Search Results - parameterized (source OR resource) code patterns

ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices by Yu, Hao, Jiang, Tangyu, Jia, Shuning, Yan, Shannan, Liu, Shunning, Qian, Haolong, Li, Guanghao, Dong, Shuting, Yuan, Chun

“…The Transformer architecture has revolutionized various fields since it was proposed, where positional encoding plays an essential role in effectively…”
Get full text

On-line construction of parameterized suffix trees for large alphabets by Lee, Taehyung, Na, Joong Chae, Park, Kunsoo

“… This situation often arises from source code management systems where, for example, a source code repository is gradually increasing in its size as users commit new codes into the repository day by day…”
Get full text

Source code modification technology based on parameterized code patterns by Itsykson, V, Timofeyev, D

“…Source code modification is one of the most frequent operations which developers perform in software life cycle…”
Get full text

A prefix array for parameterized strings by Beal, Richard, Adjeroh, Donald A., Smyth, W.F.

“… Historically, p-strings have been leveraged for source code cloning, plagiarism detection, and biological sequence structural similarity…”
Get full text

Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition by Song, Yi-Fan, Zhang, Zhang, Shan, Caifeng, Wang, Liang

“… However, the complexity of the recent State-Of-The-Art (SOTA) models for this task tends to be exceedingly sophisticated and over-parameterized…”
Get full text

Deblur-NeRF: Neural Radiance Fields from Blurry Images by Ma, Li, Li, Xiaoyu, Liao, Jing, Zhang, Qi, Wang, Xuan, Wang, Jue, Sander, Pedro V.

“…Neural Radiance Field (NeRF) has gained considerable attention recently for 3D scene reconstruction and novel view synthesis due to its remarkable synthesis…”
Get full text

Position-Guided Point Cloud Panoptic Segmentation Transformer by Xiao, Zeqi, Zhang, Wenwei, Wang, Tai, Loy, Chen Change, Lin, Dahua, Pang, Jiangmiao

“…DEtection TRansformer (DETR) started a trend that uses a group of learnable queries for unified visual perception. This work begins by applying this appealing…”
Get full text

Deep Hough Transform for Semantic Line Detection by Zhao, Kai, Han, Qi, Zhang, Chang-Bin, Xu, Jun, Cheng, Ming-Ming

“… Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments…”
Get full text

Network pruning via resource reallocation by Hou, Yuenan, Ma, Zheng, Liu, Chunxiao, Wang, Zhe, Loy, Chen Change

“… Contemporary methods typically perform iterative pruning procedure from the original over-parameterized model, which is both tedious and expensive especially when the pruning is aggressive…”
Get full text

Dense Continuous-Time Optical Flow From Event Cameras by Gehrig, Mathias, Muglikar, Manasi, Scaramuzza, Davide

“… We leverage these benefits to predict pixel trajectories densely in continuous time via parameterized Bézier curves…”
Get full text

MLR-SNet: Transferable LR Schedules for Heterogeneous Tasks by Shu, Jun, Zhu, Yanwen, Zhao, Qian, Meng, Deyu, Xu, Zongben

“… . The learnable parameterized structure brings more flexibility for MLR-SNet to learn a proper…”
Get full text

Dynamic Focus-aware Positional Queries for Semantic Segmentation by He, Haoyu, Cai, Jianfei, Pan, Zizheng, Liu, Jing, Zhang, Jing, Tao, Dacheng, Zhuang, Bohan

“… Although promising, it relies on the learnable parameterized positional queries which tend to encode the dataset statistics, leading to inaccurate localization for distinct individual queries…”
Get full text

Parameterized Strings: Algorithms and Applications by Beal, Richard

“… Historically, p-strings have been employed in source code cloning, plagiarism detection, and structural similarity between biological sequences…”
Get full text

FMW-Net: a first-order meta-weight-net approach for sample weighting by Zhou, Yubo, Shu, Jun, Liu, Junmin, Meng, Deyu

“… Recently, Meta-Weight-Net (MW-Net) method has been proposed to automatically learn the weighting function parameterized by a Multi-Layer Perceptron (MLP…”
Get full text

Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization by Qiao, Siyuan, Lin, Zhe, Zhang, Jianming, Yuille, Alan L.

“… Deep neural networks are usually over-parameterized for their tasks in order to achieve good performances, thus are likely to have underutilized computational resources…”
Get full text

Calibration of a groundwater model using pattern information from remote sensing data by Li, H.T., Brunner, P., Kinzelbach, W., Li, W.P., Dong, X.G.

“…Due to the chronic lack of verification data, hydrologic models are notoriously over-parameterized…”
Get full text

A Unified Knowledge Distillation Framework for Deep Directed Graphical Models by Chen, Yizhuo, Liang, Kaizhao, Zeng, Zhe, Yao, Shuochao, Shao, Huajie

“…) with arbitrary layers of random variables. We refer by deep DGMs to DGMs whose conditional distributions are parameterized by deep neural networks…”
Get full text

Wildland fire mid-story: A generative modeling approach for representative fuels by Hutchings, Grant, Gattiker, James, Scherting, Braden, Linn, Rodman R.

“…Computational models for understanding and predicting fire in wildland and managed lands are increasing in impact. Data characterizing the fuels and…”
Get full text

Generating Portable High-Performance Code via Multi-Dimensional Homomorphisms by Rasch, Ari, Schulze, Richard, Gorlatch, Sergei

“…, the same source code achieves a consistent, high level of performance over the variety of modern parallel processors, including multi-core CPU and many-core Graphics Processing Unit (GPU…”
Get full text

Hardware-aware Coding Function Design for Compressive Single-photon 3D Cameras by Parra, David, Gutierrez-Barragan, Felipe, Seets, Trevor, Velten, Andreas

“… However, their performance is susceptible to hardware limitations, such as system bandwidth, maximum laser power, sensor data rates, and in-sensor memory and compute resources…”
Get full text