41 citations · 162 across the 24 of their papers we have counts for
24 papers
HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models
Yu Xue, Haoxuan Qu, Zhuoling Li +5
Training-free text-to-high-resolution image generation has recently attracted growing research attention. However, existing studies on this task primarily focus on adapting off-the…
Transforming Future Data Center Operations and Management via Physical AI
Zhiwei Cao, Minghao Li, Feng Lin +4
Data centers (DCs) as mission-critical infrastructures are pivotal in powering the growth of artificial intelligence (AI) and the digital economy. The evolution from Internet DC to…
Unified Locomotion Transformer with Simultaneous Sim-to-Real Transfer for Quadrupeds
Dikai Liu, Tianwei Zhang, Jianxiong Yin +1
Quadrupeds have gained rapid advancement in their capability of traversing across complex terrains. The adoption of deep Reinforcement Learning (RL), transformers and various knowl…
Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning
Meng Shen, Yake Wei, Jianxiong Yin +3
Training multimodal models requires a large amount of labeled data. Active learning (AL) aim to reduce labeling costs. Most AL methods employ warm-start approaches, which rely on s…
Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion
Dikai Liu, Tianwei Zhang, Jianxiong Yin +1
With the rising focus on quadrupeds, a generalized policy capable of handling different robot models and sensor inputs becomes highly beneficial. Although several methods have been…
Learning Gabor Texture Features for Fine-Grained Recognition
Lanyun Zhu, Tianrun Chen, Jianxiong Yin +2
Extracting and using class-discriminative features is critical for fine-grained recognition. Existing works have demonstrated the possibility of applying deep CNNs to exploit featu…
Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation
Zhehua Zhou, Jiayang Song, Xuan Xie +5
As a representative cyber-physical system (CPS), robotic manipulator has been widely adopted in various academic research and industrial processes, indicating its potential to act…
Towards Balanced Active Learning for Multimodal Classification
Meng Shen, Yizheng Huang, Jianxiong Yin +3
Training multimodal networks requires a vast amount of data due to their larger parameter space compared to unimodal networks. Active learning is a widely used technique for reduci…
Continual Semantic Segmentation with Automatic Memory Sample Selection
Lanyun Zhu, Tianrun Chen, Jianxiong Yin +2
Continual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training. To alleviate the catastrophic forgetting issue in…
MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs
Huaizheng Zhang, Yuanming Li, Wencong Xiao +7
New architecture GPUs like A100 are now equipped with multi-instance GPU (MIG) technology, which allows the GPU to be partitioned into multiple small, isolated instances. This tech…
Saving the Limping: Fault-tolerant Quadruped Locomotion via Reinforcement Learning
Dikai Liu, Tianwei Zhang, Jianxiong Yin +1
Modern quadrupeds are skillful in traversing or even sprinting on uneven terrains in a remote uncontrolled environment. However, survival in the wild requires not only maneuverabil…
Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study
Yuecong Xu, Jianfei Yang, Haozhi Cao +5
While action recognition (AR) has gained large improvements with the introduction of large-scale video datasets and the development of deep neural networks, AR models robust to cha…
Self-Supervised Video Representation Learning by Video Incoherence Detection
Haozhi Cao, Yuecong Xu, Jianfei Yang +4
This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of hu…
InferBench: Understanding Deep Learning Inference Serving with an Automatic Benchmarking System
Huaizheng Zhang, Yizheng Huang, Yonggang Wen +2
Deep learning (DL) models have become core modules for many applications. However, deploying these models without careful performance benchmarking that considers both hardware and…
Effective Action Recognition with Embedded Key Point Shifts
Haozhi Cao, Yuecong Xu, Jianfei Yang +3
Temporal feature extraction is an essential technique in video-based action recognition. Key points have been utilized in skeleton-based action recognition methods but they require…
MLModelCI: An Automatic Cloud Platform for Efficient MLaaS
Huaizheng Zhang, Yuanming Li, Yizheng Huang +3
MLModelCI provides multimedia researchers and developers with a one-stop platform for efficient machine learning (ML) services. The system leverages DevOps techniques to optimize,…
PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition
Yuecong Xu, Haozhi Cao, Jianfei Yang +3
Long-range spatiotemporal dependencies capturing plays an essential role in improving video features for action recognition. The non-local block inspired by the non-local means is…
ARID: A New Dataset for Recognizing Action in the Dark
Yuecong Xu, Jianfei Yang, Haozhi Cao +3
The task of action recognition in dark videos is useful in various scenarios, e.g., night surveillance and self-driving at night. Though progress has been made in the action recogn…
Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition
Yuecong Xu, Jianfei Yang, Kezhi Mao +2
Temporal feature extraction is an important issue in video-based action recognition. Optical flow is a popular method to extract temporal feature, which produces excellent performa…
Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention
Qingyi Tao, Zongyuan Ge, Jianfei Cai +2
Lesion detection from computed tomography (CT) scans is challenging compared to natural object detection because of two major reasons: small lesion size and small inter-class varia…
Secure Deep Learning Engineering: A Software Quality Assurance Perspective
Lei Ma, Felix Juefei-Xu, Minhui Xue +7
Over the past decades, deep learning (DL) systems have achieved tremendous success and gained great popularity in various applications, such as intelligent machines, image processi…
DeepHunter: Hunting Deep Neural Network Defects via Coverage-Guided Fuzzing
Xiaofei Xie, Lei Ma, Felix Juefei-Xu +7
In company with the data explosion over the past decade, deep neural network (DNN) based software has experienced unprecedented leap and is becoming the key driving force of many n…
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
Jason Kuen, Xiangfei Kong, Zhe Lin +4
It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference c…
Fast MPEG-CDVS Encoder with GPU-CPU Hybrid Computing
Lingyu Duan, Wei Sun, Xinfeng Zhang +7
The compact descriptors for visual search (CDVS) standard from ISO/IEC moving pictures experts group (MPEG) has succeeded in enabling the interoperability for efficient and effecti…