280 citations · 488 across the 14 of their papers we have counts for
14 papers
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Yuhui Xu, Lingxi Xie, Xiaotao Gu +6
Recently years have witnessed a rapid development of large language models (LLMs). Despite the strong ability in many language-understanding tasks, the heavy computational burden l…
Multi-modal Prompting for Low-Shot Temporal Action Localization
Chen Ju, Zeqian Li, Peisen Zhao +5
In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instanc…
Gradient Concealment: Free Lunch for Defending Adversarial Attacks
Sen Pei, Jiaxi Sun, Xiaopeng Zhang +1
Recent studies show that the deep neural networks (DNNs) have achieved great success in various tasks. However, even the \emph{state-of-the-art} deep learning based classifiers are…
Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
Jiemin Fang, Taoran Yi, Xinggang Wang +5
Neural radiance fields (NeRF) have shown great success in modeling 3D scenes and synthesizing novel-view images. However, most previous NeRF methods take much time to optimize one…
The KFIoU Loss for Rotated Object Detection
Xue Yang, Yue Zhou, Gefan Zhang +5
Differing from the well-developed horizontal object detection area whereby the computing-friendly IoU based loss is readily adopted and well fits with the detection metrics. In con…
Deep Deformation Detail Synthesis for Thin Shell Models
Lan Chen, Lin Gao, Jie Yang +4
In physics-based cloth animation, rich folds and detailed wrinkles are achieved at the cost of expensive computational resources and huge labor tuning. Data-driven techniques make…
Multi-feature super-resolution network for cloth wrinkle synthesis
Lan Chen, Juntao Ye, Xiaopeng Zhang
Existing physical cloth simulators suffer from expensive computation and difficulties in tuning mechanical parameters to get desired wrinkling behaviors. Data-driven methods provid…
Circumventing Outliers of AutoAugment with Knowledge Distillation
Longhui Wei, An Xiao, Lingxi Xie +3
AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper se…
MGCN: Descriptor Learning using Multiscale GCNs
Yiqun Wang, Jing Ren, Dong-Ming Yan +3
We propose a novel framework for computing descriptors for characterizing points on three-dimensional surfaces. First, we present a new non-learned feature that uses graph wavelets…
Capacity Preserving Mapping for High-dimensional Data Visualization
Rongrong Wang, Xiaopeng Zhang
We provide a rigorous mathematical treatment to the crowding issue in data visualization when high dimensional data sets are projected down to low dimensions for visualization. By…
Hardware-Efficient Guided Image Filtering For Multi-Label Problem
Longquan Dai, Mengke Yuan, Zechao Li +2
The Guided Filter (GF) is well-known for its linear complexity. However, when filtering an image with an n-channel guidance, GF needs to invert an n x n matrix for each pixel. To t…
Speeding Up the Bilateral Filter: A Joint Acceleration Way
Longquan Dai, Mengke Yuan, Xiaopeng Zhang
Computational complexity of the brute-force implementation of the bilateral filter (BF) depends on its filter kernel size. To achieve the constant-time BF whose complexity is irrel…
Image Retargeting by Content-Aware Synthesis
Weiming Dong, Fuzhang Wu, Yan Kong +3
Real-world images usually contain vivid contents and rich textural details, which will complicate the manipulation on them. In this paper, we design a new framework based on conten…
Inverse Procedural Modeling of Facade Layouts
Fuzhang Wu, Dong-Ming Yan, Weiming Dong +2
In this paper, we address the following research problem: How can we generate a meaningful split grammar that explains a given facade layout? To evaluate if a grammar is meaningful…