Search Results - Computing methodologies Artificial intelligence Computer vision

On-Device Unsupervised Image Segmentation by 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…”
Get full text

DM-Tune: Quantizing Diffusion Models with Mixture-of-Gaussian Guided Noise Tuning by 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…”
Get full text

DAWN: Accelerating Point Cloud Object Detection via Object-Aware Partitioning and 3D Similarity-Based Filtering by 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…”
Get full text

PETRI: Reducing Bandwidth Requirement in Smart Surveillance by Edge-Cloud Collaborative Adaptive Frame Clustering and Pipelined Bidirectional Tracking by 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…”
Get full text

DCDiff: Enhancing JPEG Compression via Diffusion-based DC Coefficients Estimation by 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…”
Get full text

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

“… Second, we codesign the downstream vision model with the exposure pattern…”
Get full text

Robust Object Estimation using Generative-Discriminative Inference for Secure Robotics Applications by 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…”
Get full text

Pose tracking from natural features on mobile phones by 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…”
Get full text

SPN Dash - Fast Detection of Adversarial Attacks on Mobile via Sensor Pattern Noise Fingerprinting by 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…”
Get full text

Multiple 3D Object tracking for augmented reality by 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…”
Get full text

PixelSieve: Towards Efficient Activity Analysis From Compressed Video Streams by 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…”
Get full text

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

“…Integrating deep learning and image sensors has significantly transformed machine vision applications…”
Get full text

Multiple target detection and tracking with guaranteed framerates on mobile phones by Wagner, Daniel, Schmalstieg, Dieter, Bischof, Horst

“…In this paper we present a novel method for real-time pose estimation and tracking on low-end devices such as mobile phones. The presented system can track…”
Get full text

TCL: an ANN-to-SNN Conversion with Trainable Clipping Layers by 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…”
Get full text

A dataset and evaluation methodology for template-based tracking algorithms by Lieberknecht, Sebastian, Benhimane, Selim, Meier, Peter, Navab, Nassir

“…Unlike dense stereo, optical flow or multi-view stereo, template-based tracking lacks benchmark datasets allowing a fair comparison between state-of-the-art…”
Get full text

Neural Pruning Search for Real-Time Object Detection of Autonomous Vehicles by 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…”
Get full text

Leveraging Large Language Models to Annotate Activities of Daily Living Captured with Egocentric Vision by Shrestha, Sloke, Thomaz, Edison

“… We performed automatic evaluations on four different vision language pipelines (VLPs): concept detector, concept detector + GPT-3.5, BLIP2, and GPT-4…”
Get full text

An Intelligent Video Processing Architecture for Edge-cloud Video Streaming by Gao, Chengsi, Wang, Ying, Chen, Weiwei, Zhang, Lei

“…This work proposes an intelligent video processing architecture for bandwidth-efficient edge-cloud video streaming. On receiving the bandwidth-saving…”
Get full text

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

“…Continuous computer vision (CV) tasks increasingly rely on convolutional neural networks (CNN…”
Get full text

SLAMBooster: An Application-Aware Online Controller for Approximation in Dense SLAM by Pei, Yan, Biswas, Swarnendu, Fussell, Donald S., Pingali, Keshav

“… Approximate computing can be used to speed up SLAM implementations as long as the approximations do not prevent the agent from navigating correctly through the environment…”
Get full text