no code implementations • COLING 2022 • Xiangyu Gui, Feng Zhao, Langjunqing Jin, Hai Jin
During the learning process, the semantics of each entity are embedded by a vector or a point in a feature space.
1 code implementation • 21 Nov 2023 • Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, Dahua Lin
In the realm of large multi-modal models (LMMs), efficient modality alignment is crucial yet often constrained by the scarcity of high-quality image-text data.
Ranked #7 on
Visual Question Answering
on MM-Vet
no code implementations • 10 Nov 2023 • Hongyin Zhang, Diyuan Shi, Zifeng Zhuang, Han Zhao, Zhenyu Wei, Feng Zhao, Sibo Gai, Shangke Lyu, Donglin Wang
Developing robotic intelligent systems that can adapt quickly to unseen wild situations is one of the critical challenges in pursuing autonomous robotics.
no code implementations • 12 Oct 2023 • Hu Yu, Li Shen, Jie Huang, Man Zhou, Hongsheng Li, Feng Zhao
Diffusion models have demonstrated compelling generation quality by optimizing the variational lower bound through a simple denoising score matching loss.
1 code implementation • ICCV 2023 • Naishan Zheng, Man Zhou, Yanmeng Dong, Xiangyu Rui, Jie Huang, Chongyi Li, Feng Zhao
In this work, we propose a paradigm for low-light image enhancement that explores the potential of customized learnable priors to improve the transparency of the deep unfolding paradigm.
no code implementations • 23 Aug 2023 • Hu Yu, Jie Huang, Kaiwen Zheng, Man Zhou, Feng Zhao
The latter stage exploits the strong generation ability of DDPM to compensate for the haze-induced huge information loss, by working in conjunction with the physical modelling.
no code implementations • ICCV 2023 • Guangkai Xu, Wei Yin, Hao Chen, Chunhua Shen, Kai Cheng, Feng Zhao
3D scene reconstruction is a long-standing vision task.
no code implementations • 1 Aug 2023 • Jinghao Zhang, Jie Huang, Man Zhou, Chongyi Li, Feng Zhao
Learning to restore multiple image degradations within a single model is quite beneficial for real-world applications.
no code implementations • 3 Jul 2023 • Deyi Ji, Feng Zhao, Hongtao Lu
For the sake of high inference speed and low computation complexity, $\mathcal{T}$ partitions the original UHR image into patches and groups them dynamically, then learns the low-level local details with the lightweight multi-head Wavelet Transformer (WFormer) network.
no code implementations • 3 Jul 2023 • Yindi Yao, Qin Wen, Yanpeng Cui, Feng Zhao, Bozhan Zhao, Yaoping Zeng
As one of the most crucial scenarios of the Internet of Things (IoT), wireless multimedia sensor networks (WMSNs) pay more attention to the information-intensive data (e. g., audio, video, image) for remote environments.
no code implementations • 31 May 2023 • Bohong Wang, Qinglai Guo, Tian Xia, Qiang Li, Di Liu, Feng Zhao
With the development of Internet of Things (IoT) and big data technology, the data value is increasingly explored in multiple practical scenarios, including electricity transactions.
1 code implementation • CVPR 2023 • Deyi Ji, Feng Zhao, Hongtao Lu, Mingyuan Tao, Jieping Ye
With the increasing interest and rapid development of methods for Ultra-High Resolution (UHR) segmentation, a large-scale benchmark covering a wide range of scenes with full fine-grained dense annotations is urgently needed to facilitate the field.
Ranked #1 on
Semantic Segmentation
on INRIA Aerial Image Labeling
(mIOU metric)
no code implementations • 17 Apr 2023 • Mikhail A. Bragin, Farhan Hyder, Bing Yan, Peter B. Luh, Jinye Zhao, Feng Zhao, Dane A. Schiro, Tongxin Zheng
Several CH pricing methods have been presented, and a feasible cost has been used as a quality measure for the CH price.
no code implementations • CVPR 2023 • Shuo Wang, Xinhai Zhao, Hai-Ming Xu, Zehui Chen, Dameng Yu, Jiahao Chang, Zhen Yang, Feng Zhao
Based on the covariate shift assumption, we find that the gap mainly attributes to the feature distribution of BEV, which is determined by the quality of both depth estimation and 2D image's feature representation.
no code implementations • 1 Mar 2023 • Hanting Li, Hongjing Niu, Zhaoqing Zhu, Feng Zhao
Facial expression recognition (FER) is an essential task for understanding human behaviors.
Dynamic Facial Expression Recognition
Facial Expression Recognition
+1
1 code implementation • 16 Feb 2023 • Jian Wen, Xiaobin Cheng, Peifeng Ji, Jun Yang, Feng Zhao
Both the pulse position and switching frequency are randomized in the second method.
1 code implementation • ICCV 2023 • Zehui Chen, Zhenyu Li, Shuo Wang, Dengpan Fu, Feng Zhao
To this end, we propose NoiseDet, a simple yet effective framework for semi-supervised 3D object detection.
no code implementations • CVPR 2023 • Jinghao Zhang, Jie Huang, Mingde Yao, Zizheng Yang, Hu Yu, Man Zhou, Feng Zhao
Learning to leverage the relationship among diverse image restoration tasks is quite beneficial for unraveling the intrinsic ingredients behind the degradation.
no code implementations • CVPR 2023 • Jie Huang, Feng Zhao, Man Zhou, Jie Xiao, Naishan Zheng, Kaiwen Zheng, Zhiwei Xiong
Exposure correction task aims to correct the underexposure and its adverse overexposure images to the normal exposure in a single network.
no code implementations • CVPR 2023 • Zizheng Yang, Jie Huang, Jiahao Chang, Man Zhou, Hu Yu, Jinghao Zhang, Feng Zhao
Deep image recognition models suffer a significant performance drop when applied to low-quality images since they are trained on high-quality images.
no code implementations • ICCV 2023 • Qi Zhu, Man Zhou, Naishan Zheng, Chongyi Li, Jie Huang, Feng Zhao
Video deblurring aims to restore the latent video frames from their blurred counterparts.
no code implementations • ICCV 2023 • Jiahao Chang, Shuo Wang, HaiMing Xu, Zehui Chen, Chenhongyi Yang, Feng Zhao
Next, we propose a target-aware feature distillation to help the student model learn from the object-centric features of the teacher model.
1 code implementation • 17 Nov 2022 • Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, Feng Zhao
Instead of directly training a depth prediction network, we unify the image and LiDAR features in the Bird-Eye-View (BEV) space and adaptively transfer knowledge across non-homogenous representations in a teacher-student paradigm.
Ranked #12 on
3D Object Detection
on nuScenes Camera Only
no code implementations • 15 Oct 2022 • Keyu Yan, Man Zhou, Jie Huang, Feng Zhao, Chengjun Xie, Chongyi Li, Danfeng Hong
Panchromatic (PAN) and multi-spectral (MS) image fusion, named Pan-sharpening, refers to super-resolve the low-resolution (LR) multi-spectral (MS) images in the spatial domain to generate the expected high-resolution (HR) MS images, conditioning on the corresponding high-resolution PAN images.
1 code implementation • 11 Oct 2022 • Man Zhou, Hu Yu, Jie Huang, Feng Zhao, Jinwei Gu, Chen Change Loy, Deyu Meng, Chongyi Li
Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling.
1 code implementation • 29 Sep 2022 • Hongjing Niu, Hanting Li, Feng Zhao, Bin Li
The proposed scheme generates diverse prompts from a domain bank that contains many more diverse domains than existing DG datasets.
no code implementations • 13 Sep 2022 • Feng Zhao, Ziqi Zhang, Donglin Wang
This is the first study that we are aware of that looks into dynamic KSG for skill retrieval and learning.
no code implementations • 6 Sep 2022 • Qianhao Yu, Naishan Zheng, Jie Huang, Feng Zhao
The key to shadow removal is recovering the contents of the shadow regions with the guidance of the non-shadow regions.
1 code implementation • 19 Aug 2022 • Hanting Li, Hongjing Niu, Zhaoqing Zhu, Feng Zhao
One of the main reasons is that video sequences often contain frames with different expression intensities, especially for the facial expressions in the real-world scenarios, while the images in SFER frequently present uniform and high expression intensities.
Ranked #3 on
Dynamic Facial Expression Recognition
on DFEW
Dynamic Facial Expression Recognition
Facial Expression Recognition
+1
1 code implementation • 21 Jul 2022 • Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, Feng Zhao
Recently, AutoAlign presents a learnable paradigm in combining these two modalities for 3D object detection.
no code implementations • 15 Jul 2022 • Naishan Zheng, Jie Huang, Qi Zhu, Man Zhou, Feng Zhao, Zheng-Jun Zha
Low-light image enhancement is an inherently subjective process whose targets vary with the user's aesthetic.
no code implementations • 14 Jul 2022 • Hu Yu, Jie Huang, Yajing Liu, Qi Zhu, Man Zhou, Feng Zhao
Although certain Domain Adaptation (DA) dehazing methods have been presented, they inevitably require access to the source dataset to reduce the gap between the source synthetic and target real domains.
no code implementations • 10 Jun 2022 • Hanting Li, Mingzhe Sui, Zhaoqing Zhu, Feng Zhao
Dynamic facial expression recognition (DFER) in the wild is an extremely challenging task, due to a large number of noisy frames in the video sequences.
Ranked #4 on
Dynamic Facial Expression Recognition
on DFEW
Dynamic Facial Expression Recognition
Facial Expression Recognition
+1
no code implementations • 6 Jun 2022 • Qianpeng Xie, Yihang Du, He Wang, Xiaoyi Pan, Feng Zhao
Firstly, a 5-D tensor model was constructed by using the multi-dimensional space-time characteristics of the received data.
no code implementations • 4 Jun 2022 • Qianpeng Xie, He Wang, Yihang Du, Xiaoyi Pan, Feng Zhao
Firstly, the outer part PARAFAC algorithm was carried out to estimate the receive spatial response matrix and its first way factor matrix.
no code implementations • 24 May 2022 • Mingzhe Sui, Hanting Li, Zhaoqing Zhu, Feng Zhao
2D+3D facial expression recognition (FER) can effectively cope with illumination changes and pose variations by simultaneously merging 2D texture and more robust 3D depth information.
3D Facial Expression Recognition
Facial Expression Recognition
no code implementations • 25 Apr 2022 • Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, Feng Zhao
3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding.
no code implementations • 3 Feb 2022 • Guangkai Xu, Wei Yin, Hao Chen, Chunhua Shen, Kai Cheng, Feng Wu, Feng Zhao
However, in some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency.
no code implementations • 17 Jan 2022 • Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinghong Jiang, Feng Zhao, Bolei Zhou, Hang Zhao
This map enables our model to automate the alignment of non-homogenous features in a dynamic and data-driven manner.
1 code implementation • 14 Jan 2022 • Hanting Li, Mingzhe Sui, Zhaoqing Zhu, Feng Zhao
By adding the position embeddings of the face generated by PC module at the end of the two branches, the PC module can help to add position information to facial muscle motion pattern features for the MER.
no code implementations • CVPR 2022 • Jie Huang, Yajing Liu, Xueyang Fu, Man Zhou, Yang Wang, Feng Zhao, Zhiwei Xiong
However, the procedures of correcting underexposure and overexposure to normal exposures are much different from each other, leading to large discrepancies for the network in correcting multiple exposures, thus resulting in poor performance.
no code implementations • CVPR 2022 • Man Zhou, Keyu Yan, Jie Huang, Zihe Yang, Xueyang Fu, Feng Zhao
Despite the remarkable progress, existing state-of-the-art Pan-sharpening methods don't explicitly enforce the complementary information learning between two modalities of PAN and MS images.
2 code implementations • CVPR 2022 • Yurui Zhu, Jie Huang, Xueyang Fu, Feng Zhao, Qibin Sun, Zheng-Jun Zha
Shadow removal, which aims to restore the background in the shadow regions, is challenging due to the highly ill-posed nature.
no code implementations • CVPR 2022 • Zizheng Yang, Xin Jin, Kecheng Zheng, Feng Zhao
During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.
1 code implementation • 1 Dec 2021 • Zizheng Yang, Xin Jin, Kecheng Zheng, Feng Zhao
During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.
no code implementations • Expert Systems with Applications 2021 • Feng Zhao, Yating Gao, Xinning Li, Zhiyong An, Shiyu Ge, Caiming Zhang
In this paper, for accurately describing the similarity between a pair of time series, a novel similarity measurement is proposed, which is named as the dynamic multi-perspective personalized similarity measurement (DMPSM).
no code implementations • NeurIPS Workshop DLDE 2021 • Feng Zhao, Xiang Chen, Jun Wang, Zuoqiang Shi, Shao-Lun Huang
Traditionally, we provide technical parameters for ODE solvers, such as the order, the stepsize and the local error threshold.
no code implementations • 20 Sep 2021 • Hanting Li, Mingzhe Sui, Zhaoqing Zhu, Feng Zhao
To the best of our knowledge, this is the first work to introduce vision transformer into multimodal 2D+3D FER.
3D Facial Expression Recognition
Facial Expression Recognition
2 code implementations • 7 Jul 2021 • Zehui Chen, Chenhongyi Yang, Qiaofei Li, Feng Zhao, Zheng-Jun Zha, Feng Wu
Extensive experiments on MS COCO benchmark show that our approach can lead to 2. 0 mAP, 2. 4 mAP and 2. 2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead.
no code implementations • 8 Jun 2021 • Hanting Li, Mingzhe Sui, Feng Zhao, ZhengJun Zha, Feng Wu
Facial Expression Recognition (FER) in the wild is an extremely challenging task in computer vision due to variant backgrounds, low-quality facial images, and the subjectiveness of annotators.
Facial Expression Recognition
Facial Expression Recognition (FER)
1 code implementation • 10 Sep 2020 • Zehui Chen, Qiaofei Li, Feng Zhao
This technical report introduces our solutions of Team 'FineGrainedSeg' for Instance Segmentation track in 3D AI Challenge 2020.
2 code implementations • CVPR 2020 • Haozhe Qi, Chen Feng, Zhiguo Cao, Feng Zhao, Yang Xiao
Specifically, we first sample seeds from the point clouds in template and search area respectively.
no code implementations • 6 Nov 2013 • Feng Zhao
The thesis is aimed to solve the template-free protein folding problem by tackling two important components: efficient sampling in vast conformation space, and design of knowledge-based potentials with high accuracy.