A5059447545- Advanced Image and Video Retrieval Techniques
- Multimodal Machine Learning Applications
- Video Analysis and Summarization
- Anomaly Detection Techniques and Applications
- Adversarial Robustness in Machine Learning
- Image Retrieval and Classification Techniques
- Domain Adaptation and Few-Shot Learning
- Image Processing and 3D Reconstruction
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Image Enhancement Techniques
- Visual Attention and Saliency Detection
- Human Pose and Action Recognition
- Smart Parking Systems Research
- Cell Image Analysis Techniques
- Face recognition and analysis
- Neuroscience and Neuropharmacology Research
- Sentiment Analysis and Opinion Mining
- Bacillus and Francisella bacterial research
- Natural Language Processing Techniques
- Image and Video Quality Assessment
- Neuropeptides and Animal Physiology
- Neural dynamics and brain function
- Autonomous Vehicle Technology and Safety
- Sports Analytics and Performance
Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo"
2015-2024
National Research Council
2016-2024
Joanneum Research
2023
HTW Berlin - University of Applied Sciences
2023
Charles University
2023
University of Klagenfurt
2023
Institute of Scientific and Technical Information of China
2021-2022
This paper presents an approach for real-time car parking occupancy detection that uses a Convolutional Neural Network (CNN) classifier running on-board of smart camera with limited resources. Experiments show our technique is very effective and robust to light condition changes, presence shadows, partial occlusions. The reliable, even when tests are performed using images captured from viewpoint different than the used training. In addition, it also demonstrates its robustness training...
Perineuronal nets (PNNs) surround specific neurons in the brain and are involved various forms of plasticity clinical conditions. However, our understanding PNN role these phenomena is limited by lack highly quantitative maps distribution association with cell types. Here, we present a comprehensive atlas Wisteria floribunda agglutinin (WFA)-positive PNNs colocalization parvalbumin (PV) cells for over 600 regions adult mouse brain. Data analysis shows that PV expression good predictor...
Much progress has been made in the field of sentiment analysis past years. Researchers relied on textual data for this task, while only recently they have started investigating approaches to predict sentiments from multimedia content. With increasing amount shared social media, there is also a rapidly growing interest that work "in wild", i.e. are able deal with uncontrolled conditions. In work, we faced challenge training visual classifier starting large set user-generated and unlabeled...
This paper conducts a thorough examination of the 12th Video Browser Showdown (VBS) competition, which is well-established international benchmarking campaign for interactive video search systems. The annual VBS competition has witnessed steep rise in popularity multimodal embedding-based approaches retrieval. majority thirteen systems participating 2023 utilized CLIP-based cross-modal model, allowing specification free-form text queries to visual content. shared emphasis on joint embedding...
In this work, we propose CBiGAN - a novel method for anomaly detection in images, where consistency constraint is introduced as regularization term both the encoder and decoder of BiGAN. Our model exhibits fairly good modeling power reconstruction capability. We evaluate proposed on MVTec AD real-world benchmark unsupervised high-resolution images compare against standard baselines state-of-the-art approaches. Experiments show that improves performance BiGAN formulations by large margin...
Deep learning has recently become the state of art in many computer vision applications and image classification particular. However, recent works have shown that it is quite easy to create adversarial examples, i.e., images intentionally created or modified cause deep neural network make a mistake. They are like optical illusions for machines containing changes unnoticeable human eye. This represents serious threat machine methods. In this paper, we investigate robustness representations...
Content-Based Image Retrieval in large archives through the use of visual features has become a very attractive research topic recent years. The cause this strong impulse area is certainly to be attributed Convolutional Neural Network (CNN) activations as and their outstanding performance. However, practically all available image retrieval systems are implemented main memory, limiting applicability preventing usage big-data applications. In paper, we propose transform CNN into textual...
This paper describes in detail VISIONE, a video search system that allows users to for videos using textual keywords, the occurrence of objects and their spatial relationships, colors image similarity. These modalities can be combined together express complex queries meet users’ needs. The peculiarity our approach is we encode all information extracted from keyframes, such as visual deep features, tags, color object locations, convenient encoding indexed single text retrieval engine. offers...
Abstract Pupil dynamics alterations have been found in patients affected by a variety of neuropsychiatric conditions, including autism. Studies mouse models used pupillometry for phenotypic assessment and as proxy arousal. Both mice humans, is noninvasive allows longitudinal experiments supporting temporal specificity; however, its measure requires dedicated setups. Here, we introduce convolutional neural network that performs online both humans web app format. This solution dramatically...
Abstract Orthoptera are insects with excellent olfactory sense abilities due to their antennae richly equipped receptors. This makes them interesting model organisms be used as biosensors for environmental and agricultural monitoring. Herein, we investigated if the house cricket Acheta domesticus can detect different chemical cues by examining movements of attempting identify specific antennal displays associated exposed (e.g., sucrose or ammonia powder). A neural network based on...
Abstract Perineuronal nets (PNNs) surround specific neurons in the brain and are involved various forms of plasticity clinical conditions. However, our understanding PNN role these phenomena is limited by lack highly quantitative maps distribution association with cell types. Here, we present first comprehensive atlas (in Allen Brain Atlas coordinates) colocalization parvalbumin (PV) cells for over 600 regions adult mouse brain. Data analysis showed that PV expression a good predictor...