Search · four archives
Search · four archives
18 papers · ranked by Valyu relevance
Liting Liao, Haoyuan Yang, Jun Peng, Runqiu Jin + 1 more
Highlights What are the main findings?1. A late-stage Squeeze-and-Excitation (SE) channel gating mechanism is integrated after the final 1 × 1 expansion convolution, adaptively recalibrating cross-channel dependencies with negligible parameter overhead (0.2 M); however, multi-seed analysis shows this gain is…
Xuefei Xu, Chengjun Xu, Gabriel Cristobal
Remote sensing scene classification (RSSC) plays a crucial role in Earth observation. Current deep learning methods, while accurate, tend to focus on high-level semantic features and overlook complementary shallow details such as edges and textures. Moreover, conventional CNNs are limited by fixed receptive fields…
King, Courtney M., Leeds, Daniel D. + 4 more
The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to aid in object recognition in biological vision. In this work, we attempt to add…
Ting Wang, Xiao Yan, Jiawei Li, Xilong Luo + 1 more
The extraction, classification, and judgment of sports video scenes can improve work efficiency and accuracy. To understand sports videos in dynamic scenes, this study applies deep learning technology, firstly introducing clustering algorithm and attention mechanism to improve the target detection technology You Only…
Shiying Yuan, Quanlong Feng, Bowen Niu, Xiaolu Yan + 5 more
This study releases China-MAS-50k, i.e., China Multi-label dataset for Agriculture & rural Scene 50k, the first very-high-resolution (VHR) remote sensing dataset for multi-label classification covering entire China’s agricultural and rural areas, filling the gap in finely annotated data for non-urban scene recognition.…
Haonan Liu, Xiao Wang, Jialong Sun, Xingchi Yang + 2 more
Remote sensing scene classification remains challenging due to substantial object-scale variations, complex background interference, and high inter-class similarity. To address these issues, a lightweight classification framework, termed MDC-MobileNetV3, is proposed based on the MobileNetV3-Large backbone. The…
Arun D. Kulkarni
Land Use Scene Classification (LUSC) from remote sensing imagery plays a critical role in environmental monitoring, urban planning, and sustainable resource management. In recent years, deep learning methods have significantly advanced the state of the art, with Convolutional Neural Networks (CNNs) dominating the field…
Niklas Müller, H. Steven Scholte, Iris I. A. Groen
In real-world vision, the human brain needs to process large amounts of information to effectively interact with its environment. It is well established that our visual system has specialized regions to process information efficiently, such as scene-, face-, and object-selective areas, which can be uncovered using…
Diwei Sheng, Vijayraj Gohil, Satyam Gaba, Zihan Liu + 4 more
Scene change detection (SCD) is crucial for urban monitoring and navigation but remains challenging in real-world environments due to lighting variations, seasonal shifts, viewpoint differences, and complex urban layouts. Existing methods rely primarily on low-level visual features, limiting their ability to accurately…
Ilker Duymaz, Micha Engeser, Daniel Kaiser
Multivariate analyses of M/EEG data are typically performed on neural responses time-locked to discrete stimulus onsets. Such designs usually reveal high decoding performance during the initial transient response (0-500 ms), which subsequently drops to a lower, sustained level. Here, we examined time-resolved EEG…
Ziyan Zhu, Bo Zhang, Xinyi Zhang, Yuji Naya
Scene construction involves the automatic synthesis of fragmented visual inputs into coherent mental models. While previous work has focused on static landscapes, real-world scenes require integrating dynamic agents with stable environmental anchors. We investigated the neural hierarchy underlying this transformation…
Guangda Bao, Wenzhi Xia, Yun Zhou, Zhiyou Liao + 2 more
To address the inefficiency and unfairness of traditional manual scrap sorting, we propose the application of 3D vision technology for grading in this work. The multi-view 3D reconstruction algorithm achieves an accuracy within 1 mm in both synthetic and real scrap scenes. This level of accuracy meets the requirements…
Guangda Bao, Wenzhi Xia, Haichuan Wang, Zhiyou Liao + 2 more
To address the limitation of 2D methods in inferring absolute scrap dimensions from images, we propose Scrap-SAM-CLIP (SSC), a vision-language model integrating the segment anything model (SAM) and contrastive language-image pre-training in Chinese (CN-CLIP). The model enables identification of canonical scrap shapes…
Jun Yang, Tiziana Vercillo, Teresa Emma Cutrona, Simone Azeglio + 2 more
The human visual system can identify objects in complex natural scenes, yet the mechanisms supporting robust perception under such variable conditions remain incompletely understood. Here, we investigate how the statistical structure of natural scenes shapes perceptual evidence formation and determines whether…
Carolin Teuber, Anwai Archit, Tobias Boothe, Peter Ditte + 2 more
Deep learning underlies most modern approaches and tools in computer vision, including biomedical imaging. However, for interactive semantic segmentation (often called pixel classification in this context) and interactive object-level classification (object classification), feature-based shallow learning remains widely…
Muhammad Umer Ramzan, Ali Zia, Abdelwahed Khamis, Noman Ali + 2 more
—Salient object detection (SOD) aims to segment visually prominent regions in images and serves as a foundational task for various computer vision applications.We posit that SOD can now reach near-supervised accuracy without a single pixel-level label, but only when reliable pseudo-masks are available. We revisit the…
Hari Prasanth S. M., Nilusha Jayawickrama, Risto Ojala
Industrial object detection systems typically rely on large annotated datasets, which are expensive to collect and challenging to maintain in industrial scenarios where the inventory of objects changes frequently. This work addresses the challenge of few-shot object detection in such industrial scenarios, where only a…
Loïc Chadoutaud, Marvin Lerousseau, Daniel Herrero-Saboya, Julian Ostermaier + 3 more
Understanding the spatial organization of individual cell types within tissue and how this organization is disrupted in disease, is a central question in biology and medicine. Hematoxylin and eosin-stained slides are widely available and provide detailed morphological context, while spatial gene expression profiling…