Sorry, you need to enable JavaScript to visit this website.

Fine-grained action localization in untrimmed sports videos presents a significant challenge due to rapid and subtle motion transitions over short durations. Existing supervised and weakly supervised solutions often rely on extensive annotated datasets and high-capacity models, making them computationally intensive and less adaptable to real-world scenarios. In this work, we introduce a lightweight and unsupervised skeleton-based action localization pipeline that leverages spatio-temporal graph neural representations.

Paper Abstraction:

In this work, we present a novel multi-agent framework for generating immersive 3D virtual environments from high-level semantic inputs, powered by large language and vision-language models (LLMs/VLMs). Unlike prior work that focuses primarily on visual output, data-intensive training pipelines, and code generation, our system coordinates a team of specialized agents, each assigned a role such as manager, planner, or expert in visual, audio, or spatial domains, to decompose and execute environment construction tasks within a game engine.

Detecting vehicles in aerial images is difficult due to complex backgrounds, small object sizes, shadows, and occlusions. Although recent deep learning advancements have improved object detection, these models remain susceptible to adversarial attacks (AAs), challenging their reliability. Traditional AA strategies often ignore practical implementation constraints. Our work proposes realistic and practical constraints on texture (lowering resolution, limiting modified areas, and color ranges) and analyzes the impact of shape modifications on attack performance.

Recently, generative priors have shown significant improvement for unsupervised image restoration. This study explores the incorporation of multiple loss functions that capture various perceptual and structural aspects of image quality. Our proposed method improves robustness across multiple tasks, including denoising, upsampling, inpainting, and deartifacting, by utilizing a comprehensive loss function based on Learned Perceptual Image Patch Similarity(LPIPS), Multi-Scale Structural Similarity Index Measure Loss(MS-SSIM), Consistency, Feature, and Gradient losses.

Appendix of our paper: "Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models" accepted at IEEE ICIP 2025 workshop: Edge Intelligence: Smart, Efficient, and Scalable Solutions for IoT, Wearables, and Embedded Devices (SEEDS)

This supplementary material accompanies our paper titled "Texturing Endoscopic 3D Stomach via Neural Radiance Field under Uneven Lighting."

MULTIMAE MEETS EARTH OBSERVATION: PRE-TRAINING MULTI-MODAL MULTI-TASK MASKED AUTOENCODERS FOR EARTH OBSERVATION TASKS (APPENDIX)

This paper presents FaceLiVT, a lightweight yet powerful face recognition model that combines a hybrid CNN-Transformer architecture with an innovative and lightweight Multi-Head Linear Attention (MHLA) mechanism. By incorporating MHLA alongside a reparameterized token mixer, FaceLiVT effectively reduces computational complexity while preserving high accuracy. Extensive evaluations on challenging benchmarks—including LFW, CFP-FP, AgeDB-30, IJB-B, and IJB-C—highlight its superior performance compared to state-of-the-art lightweight models.

Supplementary Material.