic segmentation…

Over the past few years, various tasks involving videos such as classification, description, summarization and question answering have received a lot of attention. Current models for these tasks compute an encoding of the video by treating…

Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…

Estimating the number of clusters and cluster structures in unlabeled, complex, and high-dimensional datasets (like images) is challenging for traditional clustering algorithms. In recent years, a matrix reordering-based algorithm called…

The growing scale and sophistication of cyberattacks pose critical challenges to network security, particularly in detecting diverse intrusion types within imbalanced datasets. Traditional intrusion detection systems (IDS) often struggle to…