no code implementations • 5 Nov 2024 • Kunyu Feng, Yue Ma, Bingyuan Wang, Chenyang Qi, Haozhe Chen, Qifeng Chen, Zeyu Wang
Compared to UNet, Diffusion Transformers (DiT) demonstrate superior capabilities to effectively capture the long-range dependencies among patches, leading to higher-quality image generation.
no code implementations • 27 Sep 2024 • Weichen Dai, Yezeng Chen, Zijie Dai, Zhijie Huang, Yubo Liu, Yixuan Pan, Baiyang Song, Chengli Zhong, Xinhe Li, Zeyu Wang, Zhuoying Feng, Yi Zhou
Artificial intelligence is gradually demonstrating its immense potential, and increasing attention is being given to how AI can be harnessed to advance scientific research.
no code implementations • 21 Sep 2024 • Kanghao Chen, Zeyu Wang, Lin Wang
In this paper, we propose ExFMan, the first neural rendering framework that unveils the possibility of rendering high-quality humans in rapid motion with a hybrid frame-based RGB and bio-inspired event camera.
no code implementations • 8 Sep 2024 • Zeyu Cai, Duotun Wang, Yixun Liang, Zhijing Shao, Ying-Cong Chen, Xiaohang Zhan, Zeyu Wang
Score Distillation Sampling (SDS) has emerged as a prevalent technique for text-to-3D generation, enabling 3D content creation by distilling view-dependent information from text-to-2D guidance.
no code implementations • 30 Aug 2024 • Yiran Chen, Anyi Rao, Xuekun Jiang, Shishi Xiao, Ruiqing Ma, Zeyu Wang, Hui Xiong, Bo Dai
With advancements in video generative AI models (e. g., SORA), creators are increasingly using these techniques to enhance video previsualization.
no code implementations • 30 Aug 2024 • Juncan Deng, Shuaiting Li, Zeyu Wang, Hong Gu, Kedong Xu, Kejie Huang
Then, using the zero-data and block-wise calibration method, the optimal assignment from the set is efficiently selected while calibrating the codebook.
1 code implementation • 22 Aug 2024 • Parvin Malekzadeh, Zissis Poulos, Jacky Chen, Zeyu Wang, Konstantinos N. Plataniotis
However, these risk measures depend on the accurate estimation of extreme quantiles in the loss distribution's tail, which can be imprecise in QR-based DRL due to the rarity and extremity of tail data, as highlighted in the literature.
no code implementations • 22 Aug 2024 • Bingyuan Wang, Qifeng Chen, Zeyu Wang
The integration of generative AI in visual art has revolutionized not only how visual content is created but also how AI interacts with and reflects the underlying domain knowledge.
no code implementations • 20 Aug 2024 • Zhijing Shao, Duotun Wang, Qing-Yao Tian, Yao-Dong Yang, Hengyu Meng, Zeyu Cai, Bo Dong, Yu Zhang, Kang Zhang, Zeyu Wang
To drive the facial expressions, instead of the commonly used 3D Morphable Models (3DMMs) in 3D head avatars, we propose to adopt the expression latent space trained solely on 2D portrait images, bridging the gap between 2D talking faces and 3D avatars.
no code implementations • 20 Aug 2024 • Zhongliang Guo, Lei Fang, Jingyu Lin, Yifei Qian, Shuai Zhao, Zeyu Wang, Junhao Dong, Cunjian Chen, Ognjen Arandjelović, Chun Pong Lau
Recent advancements in generative AI, particularly Latent Diffusion Models (LDMs), have revolutionized image synthesis and manipulation.
1 code implementation • 16 Aug 2024 • Kang Du, Zhihao Liang, Zeyu Wang
We present GS-ID, a novel framework for illumination decomposition on Gaussian Splatting, achieving photorealistic novel view synthesis and intuitive light editing.
no code implementations • 15 Aug 2024 • Zeyu Wang, Zhenzhen Weng, Serena Yeung-Levy
Humans continuously perceive and process visual signals.
no code implementations • 23 Jul 2024 • Zeyu Wang, Weichen Dai, Xiangyu Zhou, Ji Qi, Yi Zhou
Vision Transformer and its variants have been adopted in many visual tasks due to their powerful capabilities, which also bring significant challenges in computation and storage.
1 code implementation • 22 Jul 2024 • Zeyu Wang, Jingyu Lin, Yifei Qian, Yi Huang, Shicen Tian, Bosong Chai, Juncan Deng, Qu Yang, Lan Du, Cunjian Chen, Kejie Huang
However, most diffusion models are limited to visible RGB image generation.
no code implementations • 16 Jul 2024 • Zeyu Wang, Zecheng Hao, Jingyu Lin, Yuchao Feng, Yufei Guo
This study introduces a novel Remote Sensing (RS) Urban Prediction (UP) task focused on future urban planning, which aims to forecast urban layouts by utilizing information from existing urban layouts and planned change maps.
no code implementations • 8 Jul 2024 • Kanghao Chen, Hangyu Li, Jiazhou Zhou, Zeyu Wang, Lin Wang
However, due to diffusion models' inherent diversity and randomness, it is hardly possible to directly apply them to achieve spatial and temporal consistency for E2V reconstruction.
no code implementations • 17 Jun 2024 • Jiaqi Wang, Yuhang Zang, Pan Zhang, Tao Chu, Yuhang Cao, Zeyi Sun, Ziyu Liu, Xiaoyi Dong, Tong Wu, Dahua Lin, Zeming Chen, Zhi Wang, Lingchen Meng, Wenhao Yao, Jianwei Yang, Sihong Wu, Zhineng Chen, Zuxuan Wu, Yu-Gang Jiang, Peixi Wu, Bosong Chai, Xuan Nie, Longquan Yan, Zeyu Wang, Qifan Zhou, Boning Wang, Jiaqi Huang, Zunnan Xu, Xiu Li, Kehong Yuan, Yanyan Zu, Jiayao Ha, Qiong Gao, Licheng Jiao
2) Open Vocabulary Object Detection: This track goes a step further, requiring algorithms to detect objects from an open set of categories, including unknown objects.
no code implementations • 13 Jun 2024 • Peixi Wu, Bosong Chai, Xuan Nie, Longquan Yan, Zeyu Wang, Qifan Zhou, Boning Wang, Yansong Peng, Hebei Li
In this technical report, we present our findings from the research conducted on the Vast Vocabulary Visual Detection (V3Det) dataset for Supervised Vast Vocabulary Visual Detection task.
no code implementations • 12 Jun 2024 • Xianhang Li, Haoqin Tu, Mude Hui, Zeyu Wang, Bingchen Zhao, Junfei Xiao, Sucheng Ren, Jieru Mei, Qing Liu, Huangjie Zheng, Yuyin Zhou, Cihang Xie
For discriminative models like CLIP, we observe enhanced zero-shot performance in cross-modal retrieval tasks.
Ranked #96 on Visual Question Answering on MM-Vet
1 code implementation • 9 Jun 2024 • Zeyu Wang, Chen Li, Huiying Xu, Xinzhong Zhu
To further enhance detection performance, Transformer-based structures have been introduced, significantly expanding the model's receptive field and achieving notable performance gains.
1 code implementation • 8 Jun 2024 • Sucheng Ren, Xiaoke Huang, Xianhang Li, Junfei Xiao, Jieru Mei, Zeyu Wang, Alan Yuille, Yuyin Zhou
This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentation, denoising, and inpainting -- within a unified image-to-image generation framework.
1 code implementation • 24 May 2024 • Zeyu Wang, Tianyi Jiang, Yao Lu, Xiaoze Bao, Shanqing Yu, Bin Wei, Qi Xuan
The knowledge-enhanced relation graph module constructs the molecule-property multi-relation graph (MPMRG) to capture the many-to-many relationships between molecules and properties.
1 code implementation • 13 May 2024 • Zeyu Wang, Yuanchun Shi, Yuntao Wang, Yuchen Yao, Kun Yan, YuHan Wang, Lei Ji, Xuhai Xu, Chun Yu
Modern information querying systems are progressively incorporating multimodal inputs like vision and audio.
1 code implementation • 7 Apr 2024 • Jiankai Tang, Xinyi Li, Jiacheng Liu, Xiyuxing Zhang, Zeyu Wang, Yuntao Wang
Remote photoplethysmography (rPPG) emerges as a promising method for non-invasive, convenient measurement of vital signs, utilizing the widespread presence of cameras.
no code implementations • 14 Mar 2024 • Duotun Wang, Hengyu Meng, Zeyu Cai, Zhijing Shao, Qianxi Liu, Lin Wang, Mingming Fan, Xiaohang Zhan, Zeyu Wang
Extensive experiments demonstrate that our framework can generate diverse and expressive head avatars with high-quality meshes that artists can easily manipulate in graphics software, facilitating downstream applications such as efficient asset creation and animation with preserved attributes.
1 code implementation • CVPR 2024 • Zhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang, Xiangru Lin, Yu Zhang, Mingming Fan, Zeyu Wang
We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device.
1 code implementation • CVPR 2024 • Hongxin Li, Zeyu Wang, Xu Yang, Yuran Yang, Shuqi Mei, Zhaoxiang Zhang
Subsequently, a graph attention module encodes the retained STM and the LTM to generate working memory (WM) which contains the scene features essential for efficient navigation.
no code implementations • 26 Feb 2024 • Zeyu Wang, Zhenzhen Weng, Serena Yeung-Levy
Conventional approaches to human mesh recovery predominantly employ a region-based strategy.
no code implementations • 24 Jan 2024 • Vidit Jain, Mukund Rungta, Yuchen Zhuang, Yue Yu, Zeyu Wang, Mu Gao, Jeffrey Skolnick, Chao Zhang
The best-performing models aim to learn a static representation by combining document and hierarchical label information.
1 code implementation • 15 Jan 2024 • Yi Lin, Zeyu Wang, Dong Zhang, Kwang-Ting Cheng, Hao Chen
To alleviate this problem, in this paper, we propose a weakly-supervised nuclei segmentation method that only requires partial point labels of nuclei.
1 code implementation • CVPR 2024 • Zeyu Wang, Xianhang Li, Hongru Zhu, Cihang Xie
For example, by training on DataComp-1B dataset, our AdvXL empowers a vanilla ViT-g model to substantially surpass the previous records of $l_{\infty}$-, $l_{2}$-, and $l_{1}$-robust accuracy by margins of 11. 4%, 14. 2% and 12. 9%, respectively.
1 code implementation • 7 Jan 2024 • Zeyu Wang, Tianyi Jiang, Jinhuan Wang, Qi Xuan
Molecular property prediction refers to the task of labeling molecules with some biochemical properties, playing a pivotal role in the drug discovery and design process.
1 code implementation • 4 Jan 2024 • Parvin Malekzadeh, Konstantinos N. Plataniotis, Zissis Poulos, Zeyu Wang
Distributional Reinforcement Learning (RL) estimates return distribution mainly by learning quantile values via minimizing the quantile Huber loss function, entailing a threshold parameter often selected heuristically or via hyperparameter search, which may not generalize well and can be suboptimal.
no code implementations • 22 Dec 2023 • Kun Yan, Lei Ji, Zeyu Wang, Yuntao Wang, Nan Duan, Shuai Ma
In this paper, we introduce gaze information, feasibly collected by AR or VR devices, as a proxy for human attention to guide VLMs and propose a novel approach, Voila-A, for gaze alignment to enhance the interpretability and effectiveness of these models in real-world applications.
no code implementations • 18 Dec 2023 • Bingyuan Wang, Hengyu Meng, Zeyu Cai, Lanjiong Li, Yue Ma, Qifeng Chen, Zeyu Wang
Visual storytelling often uses nontypical aspect-ratio images like scroll paintings, comic strips, and panoramas to create an expressive and compelling narrative.
no code implementations • 14 Dec 2023 • Frank P. -W. Lo, Jianing Qiu, Zeyu Wang, Junhong Chen, Bo Xiao, Wu Yuan, Stamatia Giannarou, Gary Frost, Benny Lo
Although artificial intelligence (AI)-based solutions have been devised to automate the dietary assessment process, these prior AI methodologies encounter challenges in their ability to generalize across a diverse range of food types, dietary behaviors, and cultural contexts.
4 code implementations • 4 Dec 2023 • Sucheng Ren, Zeyu Wang, Hongru Zhu, Junfei Xiao, Alan Yuille, Cihang Xie
This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict the next pixels for visual representation learning.
1 code implementation • CVPR 2024 • Yipeng Gao, Zeyu Wang, Wei-Shi Zheng, Cihang Xie, Yuyin Zhou
Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i. e., aligning point cloud representation to image and text embedding space individually.
Ranked #1 on Zero-shot 3D classification on Objaverse LVIS (using extra training data)
1 code implementation • 6 Oct 2023 • Peiran Xu, Zeyu Wang, Jieru Mei, Liangqiong Qu, Alan Yuille, Cihang Xie, Yuyin Zhou
Federated learning (FL) is an emerging paradigm in machine learning, where a shared model is collaboratively learned using data from multiple devices to mitigate the risk of data leakage.
no code implementations • 27 Sep 2023 • Zeyu Wang, Mizuho Iwaihara
Since aspect category detection often suffers from limited datasets and data sparsity, the prototypical network with attention mechanisms has been applied for few-shot aspect category detection.
1 code implementation • ICCV 2023 • Zeyu Wang, Dingwen Li, Chenxu Luo, Cihang Xie, Xiaodong Yang
In this work, we propose to boost the representation learning of a multi-camera BEV based student detector by training it to imitate the features of a well-trained LiDAR based teacher detector.
2 code implementations • 27 Jun 2023 • Xianhang Li, Zeyu Wang, Cihang Xie
The recent work CLIPA presents an inverse scaling law for CLIP training -- whereby the larger the image/text encoders used, the shorter the sequence length of image/text tokens that can be applied in training.
no code implementations • 6 Jun 2023 • Jinhuan Wang, Jiafei Shao, Zeyu Wang, Shanqing Yu, Qi Xuan, Xiaoniu Yang
In addition, we also investigate the impact of the second-order subgraph augmentation on mining graph structure interactions, and further, propose a contrastive objective that fuses the first-order and second-order subgraph information.
no code implementations • 25 May 2023 • Zhenzhen Weng, Zeyu Wang, Serena Yeung
Recent advancements in text-to-image generation have enabled significant progress in zero-shot 3D shape generation.
3 code implementations • 16 May 2023 • Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Zhengxin Zhang, Rae Ying Yee Wong, Alan Zhu, Lijie Yang, Xiaoxiang Shi, Chunan Shi, Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, Zhihao Jia
Our evaluation shows that SpecInfer outperforms existing LLM serving systems by 1. 5-2. 8x for distributed LLM inference and by 2. 6-3. 5x for offloading-based LLM inference, while preserving the same generative performance.
1 code implementation • NeurIPS 2023 • Xianhang Li, Zeyu Wang, Cihang Xie
However, its associated training cost is prohibitively high, imposing a significant barrier to its widespread exploration.
no code implementations • 28 Apr 2023 • Zeyu Wang, Yu Wu
In this work, we study a setting where the feedback is provided through users clicking liked and disliked searching results.
no code implementations • 8 Mar 2023 • Xiong Xiao, Zeyu Wang, Quanwang Li
Reliability updating refers to a problem that integrates Bayesian updating technique with structural reliability analysis and cannot be directly solved by structural reliability methods (SRMs) when it involves equality information.
1 code implementation • 25 Jan 2023 • Shaoyuan Xie, Zichao Li, Zeyu Wang, Cihang Xie
In recent years, camera-based 3D object detection has gained widespread attention for its ability to achieve high performance with low computational cost.
no code implementations • 28 Oct 2022 • Zeyu Wang, Haibin Shen, Changyou Men, Quan Sun, Kejie Huang
In this paper, we propose a novel task -- Thermal Infrared Image Inpainting, which aims to reconstruct missing regions of TIR images.
no code implementations • 6 Sep 2022 • Zichao Li, Li Liu, Zeyu Wang, Yuyin Zhou, Cihang Xie
Adversarial training (AT) with samples generated by Fast Gradient Sign Method (FGSM), also known as FGSM-AT, is a computationally simple method to train robust networks.
1 code implementation • CVPR 2023 • Yutong Bai, Zeyu Wang, Junfei Xiao, Chen Wei, Huiyu Wang, Alan Yuille, Yuyin Zhou, Cihang Xie
For example, by distilling the knowledge from an MAE pre-trained ViT-L into a ViT-B, our method achieves 84. 0% ImageNet top-1 accuracy, outperforming the baseline of directly distilling a fine-tuned ViT-L by 1. 2%.
no code implementations • 7 Jul 2022 • Sunayana Rane, Mira L. Nencheva, Zeyu Wang, Casey Lew-Williams, Olga Russakovsky, Thomas L. Griffiths
The performance of the computer vision systems is correlated with human judgments of the concreteness of words, which are in turn a predictor of children's word learning, suggesting that these models are capturing the relationship between words and visual phenomena.
1 code implementation • 30 Jun 2022 • Yi Lin, Zeyu Wang, Kwang-Ting Cheng, Hao Chen
Nuclei Segmentation from histology images is a fundamental task in digital pathology analysis.
no code implementations • 22 Jun 2022 • Zeyu Wang, Huiying Zhao, Peng Ren, Yuxi Zhou, Ming Sheng
Sepsis is a leading cause of death in the ICU.
1 code implementation • 7 Jun 2022 • Zeyu Wang, Yutong Bai, Yuyin Zhou, Cihang Xie
The recent success of Vision Transformers is shaking the long dominance of Convolutional Neural Networks (CNNs) in image recognition for a decade.
1 code implementation • 10 May 2022 • Jay Cao, Jacky Chen, Soroush Farghadani, John Hull, Zissis Poulos, Zeyu Wang, Jun Yuan
We show how D4PG can be used in conjunction with quantile regression to develop a hedging strategy for a trader responsible for derivatives that arrive stochastically and depend on a single underlying asset.
no code implementations • 25 Jan 2022 • Suchin Gururangan, Dallas Card, Sarah K. Dreier, Emily K. Gade, Leroy Z. Wang, Zeyu Wang, Luke Zettlemoyer, Noah A. Smith
Language models increasingly rely on massive web dumps for diverse text data.
1 code implementation • 10 Jan 2022 • Zeyu Wang, Yu Wu, Karthik Narasimhan, Olga Russakovsky
Retrieving target videos based on text descriptions is a task of great practical value and has received increasing attention over the past few years.
no code implementations • 24 Nov 2021 • Zeyu Wang, Chenglin Yao, Jianfeng Ren, Xudong Jiang
In radar activity recognition, 2D signal representations such as spectrogram, cepstrum and cadence velocity diagram are often utilized, while range information is often neglected.
no code implementations • 31 Aug 2021 • Zeyu Wang, Meiqing Wang
In addition, we studied the sample distribution of this loss function by visualization and found that the distribution is related to the neural network structure, which is distinct compared to cross-entropy.
no code implementations • 31 Aug 2021 • Haoran Duan, Fan Wan, Rui Sun, Zeyu Wang, Varun Ojha, Yu Guan, Hubert P. H. Shum, Bingzhang Hu, Yang Long
Our method achieved competitive performance in semi-supervised learning approaches on these crowd counting datasets.
no code implementations • 6 May 2021 • Kelsey Chetnik, Elisa Benedetti, Daniel P. Gomari, Annalise Schweickart, Richa Batra, Mustafa Buyukozkan, Zeyu Wang, Matthias Arnold, Jonas Zierer, Karsten Suhre, Jan Krumsiek
This paper presents maplet, an open-source R package for the creation of highly customizable, fully reproducible statistical pipelines for omics data analysis, with a special focus on metabolomics-based methods.
1 code implementation • 2 Apr 2021 • Zeyu Wang, Sheng Huang, Zhongxin Liu, Meng Yan, Xin Xia, Bei Wang, Dan Yang
Considering the lack of technologies in Plot2API, we present a novel deep multi-task learning approach named Semantic Parsing Guided Neural Network (SPGNN) which translates the Plot2API issue as a multi-label image classification and an image semantic parsing tasks for the solution.
1 code implementation • ECCV 2020 • Zeyu Wang, Berthy Feng, Karthik Narasimhan, Olga Russakovsky
We find that modern captioning systems return higher likelihoods for incorrect distractor sentences compared to ground truth captions, and that evaluation metrics like SPICE can be 'topped' using simple captioning systems relying on object detectors.
no code implementations • 6 Feb 2020 • Chi Zhang, Zeyu Wang, Abdollah Shafieezadeh
The proposed VoI analysis framework is applied for an optimal decision-making problem involving load testing of a truss bridge.
no code implementations • 4 Feb 2020 • Zeyu Wang, Abdollah Shafieezadeh
Reliability analysis for these systems when failure probabilities are small is significantly challenging, requiring a large number of costly simulations.
3 code implementations • CVPR 2020 • Zeyu Wang, Klint Qinami, Ioannis Christos Karakozis, Kyle Genova, Prem Nair, Kenji Hata, Olga Russakovsky
We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation.
Ranked #1 on Out-of-Distribution Generalization on UrbanCars
6 code implementations • 14 Nov 2019 • Yinda Xu, Zeyu Wang, Zuoxin Li, Ye Yuan, Gang Yu
Following these guidelines, we design our Fully Convolutional Siamese tracker++ (SiamFC++) by introducing both classification and target state estimation branch(G1), classification score without ambiguity(G2), tracking without prior knowledge(G3), and estimation quality score(G4).
Ranked #2 on Visual Object Tracking on VOT2017/18 (using extra training data)
1 code implementation • 25 Oct 2019 • Yajing Chen, Fanzi Wu, Zeyu Wang, Yibing Song, Yonggen Ling, Linchao Bao
The displacement map and the coarse model are used to render a final detailed face, which again can be compared with the original input image to serve as a photometric loss for the second stage.
no code implementations • 19 Apr 2019 • Shayan Hassantabar, Zeyu Wang, Niraj K. Jha
To address these challenges, we propose a two-step neural network synthesis methodology, called DR+SCANN, that combines two complementary approaches to design compact and accurate DNNs.
no code implementations • 14 Jan 2019 • Yanchi Su, Zhanshan Li, Haihong Yu, Zeyu Wang
Low rank matrix approximation (LRMA) has drawn increasing attention in recent years, due to its wide range of applications in computer vision and machine learning.
no code implementations • 25 Dec 2018 • Li Chen, Qi Li, Weiye Chen, Zeyu Wang, Haifeng Li
In this regard, we propose the Adversarial Feature Genome (AFG), a novel type of data that contains both the differences and features about classes.
1 code implementation • 31 Jul 2018 • Zeyu Wang, Shiyu Qiu, Qingyang Chen, Alexander Ringlein, Julie Dorsey, Holly Rushmeier
We introduce AniCode, a novel framework for authoring and consuming time-based media.
Graphics