Publications (33)
Voxel-based Point Cloud Geometry Compression with Space-to-Channel Context
Bojun Liu, Yangzhi Ma, Ao Luo +2
Voxel-based methods are among the most efficient for point cloud geometry compression, particularly with dense point clouds. However, they face limitations due to a restricted rece…
Learning Optical Flow with Adaptive Graph Reasoning
Ao Luo, Fan Yang, Kunming Luo +3
Estimating per-pixel motion between video frames, known as optical flow, is a long-standing problem in video understanding and analysis. Most contemporary optical flow techniques l…
ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling
Kunming Luo, Ao Luo, Chuan Wang +2
We present an unsupervised optical flow estimation method by proposing an adaptive pyramid sampling in the deep pyramid network. Specifically, in the pyramid downsampling, we propo…
Tyan-WP: A Wind Power Foundation Model for Ultra-Short-Term Probabilistic Forecasting
Jiahui Huang, Ao Luo, Lei Liu +6
Global wind power capacity, especially in China, is booming, with new farms spanning diverse terrains and climates. The industry urgently needs accurate wind power foundation model…
Off-the-shelf Vision Models Benefit Image Manipulation Localization
Zhengxuan Zhang, Keji Song, Junmin Hu +2
Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differences between manipulation-spe…
Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model
Shijian Wang, Linxin Song, Jieyu Zhang +9
Current multimodal language model (MLM) training approaches overlook the influence of instruction templates. Previous research deals with this problem by leveraging hand-crafted or…
MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classification
Jianwei Zhao, Xin Li, Fan Yang +5
Whole Slide Image (WSI) classification poses unique challenges due to the vast image size and numerous non-informative regions, which introduce noise and cause data imbalance durin…
Enhancement of baryon-to-meson ratios around jets as a signature of medium response
Ao Luo, Ya-Xian Mao, Guang-You Qin +2
We present a unique signal of jet-induced medium excitations: the enhancement of baryon-to-meson ratios around the quenched jets.To illustrate this, we study jet-particle correlati…
SCP: Spherical-Coordinate-based Learned Point Cloud Compression
Ao Luo, Linxin Song, Keisuke Nonaka +4
In recent years, the task of learned point cloud compression has gained prominence. An important type of point cloud, the spinning LiDAR point cloud, is generated by spinning LiDAR…
LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models
Hai Jiang, Ao Luo, Xiaohong Liu +2
In this paper, we propose a diffusion-based unsupervised framework that incorporates physically explainable Retinex theory with diffusion models for low-light image enhancement, na…
Memory-Efficient Learned Image Compression with Pruned Hyperprior Module
Ao Luo, Heming Sun, Jinming Liu +1
Learned Image Compression (LIC) gradually became more and more famous in these years. The hyperprior-module-based LIC models have achieved remarkable rate-distortion performance. H…
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training
Yan Zeng, Wangchunshu Zhou, Ao Luo +2
In this paper, we introduce Cross-View Language Modeling, a simple and effective pre-training framework that unifies cross-lingual and cross-modal pre-training with shared architec…
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
Kunyu Peng, Di Wen, Kailun Yang +6
In Open-Set Domain Generalization (OSDG), the model is exposed to both new variations of data appearance (domains) and open-set conditions, where both known and novel categories ar…
WebSRC: A Dataset for Web-Based Structural Reading Comprehension
Xingyu Chen, Zihan Zhao, Lu Chen +5
Web search is an essential way for humans to obtain information, but it's still a great challenge for machines to understand the contents of web pages. In this paper, we introduce…
DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis
Xinglong Luo, Ao Luo, Zhengning Wang +5
Image alignment is a fundamental task in computer vision with broad applications. Existing methods predominantly employ optical flow-based image warping. However, this technique is…
Jet shape and redistribution of the lost energy from jets in Pb+Pb collisions at the LHC in a multiphase transport model
Ao Luo, Ya-Xian Mao, Guang-You Qin +2
Jet-medium interaction involves two important effects: jet energy loss and medium response. The search for jet-induced medium excitations is one of the hot topics in jet quenching…
Learning Efficient Meshflow and Optical Flow from Event Cameras
Xinglong Luo, Ao Luo, Kunming Luo +4
In this paper, we explore the problem of event-based meshflow estimation, a novel task that involves predicting a spatially smooth sparse motion field from event cameras. To start,…
Fast Portrait Segmentation with Highly Light-weight Network
Yuezun Li, Ao Luo, Siwei Lyu
In this paper, we describe a fast and light-weight portrait segmentation method based on a new highly light-weight backbone (HLB) architecture. The core element of HLB is a bottlen…
Deep-VFX: Deep Action Recognition Driven VFX for Short Video
Ao Luo, Ning Xie, Zhijia Tao +1
Human motion is a key function to communicate information. In the application, short-form mobile video is so popular all over the world such as Tik Tok. The users would like to add…
FastForensics: Efficient Two-Stream Design for Real-Time Image Manipulation Detection
Yangxiang Zhang, Yuezun Li, Ao Luo +2
With the rise in popularity of portable devices, the spread of falsified media on social platforms has become rampant. This necessitates the timely identification of authentic cont…
Adaptive In-conversation Team Building for Language Model Agents
Linxin Song, Jiale Liu, Jieyu Zhang +5
Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks, while the effective design of multiple agents for a particula…
Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments
Di Wen, Lei Qi, Kunyu Peng +9
Despite substantial progress in video understanding, most existing datasets are limited to Earth's gravitational conditions. However, microgravity alters human motion, interactions…
Low-Light Image Enhancement with Wavelet-based Diffusion Models
Hai Jiang, Ao Luo, Songchen Han +2
Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration.…
Overall momentum balance and redistribution of the lost energy in asymmetric dijet events in 2.76~ATeV Pb-Pb collisions with a multi-phase transport model
Zhan Gao, Ao Luo, Guo-Liang Ma +2
The overall transverse momentum balance and the redistribution of the lost energy from hard jets for asymmetric dijet events in PbPb collisions at 2.76~ATeV at the LHC is studied w…
GAFlow: Incorporating Gaussian Attention into Optical Flow
Ao Luo, Fan Yang, Xin Li +4
Optical flow, or the estimation of motion fields from image sequences, is one of the fundamental problems in computer vision. Unlike most pixel-wise tasks that aim at achieving con…
RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos
Yunhui Han, Kunming Luo, Ao Luo +4
Obtaining the ground truth labels from a video is challenging since the manual annotation of pixel-wise flow labels is prohibitively expensive and laborious. Besides, existing appr…
Probing medium response via strangeness enhancement around quenched jets
Ao Luo, Shanshan Cao, Guang-You Qin
Jet-induced medium excitation is a crucial part of jet interactions with the quark-gluon plasma (QGP) in relativistic heavy-ion collisions, and has recently been confirmed by exper…
Cascade Graph Neural Networks for RGB-D Salient Object Detection
Ao Luo, Xin Li, Fan Yang +3
In this paper, we study the problem of salient object detection (SOD) for RGB-D images using both color and depth information.A major technical challenge in performing salient obje…
FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection
Jianwei Zhao, Xin Li, Fan Yang +4
Detecting objects seamlessly blended into their surroundings represents a complex task for both human cognitive capabilities and advanced artificial intelligence algorithms. Curren…
Better Explain Transformers by Illuminating Important Information
Linxin Song, Yan Cui, Ao Luo +2
Transformer-based models excel in various natural language processing (NLP) tasks, attracting countless efforts to explain their inner workings. Prior methods explain Transformers…
RecDiffusion: Rectangling for Image Stitching with Diffusion Models
Tianhao Zhou, Haipeng Li, Ziyi Wang +5
Image stitching from different captures often results in non-rectangular boundaries, which is often considered unappealing. To solve non-rectangular boundaries, current solutions i…
Learning Optical Flow from Event Camera with Rendered Dataset
Xinglong Luo, Kunming Luo, Ao Luo +3
We study the problem of estimating optical flow from event cameras. One important issue is how to build a high-quality event-flow dataset with accurate event values and flow labels…
Hybrid Graph Neural Networks for Crowd Counting
Ao Luo, Fan Yang, Xin Li +4
Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale…