Výsledky vyhľadávania - "Computing methodologies Artificial intelligence Computer vision"

DM-Tune: Quantizing Diffusion Models with Mixture-of-Gaussian Guided Noise Tuning Autor Haghi, Pouya, Falahati, Ali, Azad, Zahra, Wu, Chunshu, Song, Ruibing, Liu, Chuan, Li, Ang, Geng, Tong

“…Diffusion models have become essential generative tools for tasks such as image generation, video creation, and inpainting, but their high computational and…”
Získať plný text

On-Device Unsupervised Image Segmentation Autor Yang, Junhuan, Sheng, Yi, Zhang, Yuzhou, Jiang, Weiwen, Yang, Lei

“…Along with the breakthrough of convolutional neural networks, in particular encoder-decoder and U-Net, learning-based segmentation has emerged in many research…”
Získať plný text

DAWN: Accelerating Point Cloud Object Detection via Object-Aware Partitioning and 3D Similarity-Based Filtering Autor Tang, Dongdong, Mao, Yu, Wang, Weilan, Guan, Nan, Kuo, Tei-Wei, Xue, Chun Jason

“…As a fundamental perception task, 3D point cloud detection has become essential for applications in autonomous driving and robotics. However, point cloud…”
Získať plný text

DCDiff: Enhancing JPEG Compression via Diffusion-based DC Coefficients Estimation Autor Zhang, Ziyuan, Qiu, Han, Zhang, Tianwei, Chen, Bin, Zhang, Chao

“…JPEG is the most widely-used image compression method on low-cost cameras which cannot support learning-based compressors. One promising approach to enhance…”
Získať plný text

SNAPPIX: Efficient-Coding-Inspired In-Sensor Compression for Edge Vision Autor Lin, Weikai, Ma, Tianrui, Boloor, Adith, Feng, Yu, Xing, Ruofan, Zhang, Xuan, Zhu, Yuhao

“…Energy-efficient image acquisition on the edge is crucial for enabling remote sensing applications where the sensor node has weak compute capabilities and must…”
Získať plný text

PETRI: Reducing Bandwidth Requirement in Smart Surveillance by Edge-Cloud Collaborative Adaptive Frame Clustering and Pipelined Bidirectional Tracking Autor Liu, Ruoyang, Zhang, Lu, Wang, Jingyu, Yang, Huazhong, Liu, Yongpan

“…Neural networks running on cloud servers have been widely used in smart surveillance, but they require high bandwidth to upload videos. Edge-cloud…”
Získať plný text

Pose tracking from natural features on mobile phones Autor Wagner, Daniel, Reitmayr, Gerhard, Mulloni, Alessandro, Drummond, Tom, Schmalstieg, Dieter

“…In this paper we present two techniques for natural feature tracking in real-time on mobile phones. We achieve interactive frame rates of up to 20Hz for…”
Získať plný text

TCL: an ANN-to-SNN Conversion with Trainable Clipping Layers Autor Ho, Nguyen-Dong, Chang, Ik-Joon

“…Spiking-neural-networks (SNNs) are promising at edge devices since the event-driven operations of SNNs provides significantly lower power compared to…”
Získať plný text

Late Breaking Results: Less Sense Makes More Sense: In-Sensor Compressive Learning for Efficient Machine Vision Autor Liang, Yiwen, Cao, Weidong

“…Integrating deep learning and image sensors has significantly transformed machine vision applications. Yet, conventional highresolution image acquisition…”
Získať plný text

Multiple 3D Object tracking for augmented reality Autor Park, Youngmin, Lepetit, Vincent, Woontack Woo

“…We present a method that is able to track several 3D objects simultaneously, robustly, and accurately in real-time. While many applications need to consider…”
Získať plný text

Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision Autor Zhu, Yuhao, Samajdar, Anand, Mattina, Matthew, Whatmough, Paul

“…Continuous computer vision (CV) tasks increasingly rely on convolutional neural networks (CNN). However, CNNs have massive compute demands that far exceed the…”
Získať plný text

Robust Object Estimation using Generative-Discriminative Inference for Secure Robotics Applications Autor Liu, Yanqi, Costantini, Alessandro, Bahar, R. Iris, Sui, Zhiqiang, Ye, Zhefan, Lu, Shiyang, Jenkins, Odest Chadwicke

“…Convolutional neural networks (CNNs) are of increasing widespread use in robotics, especially for object recognition. However, such CNNs still lack several…”
Získať plný text

Accelerating real-time embedded scene labeling with convolutional networks Autor Cavigelli, Lukas, Magno, Michele, Benini, Luca

“…Today there is a clear trend towards deploying advanced computer vision (CV) systems in a growing number of application scenarios with strong real-time and…”
Získať plný text

Enabling On-Device Self-Supervised Contrastive Learning with Selective Data Contrast Autor Wu, Yawen, Wang, Zhepeng, Zeng, Dewen, Shi, Yiyu, Hu, Jingtong

“…After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy. Contrastive…”
Získať plný text

Neural Pruning Search for Real-Time Object Detection of Autonomous Vehicles Autor Zhao, Pu, Yuan, Geng, Cai, Yuxuan, Niu, Wei, Liu, Qi, Wen, Wujie, Ren, Bin, Wang, Yanzhi, Lin, Xue

“…Object detection plays an important role in self-driving cars for security development. However, mobile systems on self-driving cars with limited computation…”
Získať plný text

PixelSieve: Towards Efficient Activity Analysis From Compressed Video Streams Autor Wang, Yongchen, Wang, Ying, Li, Huawei, Li, Xiaowei

“…Pixel-level data redundancy in video induces additional memory and computing overhead when neural networks are employed to mine spatiotemporal patterns, e.g…”
Získať plný text

SPN Dash - Fast Detection of Adversarial Attacks on Mobile via Sensor Pattern Noise Fingerprinting Autor Nixon, Kent W., Mao, Jiachen, Shen, Juncheng, Yang, Huanrui, Li, Hai Helen, Chen, Yiran

“…A concerning weakness of deep neural networks is their susceptibility to adversarial attacks. While methods exist to detect these attacks, they incur…”
Získať plný text

Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning Autor Wang, Liang, Lu, Kai, Zhang, Nan, Qu, Xiaoyang, Wang, Jianzong, Wan, Jiguang, Li, Guokuan, Xiao, Jing

“…This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video of changing scenes…”
Získať plný text

SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity Autor Fan, Zichen, Dai, Steve, Venkatesan, Rangharajan, Sylvester, Dennis, Khailany, Brucek

“…Diffusion models have gained significant popularity in image generation tasks. However, generating high-quality content remains notably slow because it…”
Získať plný text

iTaskSense: Task-Oriented Object Detection in Resource-Constrained Environments Autor Jeong, SungHeon, Barkam, Hamza Errahmouni, Oh, Hyunwoo, Chen, Hanning, Das, Tamoghno, Ye, Zhen, Imani, Mohsen

“…Task-oriented object detection is increasingly essential for intelligent sensing applications, enabling AI systems to operate autonomously in complex,…”
Získať plný text