1 code implementation • 22 Mar 2024 • Yifan Zhang, Weiqi Chen, Zhaoyang Zhu, Dalin Qin, Liang Sun, Xue Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin
For the state-of-the-art (SOTA) model, the MSE is reduced by $33. 3\%$.
1 code implementation • 8 Mar 2024 • Yi-Fan Zhang, Weichen Yu, Qingsong Wen, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
In the realms of computer vision and natural language processing, Large Vision-Language Models (LVLMs) have become indispensable tools, proficient in generating textual descriptions based on visual inputs.
1 code implementation • 23 Feb 2024 • Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, Xin Liu
Training LLMs at this scale brings unprecedented challenges to training efficiency and stability.
no code implementations • 13 Feb 2024 • Fan Lyu, Kaile Du, Yuyang Li, Hanyu Zhao, Zhang Zhang, Guangcan Liu, Liang Wang
At the source stage, we transform a pre-trained deterministic model into a Bayesian Neural Network (BNN) via a variational warm-up strategy, injecting uncertainties into the model.
1 code implementation • 20 Dec 2023 • Yi-Fan Zhang, Zhang Zhang, Liang Wang, Tieniu Tan, Rong Jin
In an effort to address these issues, we delve into the realm of zero-shot machine-generated text detection.
no code implementations • 28 Nov 2023 • Yifan Zhang, Xue Wang, Tian Zhou, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
We demonstrate the effectiveness of \abbr through comprehensive experiments on multiple OOD detection benchmarks, extensive empirical studies show that \abbr significantly improves the performance of OOD detection over state-of-the-art methods.
1 code implementation • 21 Nov 2023 • Zhang Zhang, Ruyi Tao, Jiang Zhang
The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability.
1 code implementation • NeurIPS 2023 • Yi-Fan Zhang, Qingsong Wen, Xue Wang, Weiqi Chen, Liang Sun, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data.
1 code implementation • 18 Sep 2023 • Ming-Zhe Li, Zhen Jia, Zhang Zhang, Zhanyu Ma, Liang Wang
In order to solve this dilemma, we propose a multi-semantic fusion (MSF) model for improving the performance of GZSSAR, where two kinds of class-level textual descriptions (i. e., action descriptions and motion descriptions), are collected as auxiliary semantic information to enhance the learning efficacy of generalizable skeleton features.
Action Recognition Generalized Zero Shot skeletal action recognition +1
1 code implementation • 31 Aug 2023 • Andong Lu, Zhang Zhang, Yan Huang, Yifan Zhang, Chenglong Li, Jin Tang, Liang Wang
The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features.
no code implementations • 27 Aug 2023 • Jing Zhou, Xiaotong Fu, Xirong Li, Wei Feng, Zhang Zhang, Ying Ji
The most common type of lung cancer, lung adenocarcinoma (LUAD), has been increasingly detected since the advent of low-dose computed tomography screening technology.
1 code implementation • 25 Apr 2023 • Yi-Fan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is 50% higher than advanced TTA methods.
1 code implementation • CVPR 2023 • Wentao Chen, Chenyang Si, Zhang Zhang, Liang Wang, Zilei Wang, Tieniu Tan
Instead of the naive exploitation of semantic information for remedying classifiers, we explore leveraging semantic information as prompts to tune the visual feature extraction network adaptively.
1 code implementation • The Eleventh International Conference on Learning Representations (ICLR 2023) 2023 • Yifan Zhang, Xue Wang, Jian Liang, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data.
Ranked #5 on Domain Adaptation on Office-Home
no code implementations • 17 Dec 2022 • Zhen Jia, Zhang Zhang, Liang Wang, Tieniu Tan
Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value.
1 code implementation • 18 Aug 2022 • Yi-Fan Zhang, Jindong Wang, Jian Liang, Zhang Zhang, Baosheng Yu, Liang Wang, DaCheng Tao, Xing Xie
Our bound motivates two strategies to reduce the gap: the first one is ensembling multiple classifiers to enrich the hypothesis space, then we propose effective gap estimation methods for guiding the selection of a better hypothesis for the target.
1 code implementation • 16 Jul 2022 • Wentao Chen, Zhang Zhang, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan
Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class.
1 code implementation • 25 Apr 2022 • Zhang Zhang, Ruyi Tao, Yongzai Tao, Mingze Qi, Jiang Zhang
And experiments show that our model perform better on a network with higher Reachable CC.
1 code implementation • 30 Dec 2021 • Shenwang Jiang, Jianan Li, Ying Wang, Bo Huang, Zhang Zhang, Tingfa Xu
In practice, however, biased samples with corrupted labels and of tailed classes commonly co-exist in training data.
no code implementations • 5 Dec 2021 • Zhang Zhang, Yifeng Zeng, Yinghui Pan
Then, we transform the intention recognition into an un-supervised learning problem and adapt a clustering algorithm to group intentions of multiple agents through comparing their behavioural models.
no code implementations • 29 Sep 2021 • Yifan Zhang, Feng Li, Zhang Zhang, Liang Wang, DaCheng Tao, Tieniu Tan
However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.
4 code implementations • 29 Jun 2021 • Yi-Fan Song, Zhang Zhang, Caifeng Shan, Liang Wang
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints.
Ranked #17 on Skeleton Based Action Recognition on NTU RGB+D 120
no code implementations • 29 Mar 2021 • Yi-Fan Zhang, Zhang Zhang, Da Li, Zhen Jia, Liang Wang, Tieniu Tan
Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community.
no code implementations • 20 Jan 2021 • Yi-Fan Zhang, Weiqiang Ren, Zhang Zhang, Zhen Jia, Liang Wang, Tieniu Tan
(ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR.
1 code implementation • 20 Oct 2020 • Yi-Fan Song, Zhang Zhang, Caifeng Shan, Liang Wang
However, the complexity of the State-Of-The-Art (SOTA) models of this task tends to be exceedingly sophisticated and over-parameterized, where the low efficiency in model training and inference has obstructed the development in the field, especially for large-scale action datasets.
Ranked #25 on Skeleton Based Action Recognition on NTU RGB+D 120
3 code implementations • 9 Aug 2020 • Yi-Fan Song, Zhang Zhang, Caifeng Shan, Liang Wang
More crucially, on the synthetic occlusion and jittering datasets, the performance deterioration due to the occluded and disturbed joints can be significantly alleviated by utilizing the proposed RA-GCN.
Ranked #43 on Skeleton Based Action Recognition on NTU RGB+D 120
1 code implementation • IEEE Transactions on Multimedia 2020 • Cairong Zhao, Xinbi Lv, Zhang Zhang, WangMeng Zuo, Jun Wu, Duoqian Miao
The extraction of robust feature representations from pedestrian images through CNNs with a single deterministic pooling operation is problematic as the features in real pedestrian images are complex and diverse.
no code implementations • 18 Jan 2020 • Mengyuan Chen, Jiang Zhang, Zhang Zhang, Lun Du, Qiao Hu, Shuo Wang, Jiaqi Zhu
We carried out experiments on discrete and continuous time series data.
no code implementations • 15 Jul 2019 • Zhang Zhang, DaCheng Tao
In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts.
3 code implementations • 16 May 2019 • Yi-Fan Song, Zhang Zhang, Liang Wang
To enhance the robustness of action recognition models to incomplete skeletons, we propose a multi-stream graph convolutional network (GCN) for exploring sufficient discriminative features distributed over all skeleton joints.
Ranked #74 on Skeleton Based Action Recognition on NTU RGB+D
no code implementations • 6 Mar 2019 • Da Li, Zhang Zhang
The Large-Scale Pedestrian Retrieval Competition (LSPRC) mainly focuses on person retrieval which is an important end application in intelligent vision system of surveillance.
1 code implementation • 30 Dec 2018 • Zhang Zhang, Yi Zhao, Jing Liu, Shuo Wang, Ruyi Tao, Ruyue Xin, Jiang Zhang
We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.
1 code implementation • 12 Nov 2018 • Huimin Xu, Zhang Zhang, Lingfei Wu, Cheng-Jun Wang
Our analysis of thousands of movies and books reveals how these cultural products weave stereotypical gender roles into morality tales and perpetuate gender inequality through storytelling.
no code implementations • CVPR 2018 • Houjing Huang, Dangwei Li, Zhang Zhang, Xiaotang Chen, Kaiqi Huang
Person re-identification (ReID) is the task of retrieving particular persons across different cameras.
no code implementations • CVPR 2017 • Dangwei Li, Xiaotang Chen, Zhang Zhang, Kaiqi Huang
It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a fundamental problem in ReID and is still an open problem today.
Ranked #110 on Person Re-Identification on Market-1501
no code implementations • 29 Nov 2016 • Kai Yu, Yang Zhou, Da Li, Zhang Zhang, Kaiqi Huang
Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world.
no code implementations • 17 Nov 2016 • Kai Yu, Biao Leng, Zhang Zhang, Dangwei Li, Kaiqi Huang
Based on GoogLeNet, firstly, a set of mid-level attribute features are discovered by novelly designed detection layers, where a max-pooling based weakly-supervised object detection technique is used to train these layers with only image-level labels without the need of bounding box annotations of pedestrian attributes.
no code implementations • CVPR 2016 • Zhang Zhang, Kaiqi Huang, Tieniu Tan, Peipei Yang, Jun Li
For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data.
2 code implementations • 23 Mar 2016 • Dangwei Li, Zhang Zhang, Xiaotang Chen, Haibin Ling, Kaiqi Huang
RAP has in total 41, 585 pedestrian samples, each of which is annotated with 72 attributes as well as viewpoints, occlusions, body parts information.