1 code implementation • ECCV 2020 • Niamul Quader, Md Mafijul Islam Bhuiyan, Juwei Lu, Peng Dai, Wei Li
We propose novel approaches for simultaneously identifying important weights of a convolutional neural network (ConvNet) and providing more attention to the important weights during training.
no code implementations • ECCV 2020 • Niamul Quader, Juwei Lu, Peng Dai, Wei Li
State-of-the-art approaches to video-based action and gesture recognition often employ two key concepts: First, they employ multistream processing; second, they use an ensemble of convolutional networks.
Ranked #1 on Action Classification on Jester test
no code implementations • 13 Apr 2024 • Henry Peng Zou, Gavin Heqing Yu, Ziwei Fan, Dan Bu, Han Liu, Peng Dai, Dongmei Jia, Cornelia Caragea
To address these issues, we introduce EIVEN, a data- and parameter-efficient generative framework that pioneers the use of multimodal LLM for implicit attribute value extraction.
1 code implementation • 28 Mar 2024 • Xiaoyang Lyu, Chirui Chang, Peng Dai, Yang-tian Sun, Xiaojuan Qi
Scene reconstruction from multi-view images is a fundamental problem in computer vision and graphics.
no code implementations • 6 Mar 2024 • Peng Dai, Yang Zhang, Tao Liu, Zhen Fan, Tianyuan Du, Zhuo Su, Xiaozheng Zheng, Zeming Li
It is especially challenging to achieve real-time human motion tracking on a standalone VR Head-Mounted Display (HMD) such as Meta Quest and PICO.
no code implementations • 24 Jan 2024 • Chuan Guo, Yuxuan Mu, Xinxin Zuo, Peng Dai, Youliang Yan, Juwei Lu, Li Cheng
Building upon this, we present a novel generative model that produces diverse stylization results of a single motion (latent) code.
no code implementations • 11 Jan 2024 • Peng Dai, Feitong Tan, Xin Yu, yinda zhang, Xiaojuan Qi
To this end, we propose a new method, GO-NeRF, capable of utilizing scene context for high-quality and harmonious 3D object generation within an existing NeRF.
no code implementations • 14 Dec 2023 • Shaocong Wang, Yizhao Gao, Yi Li, Woyu Zhang, Yifei Yu, Bo wang, Ning Lin, Hegan Chen, Yue Zhang, Yang Jiang, Dingchen Wang, Jia Chen, Peng Dai, Hao Jiang, Peng Lin, Xumeng Zhang, Xiaojuan Qi, Xiaoxin Xu, Hayden So, Zhongrui Wang, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu
Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
no code implementations • ICCV 2023 • Xin Yu, Peng Dai, Wenbo Li, Lan Ma, Zhengzhe Liu, Xiaojuan Qi
In this work, we focus on synthesizing high-quality textures on 3D meshes.
1 code implementation • CVPR 2023 • Peng Dai, yinda zhang, Xin Yu, Xiaoyang Lyu, Xiaojuan Qi
Rendering novel view images is highly desirable for many applications.
2 code implementations • 24 Mar 2023 • Zhengzhe Liu, Peng Dai, Ruihui Li, Xiaojuan Qi, Chi-Wing Fu
The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistency between rendered images and the input text.
1 code implementation • ICCV 2023 • Xiaoyang Lyu, Peng Dai, Zizhang Li, Dongyu Yan, Yi Lin, Yifan Peng, Xiaojuan Qi
We found that the color rendering loss results in optimization bias against low-intensity areas, causing gradient vanishing and leaving these areas unoptimized.
no code implementations • 17 Feb 2023 • Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Liefeng Bo
Recent years have witnessed the emerging success of many deep learning-based recommendation models for augmenting collaborative filtering architectures with various neural network architectures, such as multi-layer perceptron and autoencoder.
no code implementations • ICCV 2023 • Bin Shao, Jianzhuang Liu, Renjing Pei, Songcen Xu, Peng Dai, Juwei Lu, Weimian Li, Youliang Yan
However, compared to image-language pre-training, VLP has lagged far behind due to the lack of large amounts of video-text pairs.
no code implementations • CVPR 2023 • Renjing Pei, Jianzhuang Liu, Weimian Li, Bin Shao, Songcen Xu, Peng Dai, Juwei Lu, Youliang Yan
Pre-training a vison-language model and then fine-tuning it on downstream tasks have become a popular paradigm.
2 code implementations • 9 Sep 2022 • Zhengzhe Liu, Peng Dai, Ruihui Li, Xiaojuan Qi, Chi-Wing Fu
Text-guided 3D shape generation remains challenging due to the absence of large paired text-shape data, the substantial semantic gap between these two modalities, and the structural complexity of 3D shapes.
1 code implementation • 20 Jul 2022 • Xin Yu, Peng Dai, Wenbo Li, Lan Ma, Jiajun Shen, Jia Li, Xiaojuan Qi
With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i. e., ultra-high-definition) images.
Ranked #1 on Image Restoration on UHDM
1 code implementation • 31 May 2022 • Peng Dai, Yiqiang Feng, Renliang Weng, ChangShui Zhang
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance.
1 code implementation • CVPR 2022 • Peng Dai, Xin Yu, Lan Ma, Baoheng Zhang, Jia Li, Wenbo Li, Jiajun Shen, Xiaojuan Qi
Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras.
no code implementations • 26 Jan 2022 • Houpu Yao, Jiazhou Wang, Peng Dai, Liefeng Bo, Yanqing Chen
As there is a growing interest in utilizing data across multiple resources to build better machine learning models, many vertically federated learning algorithms have been proposed to preserve the data privacy of the participating organizations.
1 code implementation • IJCAI 2021 • Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Liefeng Bo, Xiyue Zhang, Tianyi Chen
Crime prediction is crucial for public safety and resource optimization, yet is very challenging due to two aspects: i) the dynamics of criminal patterns across time and space, crime events are distributed unevenly on both spatial and temporal domains; ii) time-evolving dependencies between different types of crimes (e. g., Theft, Robbery, Assault, Damage) which reveal fine-grained semantics of crimes.
1 code implementation • 7 Jan 2022 • Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Mengyin Lu, Liefeng Bo
Due to the overlook of user's multi-behavioral patterns over different items, existing recommendation methods are insufficient to capture heterogeneous collaborative signals from user multi-behavior data.
no code implementations • 21 Dec 2021 • Varshanth R. Rao, Md Ibrahim Khalil, Haoda Li, Peng Dai, Juwei Lu
In this paper, we propose a framework centering around a novel architecture called the Event Decomposition Recomposition Network (EDRNet) to tackle the Audio-Visual Event (AVE) localization problem in the supervised and weakly supervised settings.
no code implementations • 11 Dec 2021 • Hanwen Liang, Niamul Quader, Zhixiang Chi, Lizhe Chen, Peng Dai, Juwei Lu, Yang Wang
Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e. g. speed, temporal order, etc.
1 code implementation • 8 Oct 2021 • Chao Huang, Huance Xu, Yong Xu, Peng Dai, Lianghao Xia, Mengyin Lu, Liefeng Bo, Hao Xing, Xiaoping Lai, Yanfang Ye
While many recent efforts show the effectiveness of neural network-based social recommender systems, several important challenges have not been well addressed yet: (i) The majority of models only consider users' social connections, while ignoring the inter-dependent knowledge across items; (ii) Most of existing solutions are designed for singular type of user-item interactions, making them infeasible to capture the interaction heterogeneity; (iii) The dynamic nature of user-item interactions has been less explored in many social-aware recommendation techniques.
1 code implementation • 8 Oct 2021 • Xiyue Zhang, Chao Huang, Yong Xu, Lianghao Xia, Peng Dai, Liefeng Bo, Junbo Zhang, Yu Zheng
Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment.
1 code implementation • 8 Oct 2021 • Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Bo Zhang, Liefeng Bo
The overlook of multiplex behavior relations can hardly recognize the multi-modal contextual signals across different types of interactions, which limit the feasibility of current recommendation methods.
1 code implementation • 8 Oct 2021 • Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Xiyue Zhang, Hongsheng Yang, Jian Pei, Liefeng Bo
In particular: i) complex inter-dependencies across different types of user behaviors; ii) the incorporation of knowledge-aware item relations into the multi-behavior recommendation framework; iii) dynamic characteristics of multi-typed user-item interactions.
1 code implementation • 8 Oct 2021 • Chao Huang, Jiahui Chen, Lianghao Xia, Yong Xu, Peng Dai, Yanqing Chen, Liefeng Bo, Jiashu Zhao, Jimmy Xiangji Huang
The learning process of intra- and inter-session transition dynamics are integrated, to preserve the underlying low- and high-level item relationships in a common latent space.
1 code implementation • 8 Oct 2021 • Xiaoling Long, Chao Huang, Yong Xu, Huance Xu, Peng Dai, Lianghao Xia, Liefeng Bo
To model relation heterogeneity, we design a metapath-guided heterogeneous graph neural network to aggregate feature embeddings from different types of meta-relations across users and items, em-powering SMIN to maintain dedicated representations for multi-faceted user- and item-wise dependencies.
1 code implementation • 8 Oct 2021 • Lianghao Xia, Yong Xu, Chao Huang, Peng Dai, Liefeng Bo
Modern recommender systems often embed users and items into low-dimensional latent representations, based on their observed interactions.
no code implementations • ICCV 2021 • Deepak Sridhar, Niamul Quader, Srikanth Muralidharan, Yaoxin Li, Peng Dai, Juwei Lu
Our attention mechanism outperforms prior self-attention modules such as the squeeze-and-excitation in action detection task.
1 code implementation • ICCV 2021 • Hanwen Liang, Qiong Zhang, Peng Dai, Juwei Lu
State of the art (SOTA) few-shot learning (FSL) methods suffer significant performance drop in the presence of domain differences between source and target datasets.
3 code implementations • 8 Jul 2021 • Bo Liu, Chaowei Tan, Jiazhou Wang, Tao Zeng, Huasong Shan, Houpu Yao, Heng Huang, Peng Dai, Liefeng Bo, Yanqing Chen
We use this platform to demonstrate our research and development results on privacy preserving machine learning algorithms.
1 code implementation • CVPR 2021 • Peng Dai, Renliang Weng, Wongun Choi, ChangShui Zhang, Zhangping He, Wei Ding
In this paper, we propose a novel proposal-based learnable framework, which models MOT as a proposal generation, proposal scoring and trajectory inference paradigm on an affinity graph.
no code implementations • 23 Dec 2019 • Yuxiang Ren, Hao Zhu, Jiawei Zhang, Peng Dai, Liefeng Bo
Existing fraud detection methods try to identify unexpected dense subgraphs and treat related nodes as suspicious.
1 code implementation • CVPR 2020 • Peng Dai, yinda zhang, Zhuwen Li, Shuaicheng Liu, Bing Zeng
The input to the network is the raw point cloud of a scene and the output are image or image sequences from a novel view or along a novel camera trajectory.
1 code implementation • 19 Nov 2019 • Yuxiang Ren, Bo Liu, Chao Huang, Peng Dai, Liefeng Bo, Jiawei Zhang
The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering.
Ranked #7 on Heterogeneous Node Classification on DBLP (PACT) 14k
no code implementations • 14 Sep 2016 • Peng Dai, Xue Teng, Frank Rudzicz, Ing Yann Soon
Experiments are carried out on the AURORA2 database and show that the word recognition rate using our proposed feature extraction method is significantly increased over the baseline.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 16 Jan 2014 • Peng Dai, Mausam, Daniel Sabby Weld, Judy Goldsmith
Value iteration is a powerful yet inefficient algorithm for Markov decision processes (MDPs) because it puts the majority of its effort into backing up the entire state space, which turns out to be unnecessary in many cases.