People know and care for personal objects, which can be different for individuals. Automatically discovering personal objects is thus of great practical importance. We, in this paper, pursue this task with wearable cameras based on the common sense that personal objects generally company us in various scenes. With this clue, we exploit a new object-scene distribution for robust detection. Two technical challenges involved in estimating this distribution, i.e., scene extraction and unsupervised object discovery, are tackled. For scene extraction, we learn the latent representation instead of simply selecting a few frames from the videos. In object discovery, we build an interaction model to select frame-level objects and use nonparametric Bayesian clustering. Experiments verify the usefulness of our approach.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TIP.2015.2487868 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Neuroprotective Potential of L. Essential Oil Against Scopolamine-Induced Memory Deficits and Oxidative Stress in a Zebrafish Model.
Biomolecules
January 2025
Department of Biology, Faculty of Biology, Alexandru Ioan Cuza University of Iasi, 700506 Iasi, Romania.
L., also known as sweet marjoram, is a plant with multiple uses, both in the culinary field and traditional medicine, because of its major antioxidant, anti-inflammatory, antimicrobial, and digestive properties. In this research, we focused on the effects of essential oil (OmEO, at concentrations of 25, 150, and 300 μL/L), evaluating chemical structure as well as its impact on cognitive performance and oxidative stress, in both naive zebrafish (), as well as in a scopolamine-induced amnesic model (SCOP, 100 μM).
View Article and Find Full Text PDFEnhancing Microcalcification Detection in Mammography with YOLO-v8 Performance and Clinical Implications.
Diagnostics (Basel)
December 2024
Artificial Intelligence Development Center, Changhua Christian Hospital, Changhua 50050, Taiwan.
: Microcalcifications in the breast are often an early warning sign of breast cancer, and their accurate detection is crucial for the early discovery and management of the disease. In recent years, deep learning technology, particularly models based on object detection, has significantly improved the ability to detect microcalcifications. This study aims to use the advanced YOLO-v8 object detection algorithm to identify breast microcalcifications and explore its advantages in terms of performance and clinical application.
View Article and Find Full Text PDFNeuroprotection by chronic administration of Fluoroethylnormemantine (FENM) in mouse models of Alzheimer's disease.
Alzheimers Res Ther
January 2025
MMDN, Univ Montpellier, EPHE, INSERM, Montpellier, France.
Background: Fluoroethylnormemantine (FENM), a new Memantine (MEM) derivative, prevented amyloid-β[25-35] peptide (Aβ)-induced neurotoxicity in mice, a pharmacological model of Alzheimer's disease (AD) with high predictive value for drug discovery. Here, as drug infusion is likely to better reflect drug bioavailability due to the interspecies pharmacokinetics variation, we analyzed the efficacy of FENM after chronic subcutaneous (SC) infusion, in comparison with IP injections in two AD mouse models, Aβ-injected mice and the transgenic APP/PSEN1 (APP/PS1) line.
Methods: In Aβ-treated mice, FENM was infused at 0.
Causality is a fundamental part of the scientific endeavor to understand the world. Unfortunately, causality is still taboo in much of psychology and social science. Motivated by a growing number of recommendations for the importance of adopting causal approaches to research, we reformulate the typical approach to research in psychology to harmonize inevitably causal theories with the rest of the research pipeline.
View Article and Find Full Text PDFPattern memory cannot be completely and truly realized in deep neural networks.
Sci Rep
December 2024
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, China.
The unknown boundary issue, between superior computational capability of deep neural networks (DNNs) and human cognitive ability, has becoming crucial and foundational theoretical problem in AI evolution. Undoubtedly, DNN-empowered AI capability is increasingly surpassing human intelligence in handling general intelligent tasks. However, the absence of DNN's interpretability and recurrent erratic behavior remain incontrovertible facts.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!