73 hasil
Menampilkan 1–20 · 0,26 detik · RSS
Visual Intelligence
Scopus
ISSN 2097-3330 · Springer · 73 artikel di indeks
-
Artikel Jurnal
SAM2-UNet: segment anything 2 makes strong encoder for natural and medical image segmentation
Abstract Image segmentation plays an important role in vision understanding. Recently, the emerging vision foundation models continuously achieved superior performance on various tasks. Following such success, in this paper, we prove that the Segment Anything Model 2 (SAM2) can be a strong encoder…
-
Artikel Jurnal
HDVS: semi-supervised semantic segmentation via heterogeneous dual-branch voting supervision
Abstract Semi-supervised semantic segmentation, which aims to utilize large volumes of unlabeled images to achieve accurate segmentation results with fewer human annotations, has attracted increasing attention. Prior methods were primarily based on the assumption that the pseudo-labels generated by…
-
Artikel Jurnal
DAS-SAM: fine-tuning SAM towards drivable area segmentation via efficient multi-scale traffic scene-aware adaptation
Abstract Drivable area segmentation (DAS) plays an important role in autonomous driving. Segment anything model (SAM) has recently emerged as a powerful foundation model, demonstrating remarkable potential across diverse downstream segmentation tasks through domain-specific parameter-efficient…
-
Artikel Jurnal
Efficient image dehazing with synergic expert modulation
Abstract Recent developments in context modulation mechanisms have achieved significant improvements in performance, as well as better trade-offs between model accuracy and efficiency. These mechanisms operate on input through context modeling and then leverage these contexts to modulate projected…
-
Artikel Jurnal
Adversarial attacks on medical hyperspectral imaging exploiting spectral-spatial dependencies and multiscale features
Abstract Medical hyperspectral imaging (MHSI) has demonstrated considerable promise in disease diagnosis by capturing spectral-spatial information of tissues. While deep learning has substantially improved MHSI classification accuracy, its robustness remains limited due to the well-known trade-off…
-
Artikel Jurnal
ProACT: prototype-guided anchor-based test-time adaptation for pneumoconiosis diagnosis
Abstract Maintaining reliable performance in the multi-center deployment of pneumoconiosis diagnosis models is difficult under severe distribution shifts because adaptation must respect the multi-region diagnostic criteria specific to pneumoconiosis. Generic grounded test-time adaptation (TTA)…
-
Artikel Jurnal
CMJU: cross-modal joint unlearning for balanced forgetting in multimodal large language models
Abstract Multimodal large language models (MLLMs) may memorize private or sensitive knowledge from training data, making unlearning important for safe deployment. Existing studies have shown that unlearning in MLLMs can remain inconsistent across multimodal and text-only inputs: target knowledge…
-
Artikel Jurnal
Leveraging multi-modal and historical knowledge graphs for continual robot navigation
Abstract In contemporary robotic navigation systems, autonomous agents are increasingly required to operate in complex, dynamically evolving environments. However, in dynamic environments, the disparity between heterogeneous sensor inputs and continuously changing conditions frequently induces…
-
Artikel Jurnal
Scale-adaptive multi-predator network for camouflaged object detection
Abstract In this paper, we propose a scale-adaptive multi-predator (SAMP) network for camouflaged object detection (COD), which aims to segment objects that have successfully concealed themselves by blending into the surrounding environment. Despite the challenging nature of distinguishing objects…
-
Artikel Jurnal
MAC1toK: relax feature matching with maximal cliques for 3D registration
Abstract The majority of existing point cloud registration (PCR) methods exhibit performance degradation under extremely low inlier ratios. To address this limitation, this paper presents a robust learning-free estimator called MAC1toK, which relaxes the feature matching with maximal cliques from…
-
Artikel Jurnal
PAMD: plausibility-aware motion diffusion model for long dance generation
Abstract Computational dance generation is crucial in many areas, such as art, human-computer interaction, virtual reality, and digital entertainment, particularly for generating coherent and expressive long dance sequences. Diffusion-based music-to-dance generation has made significant progress…
-
Artikel Jurnal
MARMOT: masked autoencoder for modeling transient imaging
Abstract Pretrained models have recently emerged as effective priors for a wide range of vision and computational imaging problems. Transient measurements have emerged as a new imaging modality, in which a time-resolved sensor records photon counts over time bins. In confocal non-line-of-sight…
-
Artikel Jurnal
Thinking outside the frame: viewpoint-aware spatial reasoning in large multimodal models
Abstract Large multimodal models (LMMs) have greatly improved cross-modal tasks but continue to struggle with spatial reasoning. In particular, they exhibit a bias toward egocentric reasoning and have limited ability to reframe spatial relations allocentrically, making them unreliable under…
-
Artikel Jurnal
NVS-UIE: diffusion UIE towards novel view synthesis via physics-aligned frequency fusion
Abstract The underwater images always suffer from low contrast and color bias due to the scattering water medium. Such degradations impair the image quality and therefore have adversarial effects on the underwater visual-based tasks. In recent years, many learning-based underwater image enhancement…
-
Artikel Jurnal
DIVA-3D: a diverse 3D talking head dataset from in-the-wild videos
Abstract The synthesis of lifelike three-dimensional (3D) talking heads from audio requires precise lip synchronization and nuanced facial expressions. However, current methods often fall short of this goal, largely due to the scarcity of large-scale, diverse training data. To address this issue…
-
Artikel Jurnal
DanceDiT: towards efficient and consistent human image animation with diffusion transformer
Abstract Pose-driven human image animation aims to synthesize a human video from a reference image and a target pose sequence while preserving identity consistency, motion consistency, and temporal coherence. Existing methods often improve controllability by introducing duplicated reference…
-
Artikel Jurnal
Symbolic-driven agentic reasoning for environmental and behavioral event detection
Abstract Analyzing complex environmental and behavioral activities requires intelligent systems that not only perceive visual scenes but also reason about underlying events and interactions. Conventional computer vision models often operate at the object-detection level, limiting their ability to…
-
Artikel Jurnal
Dual-rate parameter-efficient tuning with sample enhancement for source-free domain-adaptive keypoint detection
Abstract Source-free domain-adaptive keypoint detection (SFDA-KD) is a method that adapts a keypoint detection model to an unlabeled target domain without accessing the source domain data. In this task, keypoints are spread out across images, and the domain distribution shifts when labels are…
-
Artikel Jurnal
Intelligent robot systems: a survey from the perspective of visual intelligence
Abstract Intelligent robots have seen significant advancements over the past few decades, with notable developments in recent years. The integration of artificial intelligence into robotics is transforming the manufacturing, agricultural, and healthcare industries, leading to increased efficiency…