no code implementations • ECCV 2020 • Fan Wang, Huidong Liu, Dimitris Samaras, Chao Chen
We show in experiments that our method generates synthetic images with realistic topology.
no code implementations • ECCV 2020 • Yi Huang, Fan Wang, Adams Wai-Kin Kong, Kwok-Yan Lam
The experiments show that the universal patches are able to mislead the detector with greater probabilities.
no code implementations • EMNLP (NLP4ConvAI) 2021 • Xinxian Huang, Huang He, Siqi Bao, Fan Wang, Hua Wu, Haifeng Wang
Large-scale conversation models are turning to leveraging external knowledge to improve the factual accuracy in response generation.
no code implementations • 23 Nov 2023 • Jing Wang, Yuang Liu, Qiang Zhou, Fan Wang
Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set.
no code implementations • 20 Nov 2023 • Haiyang Ying, Yixuan Yin, Jinzhi Zhang, Fan Wang, Tao Yu, Ruqi Huang, Lu Fang
Towards holistic understanding of 3D scenes, a general 3D segmentation method is needed that can segment diverse objects without restrictions on object quantity or categories, while also reflecting the inherent hierarchical structure.
no code implementations • 21 Oct 2023 • Lihang Liu, Donglong He, Xianbin Ye, Jingbo Zhou, Shanzhuo Zhang, Xiaonan Zhang, Jun Li, Hua Chai, Fan Wang, Jingzhou He, Liang Zheng, Yonghui Li, Xiaomin Fang
In this work, we show that by pre-training a geometry-aware SE(3)-Equivariant neural network on a large-scale docking conformation generated by traditional physics-based docking tools and then fine-tuning with a limited set of experimentally validated receptor-ligand complexes, we can achieve outstanding performance.
no code implementations • 12 Oct 2023 • Zijie Wu, Chaohui Yu, Zhen Zhu, Fan Wang, Xiang Bai
To utilize the abundant visual priors in the off-the-shelf T2I models, a series of methods try to invert an image to proper embedding that aligns with the semantic space of the T2I model.
2 code implementations • 15 Sep 2023 • Henry Hengyuan Zhao, Pichao Wang, Yuyang Zhao, Hao Luo, Fan Wang, Mike Zheng Shou
Recently, many parameter-efficient fine-tuning (PEFT) methods have been proposed, and their experiments demonstrate that tuning only 1% of extra parameters could surpass full fine-tuning in low-data resource scenarios.
no code implementations • 15 Sep 2023 • Xiaonan Lu, Jianlong Yuan, Ruigang Niu, Yuan Hu, Fan Wang
Therefore, they cannot be directly applied to cope with image change understanding (ICU), which requires models to capture actual changes between multiple images and describe them in language.
no code implementations • 13 Sep 2023 • Ze Zheng, Baolei Liu, Jiaqi Song, Lei Ding, Xiaolan Zhong, David Mcgloin, Fan Wang
Lensless imagers based on diffusers or encoding masks enable high-dimensional imaging from a single shot measurement and have been applied in various applications.
no code implementations • 11 Sep 2023 • Yabing Wang, Shuhui Wang, Hao Luo, Jianfeng Dong, Fan Wang, Meng Han, Xun Wang, Meng Wang
Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR.
no code implementations • 10 Sep 2023 • Zelin Zang, Hao Luo, Kai Wang, Panpan Zhang, Fan Wang, Stan. Z Li, Yang You
When applied to biological data, DiffAug improves performance by up to 10. 1%, with an average improvement of 5. 8%.
no code implementations • 7 Sep 2023 • Zehua Ren, Yongheng Sun, Miaomiao Wang, Yuying Feng, Xianjun Li, Chao Jin, Jian Yang, Chunfeng Lian, Fan Wang
In this paper, we propose to leverage the idea of counterfactual reasoning coupled with the auxiliary task of brain tissue segmentation to learn fine-grained positional and morphological representations of PWMLs for accurate localization and segmentation.
no code implementations • 7 Sep 2023 • Shuting He, Weihua Chen, Kai Wang, Hao Luo, Fan Wang, Wei Jiang, Henghui Ding
Then, to measure the importance of each generated region, we introduce a Region Assessment Module (RAM) that assigns confidence scores to different regions and reduces the negative impact of the occlusion regions by lower scores.
1 code implementation • 7 Sep 2023 • Hongzhi Qi, Qing Zhao, Changwei Song, Wei Zhai, Dan Luo, Shuo Liu, Yi Jing Yu, Fan Wang, Huijing Zou, Bing Xiang Yang, Jianqiang Li, Guanghui Fu
In response, we introduce two novel annotated datasets from Chinese social media, focused on cognitive distortions and suicidal risk classification.
1 code implementation • 29 Aug 2023 • Guanghui Fu, Qing Zhao, Jianqiang Li, Dan Luo, Changwei Song, Wei Zhai, Shuo Liu, Fan Wang, Yan Wang, Lijuan Cheng, Juan Zhang, Bing Xiang Yang
In the contemporary landscape of social media, an alarming number of users express negative emotions, some of which manifest as strong suicidal intentions.
no code implementations • 27 Aug 2023 • Chen Shen, Jun Zhang, Xinggong Liang, Zeyi Hao, Kehan Li, Fan Wang, Zhenyuan Wang, Chunfeng Lian
Forensic pathology is critical in analyzing death manner and time from the microscopic aspect to assist in the establishment of reliable factual bases for criminal investigation.
no code implementations • 15 Aug 2023 • Zizhang Wu, Yuanzhu Gan, Tianhao Xu, Fan Wang
To address this issue, we propose a Graph-Segmenter, including a Graph Transformer and a Boundary-aware Attention module, which is an effective network for simultaneously modeling the more profound relation between windows in a global view and various pixels inside each window as a local one, and for substantial low-cost boundary adjustment.
no code implementations • 14 Aug 2023 • Chaohui Yu, Qiang Zhou, Zhibin Wang, Fan Wang
Second, we propose an align-guided contrastive loss to refine the alignment of vision and text embeddings.
no code implementations • 13 Aug 2023 • Yongheng Sun, Fan Wang, Jun Shu, Haifeng Wang, Li Wang. Deyu Meng, Chunfeng Lian
However, segmentation on longitudinal data is challenging due to dynamic brain changes across the lifespan.
no code implementations • ICCV 2023 • Shuning Chang, Pichao Wang, Hao Luo, Fan Wang, Mike Zheng Shou
Therefore, we propose the path pruning and EnsembleScale skills for improvement, which cut out the underperforming paths and re-weight the ensemble components, respectively, to optimize the path combination and make the short paths focus on providing high-quality representation for subsequent paths.
no code implementations • 3 Aug 2023 • Yuang Liu, Qiang Zhou, Jing Wang, Fan Wang, Jun Wang, Wei zhang
Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe.
1 code implementation • 3 Aug 2023 • Qiang Zhou, Chaohui Yu, Shaofeng Zhang, Sitong Wu, Zhibing Wang, Fan Wang
To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning.
no code implementations • 27 Jul 2023 • Jingliang Li, Qiang Zhou, Chaohui Yu, Zhengda Lu, Jun Xiao, Zhibin Wang, Fan Wang
To make the constructed volumes as close as possible to the surfaces of objects in the scene and the rendered depth more accurate, we propose to perform depth prediction and radiance field reconstruction simultaneously.
no code implementations • 26 Jul 2023 • Chaohui Yu, Qiang Zhou, Jingliang Li, Zhe Zhang, Zhibin Wang, Fan Wang
To better utilize the sparse 3D points, we propose an efficient point cloud guidance loss to adaptively drive the NeRF's geometry to align with the shape of the sparse 3D points.
1 code implementation • 15 Jun 2023 • Chong Liu, Yuqi Zhang, Hongsong Wang, Weihua Chen, Fan Wang, Yan Huang, Yi-Dong Shen, Liang Wang
Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words.
1 code implementation • 15 Jun 2023 • Yuqi Zhang, Qi Qian, Hongsong Wang, Chong Liu, Weihua Chen, Fan Wang
In particular, the plain GCR is extended for cross-camera retrieval and an improved feature propagation formulation is presented to leverage affinity relationships across different cameras.
no code implementations • 5 Jun 2023 • Lei Chen, Fei Du, Yuan Hu, Fan Wang, Zhibin Wang
Recurrent predictions for future atmospheric fields are firstly performed at 1. 40625-degree resolution, and then a diffusion-based super-resolution model is leveraged to recover the high spatial resolution and finer-scale atmospheric details.
1 code implementation • CVPRW 2023 • Marcos V. Conde, Manuel Kolmet, Tim Seizinger, Tom E. Bishop, Radu Timofte, Xiangyu Kong, Dafeng Zhang, Jinlong Wu, Fan Wang, Juewen Peng, Zhiyu Pan, Chengxin Liu, Xianrui Luo, Huiqiang Sun, Liao Shen, Zhiguo Cao, Ke Xian, Chaowei Liu, Zigeng Chen, Xingyi Yang, Songhua Liu, Yongcheng Jing, Michael Bi Mi, Xinchao Wang, Zhihao Yang, Wenyi Lian, Siyuan Lai, Haichuan Zhang, Trung Hoang, Amirsaeed Yazdani, Vishal Monga, Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön, Yuxuan Zhao, Baoliang Chen, Yiqing Xu, JiXiang Niu
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge.
1 code implementation • 17 May 2023 • Wenfang Sun, Yingjun Du, XianTong Zhen, Fan Wang, Ling Wang, Cees G. M. Snoek
To account for the uncertainty caused by the limited training tasks, we propose a variational MetaModulation where the modulation parameters are treated as latent variables.
1 code implementation • CVPR 2023 • Jiefeng Li, Siyuan Bian, Qi Liu, Jiasheng Tang, Fan Wang, Cewu Lu
In this work, we present NIKI (Neural Inverse Kinematics with Invertible Neural Network), which models bi-directional errors to improve the robustness to occlusions and obtain pixel-aligned accuracy.
Ranked #1 on
3D Human Pose Estimation
on AGORA
1 code implementation • 26 Apr 2023 • Fangjian Lin, Jianlong Yuan, Sitong Wu, Fan Wang, Zhibin Wang
Interestingly, the ranking of these spatial token mixers also changes under our UniNeXt, suggesting that an excellent spatial token mixer may be stifled due to a suboptimal general architecture, which further shows the importance of the study on the general architecture of vision backbone.
no code implementations • 1 Apr 2023 • Shuning Chang, Pichao Wang, Fan Wang, Jiashi Feng, Mike Zheng Show
Specifically, one branch focuses on detection representation for actor detection, and the other one for action recognition.
4 code implementations • CVPR 2023 • Weihua Chen, Xianzhe Xu, Jian Jia, Hao Luo, Yaohua Wang, Fan Wang, Rong Jin, Xiuyu Sun
Unlike the existing self-supervised learning methods, prior knowledge from human images is utilized in SOLIDER to build pseudo semantic labels and import more semantic information into the learned representation.
Ranked #1 on
Person Search
on PRW
no code implementations • 29 Mar 2023 • Chaitanya Mitash, Fan Wang, Shiyang Lu, Vikedo Terhuja, Tyler Garaas, Felipe Polido, Manikantan Nambi
This paper introduces Amazon Robotic Manipulation Benchmark (ARMBench), a large-scale, object-centric benchmark dataset for robotic manipulation in the context of a warehouse.
2 code implementations • 22 Mar 2023 • Hansheng Chen, Wei Tian, Pichao Wang, Fan Wang, Lu Xiong, Hao Li
In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose with differentiable probability density on the SE(3) manifold.
Ranked #3 on
6D Pose Estimation using RGB
on LineMOD
1 code implementation • CVPR 2023 • Shuning Chang, Pichao Wang, Ming Lin, Fan Wang, David Junhao Zhang, Rong Jin, Mike Zheng Shou
In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks.
no code implementations • 14 Mar 2023 • Hengyuan Zhao, Hao Luo, Yuyang Zhao, Pichao Wang, Fan Wang, Mike Zheng Shou
In view of the practicality of PETL, previous works focus on tuning a small set of parameters for each downstream task in an end-to-end manner while rarely considering the task distribution shift issue between the pre-training task and the downstream task.
1 code implementation • 6 Mar 2023 • Fan Wang, Keli Wang, Boyu Yao
In this work, we propose a novel unsupervised anomaly detection method for time series data.
no code implementations • 1 Mar 2023 • Qiang Zhou, Chaohui Yu, Zhibin Wang, Fan Wang
In this paper, we propose an end-to-end framework for oriented object detection, which simplifies the model pipeline and obtains superior performance.
no code implementations • CVPR 2023 • Fan Wang, Adams Wai-Kin Kong
Model attribution is a critical component of deep neural networks (DNNs) for its interpretability to complex models.
no code implementations • CVPR 2023 • Chaohui Yu, Qiang Zhou, Jingliang Li, Jianlong Yuan, Zhibin Wang, Fan Wang
In this work, we propose a novel and data-efficient framework for WILSS, named FMWISS.
no code implementations • 27 Feb 2023 • Qiang Zhou, Yuang Liu, Chaohui Yu, Jingliang Li, Zhibin Wang, Fan Wang
Instead of relabeling each dataset with the unified taxonomy, a category-guided decoding module is designed to dynamically guide predictions to each datasets taxonomy.
no code implementations • 14 Feb 2023 • Dajing Wang, Baolei Liu, Jiaqi Song, Yao Wang, Xuchen Shan, Fan Wang
In this paper, we present a dual-mode adaptive singular value decomposition ghost imaging (A-SVD GI), which can be easily switched between the modes of imaging and edge detection.
1 code implementation • 11 Jan 2023 • Bo Dong, Pichao Wang, Fan Wang
On the ADE20K dataset, our model achieves 41. 8 mIoU and 4. 6 GFLOPs, which is 4. 4 mIoU higher than Segformer, with 45% less GFLOPs.
no code implementations • 1 Jan 2023 • Chenyu Xue, Fan Wang, Yuanzhuo Zhu, Hui Li, Deyu Meng, Dinggang Shen, Chunfeng Lian
Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and (even more importantly) explainable predictions.
1 code implementation • CVPR 2023 • Fei Du, Jianlong Yuan, Zhibin Wang, Fan Wang
To this end, we propose an efficient method to correct the mask with a lightweight mask correction network.
no code implementations • ICCV 2023 • Yongheng Sun, Fan Wang, Jun Shu, Haifeng Wang, Li Wang, Deyu Meng, Chunfeng Lian
However, segmentation on longitudinal data is challenging due to dynamic brain changes across the lifespan.
no code implementations • CVPR 2023 • Fan Wang, Zhongyi Han, Zhiyan Zhang, Rundong He, Yilong Yin
Source free domain adaptation (SFDA) aims to transfer a trained source model to the unlabeled target domain without accessing the source data.
1 code implementation • 19 Dec 2022 • Mingzhu Cai, Siqi Bao, Xin Tian, Huang He, Fan Wang, Hua Wu
In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv.
no code implementations • 13 Dec 2022 • Zizhang Wu, Man Wang, Weiwei Sun, Yuchen Li, Tianhao Xu, Fan Wang, Keke Huang
Channel and spatial attention mechanism has proven to provide an evident performance boost of deep convolution neural networks (CNNs).
no code implementations • 8 Dec 2022 • Zizhang Wu, Yuanzhu Gan, Xianzhi Li, Yunzhe Wu, Xiaoquan Wang, Tianhao Xu, Fan Wang
Most existing networks based on public datasets may generalize suboptimal results on these valet parking scenes, also affected by the fisheye distortion.
no code implementations • 8 Dec 2022 • Zizhang Wu, Tianhao Xu, Fan Wang, Xiaoquan Wang, Jing Song
Vehicle re-identification (Re-ID) is a critical component of the autonomous driving perception system, and research in this area has accelerated in recent years.
1 code implementation • 16 Nov 2022 • Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, Fan Wang
Although improving motion recognition to some extent, these methods still face sub-optimal situations in the following aspects: (i) Data augmentation, i. e., the scale of the RGB-D datasets is still limited, and few efforts have been made to explore novel data augmentation strategies for videos; (ii) Optimization mechanism, i. e., the tightly space-time-entangled network structure brings more challenges to spatiotemporal information modeling; And (iii) cross-modal knowledge fusion, i. e., the high similarity between multimodal representations caused to insufficient late fusion.
Ranked #2 on
Action Recognition
on NTU RGB+D
no code implementations • 2 Nov 2022 • Siqi Bao, Huang He, Jun Xu, Hua Lu, Fan Wang, Hua Wu, Han Zhou, Wenquan Wu, Zheng-Yu Niu, Haifeng Wang
Recently, the practical deployment of open-domain dialogue systems has been plagued by the knowledge issue of information deficiency and factual inaccuracy.
no code implementations • 1 Nov 2022 • Jianwu Fang, Fan Wang, Peining Shen, Zhedong Zheng, Jianru Xue, Tat-Seng Chua
In the driving scene, the road participants usually show frequent interaction and intention understanding with the surrounding.
1 code implementation • NIPS 2022 • Zhenyu Wang, Hao Luo, Pichao Wang, Feng Ding, Fan Wang, Hao Li
Although Vision transformers (ViTs) have recently dominated many vision tasks, deploying ViT models on resource-limited devices remains a challenging problem.
1 code implementation • 14 Oct 2022 • Xin Tian, Yingzhan Lin, Mengfei Song, Siqi Bao, Fan Wang, Huang He, Shuqi Sun, Hua Wu
Firstly, as the query is in the form of natural language and not confined to the schema of the knowledge base, the issue of domain adaption is alleviated remarkably in Q-TOD.
no code implementations • 29 Sep 2022 • Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, Fan Wang
To achieve these two purposes, we propose a novel data-centric ViT training framework to dynamically measure the ``difficulty'' of training samples and generate ``effective'' samples for models at different training stages.
1 code implementation • 30 Aug 2022 • Jianlong Yuan, Qian Qi, Fei Du, Zhibin Wang, Fan Wang, Yifan Liu
Inspired by the recent progress on semantic directions on feature-space, we propose to include augmentations in feature space for efficient distillation.
1 code implementation • 30 Aug 2022 • Hua Lu, Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang
Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses when interacting with real users.
1 code implementation • 11 Aug 2022 • Lihang Liu, Donglong He, Xiaomin Fang, Shanzhuo Zhang, Fan Wang, Jingzhou He, Hua Wu
Full-range many-body interactions between electrons have been proven effective in obtaining an accurate solution of the Schr"odinger equation by classical computational chemistry methods, although modeling such interactions consumes an expensive computational cost.
1 code implementation • 28 Jul 2022 • Xiaomin Fang, Fan Wang, Lihang Liu, Jingzhou He, Dayong Lin, Yingfei Xiang, Xiaonan Zhang, Hua Wu, Hui Li, Le Song
Our proposed method, HelixFold-Single, first pre-trains a large-scale protein language model (PLM) with thousands of millions of primary sequences utilizing the self-supervised learning paradigm, which will be used as an alternative to MSAs for learning the co-evolution information.
no code implementations • 12 Jul 2022 • Xiao Pan, Hao Luo, Weihua Chen, Fan Wang, Hao Li, Wei Jiang, Jianming Zhang, Jianyang Gu, Peike Li
To address this issue, we propose the Ranking-based Backward Compatible Learning (RBCL), which directly optimizes the ranking metric between new features and old features.
1 code implementation • 12 Jul 2022 • Guoxia Wang, Xiaomin Fang, Zhihua Wu, Yiqun Liu, Yang Xue, Yingfei Xiang, dianhai yu, Fan Wang, Yanjun Ma
Due to the complex model architecture and large memory consumption, it requires lots of computational resources and time to implement the training and inference of AlphaFold2 from scratch.
no code implementations • 10 Jul 2022 • Jie Gao, Jing Hu, Wanqing Sun, Yili Shen, Xiaonan Zhang, Xiaomin Fang, Fan Wang, Guodong Zhao
Our study highlights the prediction power of TCR and its potential value for cancer drug repurpose and precision oncology treatment.
no code implementations • 28 Jun 2022 • Han Zhou, Xinchao Xu, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Siqi Bao, Fan Wang, Haifeng Wang
Making chatbots world aware in a conversation like a human is a crucial challenge, where the world may contain dynamic knowledge and spatiotemporal state.
no code implementations • 24 May 2022 • Fan Wang, Weiming Liu, Chaochao Chen, Mengying Zhu, Xiaolin Zheng
The ever-increasing data scale of user-item interactions makes it challenging for an effective and efficient recommender system.
no code implementations • 22 May 2022 • Fan Wang, Zhongyi Han, Zhiyan Zhang, Yilong Yin
We then propose minimum happy points learning (MHPL) to actively explore and exploit MH points.
no code implementations • 17 May 2022 • Shanzhuo Zhang, Zhiyuan Yan, Yueyang Huang, Lihang Liu, Donglong He, Wei Wang, Xiaomin Fang, Xiaonan Zhang, Fan Wang, Hua Wu, Haifeng Wang
Additionally, the pre-trained model provided by H-ADMET can be fine-tuned to generate new and customised ADMET endpoints, meeting various demands of drug research and development requirements.
no code implementations • 15 May 2022 • Fan Wang, Adams Wai-Kin Kong
In this paper, we first show that the expected Kendall's rank correlation is positively correlated to cosine similarity and then indicate that the direction of attribution is the key to attribution robustness.
no code implementations • 26 Apr 2022 • Fan Wang
I develop and estimate a dynamic equilibrium model of risky entrepreneurs' borrowing and savings decisions incorporating both formal and local-informal credit markets.
no code implementations • 8 Apr 2022 • Vegard M. Nygaard, Bent E. Sørensen, Fan Wang
A planner allocates discrete transfers of size $D_g$ to $N$ heterogeneous groups labeled $g$ and has CES preferences over the resulting outcomes, $H_g(D_g)$.
1 code implementation • 6 Apr 2022 • Can Chen, Jingbo Zhou, Fan Wang, Xue Liu, Dejing Dou
Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning.
no code implementations • 6 Apr 2022 • Esteban Puentes, Fan Wang, Jere R. Behrman, Flávio Cunha, John Hoddinott, John A. Maluccio, Linda S. Adair, Judith B. Borja, Reynaldo Martorell, Aryeh D. Stein
We examine effects of protein and energy intakes on height and weight growth for children between 6 and 24 months old in Guatemala and the Philippines.
no code implementations • 5 Apr 2022 • Fan Wang, Esteban Puentes, Jere R. Behrman, Flávio Cunha
We explore the exogenous variation in reference height produced by a protein-supplementation experiment in Guatemala to estimate our model's parameters.
no code implementations • 4 Apr 2022 • Emily Hannum, Fan Wang
Much more than Han youth, ethnic minority youth were negatively affected by closure, in terms of its impact on both educational attainment and written Mandarin facility.
no code implementations • 1 Apr 2022 • Xiaoying Liu, Jere R. Behrman, Emily Hannum, Fan Wang, Qingguo Zhao
This paper investigates whether associations between birth weight and prenatal ambient environmental conditions--pollution and extreme temperatures--differ by 1) maternal education; 2) children's innate health; and 3) interactions between these two.
no code implementations • 31 Mar 2022 • Emily Hannum, Xiaoying Liu, Fan Wang
We estimate the impact of educational infrastructure consolidation on educational attainment using the case of China's rural primary school closure policies in the early 2000s.
1 code implementation • CVPR 2022 • Hansheng Chen, Pichao Wang, Fan Wang, Wei Tian, Lu Xiong, Hao Li
The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution.
Ranked #5 on
6D Pose Estimation using RGB
on LineMOD
no code implementations • 18 Mar 2022 • Fan Wang, Tomoyoshi Shimobaba, Takashi Kakue, Tomoyoshi Ito
A controllable energy method, which considers the undersampling issue of the transfer function and valid spectral energy of a source signal, is proposed to implement angular spectrum diffraction calculation in near and far fields.
no code implementations • 12 Mar 2022 • Chunyu Li, Jiajia Ding, Xing Hu, Fan Wang
To fit bag sampling well, after query and document are encoded, the global features of each group are extracted by convolutional layer and max-pooling to improve the model's resistance to the impact of labeling noise, finally, calculate the LCE group-wise loss.
no code implementations • 28 Jan 2022 • Zizhang Wu, Jason Wang, Tianhao Xu, Fan Wang
The owner-member relationship between wheels and vehicles contributes significantly to the 3D perception of vehicles, especially in embedded environments.
no code implementations • 21 Jan 2022 • Pichao Wang, Fan Wang, Hao Li
During the KD process, the TCL loss transfers the local structure, exploits the higher order information, and mitigates the misalignment of the heterogeneous output of teacher and student networks.
no code implementations • 19 Jan 2022 • Jinfei Wang, Yi Ma, Na Yi, Rahim Tafazolli, Fan Wang
Finally, it is shown that the network-ELAA can offer significant coverage extension (50% or more in most of cases) when comparing with the single-AP scenario.
no code implementations • 16 Jan 2022 • Fan Wang, Chaofan Zhang, Fulin Tang, Hongkui Jiang, Yihong Wu, Yong liu
In this paper, we present a novel lightweight object-level mapping and localization method with high accuracy and robustness.
no code implementations • CVPR 2022 • Fan Wang, Zhongyi Han, Yongshun Gong, Yilong Yin
In contrast, we provide a fascinating insight: rather than attempting to learn domain-invariant representations, it is better to explore the domain-invariant parameters of the source model.
1 code implementation • CVPR 2022 • Gang Yang, Man Zhou, Keyu Yan, Aiping Liu, Xueyang Fu, Fan Wang
Pan-sharpening aims to obtain high-resolution multispectral (MS) images for remote sensing systems and deep learning-based methods have achieved remarkable success.
1 code implementation • 28 Dec 2021 • Kai Chen, Weihua Chen, Tao He, Rong Du, Fan Wang, Xiuyu Sun, Yuchen Guo, Guiguang Ding
In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the target domain.
no code implementations • 23 Dec 2021 • Xin Tian, Xinxian Huang, Dongfeng He, Yingzhan Lin, Siqi Bao, Huang He, Liankai Huang, Qiang Ju, Xiyuan Zhang, Jian Xie, Shuqi Sun, Fan Wang, Hua Wu, Haifeng Wang
Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations.
1 code implementation • 23 Dec 2021 • Jingkai Zhou, Pichao Wang, Fan Wang, Qiong Liu, Hao Li, Rong Jin
Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning.
Ranked #45 on
Semantic Segmentation
on ADE20K val
1 code implementation • CVPR 2022 • Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, Fan Wang, Du Zhang, Zhen Lei, Hao Li, Rong Jin
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors.
Ranked #1 on
Hand Gesture Recognition
on NVGesture
no code implementations • 9 Dec 2021 • Yang Xue, Zijing Liu, Xiaomin Fang, Fan Wang
However, neither sequences nor contact maps can fully characterize structures and functions of the proteins, which are closely related to the PPI problem.
1 code implementation • 2 Dec 2021 • Zhaoyuan Yin, Pichao Wang, Fan Wang, Xianzhe Xu, Hanling Zhang, Hao Li, Rong Jin
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations.
Ranked #2 on
Unsupervised Semantic Segmentation
on COCO-Stuff-171
(using extra training data)
no code implementations • 30 Nov 2021 • ZhiYuan Chen, Xiaomin Fang, Zixu Hua, Yueyang Huang, Fan Wang, Hua Wu
Efficient exploration of the chemical space to search the candidate drugs that satisfy various constraints is a fundamental task of drug discovery.
2 code implementations • 23 Nov 2021 • Hao Luo, Pichao Wang, Yi Xu, Feng Ding, Yanxin Zhou, Fan Wang, Hao Li, Rong Jin
We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks.
Ranked #1 on
Unsupervised Person Re-Identification
on Market-1501
(Rank-1 metric, using extra
training data)
1 code implementation • 18 Nov 2021 • Zijing Liu, Xianbin Ye, Xiaomin Fang, Fan Wang, Hua Wu, Haifeng Wang
Machine learning shows great potential in virtual screening for drug discovery.
no code implementations • 17 Nov 2021 • Ming Yan, Haiyang Xu, Chenliang Li, Junfeng Tian, Bin Bi, Wei Wang, Weihua Chen, Xianzhe Xu, Fan Wang, Zheng Cao, Zhicheng Zhang, Qiyu Zhang, Ji Zhang, Songfang Huang, Fei Huang, Luo Si, Rong Jin
The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image.
Ranked #8 on
Visual Question Answering (VQA)
on VQA v2 test-dev
1 code implementation • EMNLP (NLP4ConvAI) 2021 • Xin Tian, Liankai Huang, Yingzhan Lin, Siqi Bao, Huang He, Yunyi Yang, Hua Wu, Fan Wang, Shuqi Sun
In this paper, we propose a novel Amendable Generation for Dialogue State Tracking (AG-DST), which contains a two-pass generation process: (1) generating a primitive dialogue state based on the dialogue of the current turn and the previous dialogue state, and (2) amending the primitive dialogue state from the first pass.
Ranked #1 on
Dialogue State Tracking
on Wizard-of-Oz
Dialogue State Tracking
Multi-domain Dialogue State Tracking
+1
no code implementations • 29 Sep 2021 • Fan Wang, Hao Tian, Haoyi Xiong, Hua Wu, Yang Cao, Yu Kang, Haifeng Wang
While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs).
3 code implementations • 20 Sep 2021 • Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhihua Wu, Zhen Guo, Hua Lu, Xinxian Huang, Xin Tian, Xinchao Xu, Yingzhan Lin, Zheng-Yu Niu
To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL with up to 11 billion parameters, trained on both Chinese and English social media conversations.
1 code implementation • 14 Sep 2021 • Haojie Shi, Bo Zhou, Hongsheng Zeng, Fan Wang, Yueqiang Dong, Jiangyong Li, Kang Wang, Hao Tian, Max Q. -H. Meng
However, due to the complex nonlinear dynamics in quadrupedal robots and reward sparsity, it is still difficult for RL to learn effective gaits from scratch, especially in challenging tasks such as walking over the balance beam.
2 code implementations • ICLR 2022 • Tongkun Xu, Weihua Chen, Pichao Wang, Fan Wang, Hao Li, Rong Jin
Along with the pseudo labels, a weight-sharing triple-branch transformer framework is proposed to apply self-attention and cross-attention for source/target feature learning and source-target domain alignment, respectively.
Ranked #2 on
Domain Adaptation
on Office-31
2 code implementations • 8 Sep 2021 • Fan Wang, Hao Tian, Haoyi Xiong, Hua Wu, Jie Fu, Yang Cao, Yu Kang, Haifeng Wang
In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.
no code implementations • 8 Sep 2021 • Pichao Wang, Xue Wang, Hao Luo, Jingkai Zhou, Zhipeng Zhou, Fan Wang, Hao Li, Rong Jin
In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the \textit{convolutional stem} (\textit{conv-stem}) matters.
no code implementations • 8 Sep 2021 • Bo Zhou, Kejiao Li, Hongsheng Zeng, Fan Wang, Hao Tian
Combining off-policy reinforcement learning methods with function approximators such as neural networks has been found to lead to overestimation of the value function and sub-optimal solutions.
no code implementations • 23 Aug 2021 • Yiqi Jiang, Weihua Chen, Xiuyu Sun, Xiaoyu Shi, Fan Wang, Hao Li
Recently, GAN based method has demonstrated strong effectiveness in generating augmentation data for person re-identification (ReID), on account of its ability to bridge the gap between domains and enrich the data variety in feature space.
1 code implementation • 21 Jul 2021 • Shuangli Li, Jingbo Zhou, Tong Xu, Liang Huang, Fan Wang, Haoyi Xiong, Weili Huang, Dejing Dou, Hui Xiong
To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool).
Ranked #2 on
Protein-Ligand Affinity Prediction
on PDBbind
1 code implementation • 5 Jul 2021 • Yuqi Zhang, Qian Qi, Chong Liu, Weihua Chen, Fan Wang, Hao Li, Rong Jin
In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric.
no code implementations • 29 Jun 2021 • Bo Zhou, Hongsheng Zeng, Yuecheng Liu, Kejiao Li, Fan Wang, Hao Tian
At the planning stage, the search space is limited to the action set produced by the policy.
no code implementations • 11 Jun 2021 • Xiaomin Fang, Lihang Liu, Jieqiong Lei, Donglong He, Shanzhuo Zhang, Jingbo Zhou, Fan Wang, Hua Wu, Haifeng Wang
Recent advances in graph neural networks (GNNs) have shown great promise in applying GNNs for molecular representation learning.
Ranked #2 on
Molecular Property Prediction
on ToxCast
1 code implementation • 28 May 2021 • Pichao Wang, Xue Wang, Fan Wang, Ming Lin, Shuning Chang, Hao Li, Rong Jin
A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies.
1 code implementation • 20 May 2021 • Hao Luo, Weihua Chen, Xianzhe Xu, Jianyang Gu, Yuqi Zhang, Chong Liu, Yiqi Jiang, Shuting He, Fan Wang, Hao Li
We mainly focus on four points, i. e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge.
1 code implementation • 14 May 2021 • Chong Liu, Yuqi Zhang, Hao Luo, Jiasheng Tang, Weihua Chen, Xianzhe Xu, Fan Wang, Hao Li, Yi-Dong Shen
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions.
1 code implementation • 13 May 2021 • Fan Wang, Saarthak Kapse, Steven Liu, Prateek Prasanna, Chao Chen
Characterization of breast parenchyma on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a challenging task owing to the complexity of underlying tissue structures.
1 code implementation • 6 May 2021 • Siqi Bao, Bingjin Chen, Huang He, Xin Tian, Han Zhou, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Yingzhan Lin
In this work, we explore the application of PLATO-2 on various dialogue systems, including open-domain conversation, knowledge grounded dialogue, and task-oriented conversation.
no code implementations • 30 Mar 2021 • Shuning Chang, Pichao Wang, Fan Wang, Hao Li, Jiashi Feng
Temporal action proposal generation (TAPG) is a fundamental and challenging task in video understanding, especially in temporal action detection.
1 code implementation • NA 2021 • Weibin Li, Shanzhuo Zhang, Lihang Liu, Zhengjie Huang, Jieqiong Lei, Xiaomin Fang, Shikun Feng, Fan Wang
As graph neural networks have achieved great success in many domains, some studies apply graph neural networks to molecular property prediction and regard each molecule as a graph.
Ranked #5 on
Graph Property Prediction
on ogbg-molhiv
1 code implementation • 15 Feb 2021 • Weijia Zhang, Hao liu, Fan Wang, Tong Xu, Haoran Xin, Dejing Dou, Hui Xiong
Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
4 code implementations • ICCV 2021 • Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, Wei Jiang
Extracting robust feature representation is one of the key challenges in object re-identification (ReID).
Ranked #1 on
Person Re-Identification
on Market-1501-C
1 code implementation • 3 Feb 2021 • Huang He, Hua Lu, Siqi Bao, Fan Wang, Hua Wu, ZhengYu Niu, Haifeng Wang
The Track-1 of DSTC9 aims to effectively answer user requests or questions during task-oriented dialogues, which are out of the scope of APIs/DB.
1 code implementation • 20 Jan 2021 • Fei Du, Bo Xu, Jiasheng Tang, Yuqi Zhang, Fan Wang, Hao Li
We extend the classical tracking-by-detection paradigm to this tracking-any-object task.
Ranked #1 on
Multi-Object Tracking
on TAO
(using extra training data)
no code implementations • 6 Jan 2021 • Fan Wang, Lei Luo, En Zhu, Siwei Wang, Jun Long
Recent Multiple Object Tracking (MOT) methods have gradually attempted to integrate object detection and instance re-identification (Re-ID) into a united network to form a one-stage solution.
1 code implementation • 25 Dec 2020 • Jianyang Gu, Hao Luo, Weihua Chen, Yiqi Jiang, Yuqi Zhang, Shuting He, Fan Wang, Hao Li, Wei Jiang
Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.
no code implementations • 24 Dec 2020 • Fan Wang, Yongsheng Han, Ziyi He, Dachun Yang
In this article, the authors introduce Besov and Triebel-Lizorkin spaces on spaces of homogeneous type in the sense of Coifman and Weiss, prove that these (in)homogeneous Besov and Triebel-Lizorkin spaces are independent of the choices of both exp-ATIs (or exp-IATIs) and underlying spaces of distributions, and give some basic properties of these spaces.
Functional Analysis Analysis of PDEs Classical Analysis and ODEs Primary 46E35, Secondary 42B25, 42B20, 42B35, 30L99
1 code implementation • 17 Dec 2020 • Jingbo Zhou, Shuangli Li, Liang Huang, Haoyi Xiong, Fan Wang, Tong Xu, Hui Xiong, Dejing Dou
The hierarchical attentive aggregation can capture spatial dependencies among atoms, as well as fuse the position-enhanced information with the capability of discriminating multiple spatial relations among atoms.
no code implementations • 12 Dec 2020 • Chaohao Chen, Baolei Liu, Yongtao Liu, Jiayan Liao, Xuchen Shan, Fan Wang, Dayong Jin
Point spread function (PSF) engineering of the emitter can code higher spatial frequency information of an image to break diffraction limit but suffer from the complexed optical systems.
Optics
no code implementations • 7 Dec 2020 • Fan Wang, Jiangxin Yang, Yanlong Cao, Yanpeng Cao, Michael Ying Yang
Image Super-Resolution (SR) provides a promising technique to enhance the image quality of low-resolution optical sensors, facilitating better-performing target detection and autonomous navigation in a wide range of robotics applications.
no code implementations • 24 Nov 2020 • Fan Wang
Infrared search and tracking (IRST) system has been widely concerned and applied in the area of national defence.
no code implementations • 9 Jul 2020 • Haojie Liu, Ming Lu, Zhan Ma, Fan Wang, Zhihuang Xie, Xun Cao, Yao Wang
Over the past two decades, traditional block-based video coding has made remarkable progress and spawned a series of well-known standards such as MPEG-4, H. 264/AVC and H. 265/HEVC.
3 code implementations • Findings (ACL) 2021 • Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhen Guo, Zhibin Liu, Xinchao Xu
To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning.
no code implementations • 14 May 2020 • Pingping Lu, Chen Cui, Shaobing Xu, Huei Peng, Fan Wang
AI-based lane detection algorithms were actively studied over the last few years.
no code implementations • 12 May 2020 • Zizhang Wu, Weiwei Sun, Man Wang, Xiaoquan Wang, Lizhu Ding, Fan Wang
\romannumeral2, Expert knowledge for parking slot detection is under-estimated.
2 code implementations • 22 Apr 2020 • Shuting He, Hao Luo, Weihua Chen, Miao Zhang, Yuqi Zhang, Fan Wang, Hao Li, Wei Jiang
Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.
1 code implementation • 20 Apr 2020 • Fan Wang, Ming Tang
An important objective of designing lithium-ion rechargeable battery cells is to maximize their rate performance without compromising the energy density, which is mainly achieved through computationally expensive numerical simulations at present.
Materials Science Applied Physics
no code implementations • 10 Dec 2019 • Bo Zhou, Hongsheng Zeng, Fan Wang, Yunxiang Li, Hao Tian
By integrating dynamics models into model-free reinforcement learning (RL) methods, model-based value expansion (MVE) algorithms have shown a significant advantage in sample efficiency as well as value estimation.
no code implementations • 6 Nov 2019 • Fan Wang, Xiaomin Fang, Lihang Liu, Hao Tian, Zhiming Peng
The proposed method takes advantage of the characteristics of recommender systems and draws ideas from the model-based reinforcement learning method for higher sample efficiency.
3 code implementations • ACL 2020 • Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang
Pre-training models have been proved effective for a wide range of natural language processing tasks.
no code implementations • 25 Sep 2019 • Bo Zhou, Fan Wang, Hongsheng Zeng, Hao Tian
A promising direction is to combine model-based reinforcement learning with model-free reinforcement learning, such as model-based value expansion(MVE).
Model-based Reinforcement Learning
reinforcement-learning
+1
no code implementations • 24 Jul 2019 • Shaodi You, Erqi Huang, Shuaizhe Liang, Yongrong Zheng, Yunxiang Li, Fan Wang, Sen Lin, Qiu Shen, Xun Cao, Diming Zhang, Yuanjiang Li, Yu Li, Ying Fu, Boxin Shi, Feng Lu, Yinqiang Zheng, Robby T. Tan
This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark.
1 code implementation • 5 Jun 2019 • Chaotao Chen, Jinhua Peng, Fan Wang, Jun Xu, Hua Wu
In this paper, we propose a multi-mapping mechanism to better capture the one-to-many relationship, where multiple mapping modules are employed as latent mechanisms to model the semantic mappings from an input post to its diverse responses.
1 code implementation • ACL 2019 • Siqi Bao, Huang He, Fan Wang, Rongzhong Lian, Hua Wu
In this paper, a novel Generation-Evaluation framework is developed for multi-turn conversations with the objective of letting both participants know more about each other.
1 code implementation • 13 Feb 2019 • Rongzhong Lian, Min Xie, Fan Wang, Jinhua Peng, Hua Wu
Specifically, a posterior distribution over knowledge is inferred from both utterances and responses, and it ensures the appropriate selection of knowledge during the training process.
1 code implementation • 7 Feb 2019 • Łukasz Kidziński, Carmichael Ong, Sharada Prasanna Mohanty, Jennifer Hicks, Sean F. Carroll, Bo Zhou, Hongsheng Zeng, Fan Wang, Rongzhong Lian, Hao Tian, Wojciech Jaśkowski, Garrett Andersen, Odd Rune Lykkebø, Nihat Engin Toklu, Pranav Shyam, Rupesh Kumar Srivastava, Sergey Kolesnikov, Oleksii Hrinchuk, Anton Pechenko, Mattias Ljungström, Zhen Wang, Xu Hu, Zehong Hu, Minghui Qiu, Jun Huang, Aleksei Shpilman, Ivan Sosin, Oleg Svidchenko, Aleksandra Malysheva, Daniel Kudenko, Lance Rane, Aditya Bhatt, Zhengfei Wang, Penghui Qi, Zeyang Yu, Peng Peng, Quan Yuan, Wenxin Li, Yunsheng Tian, Ruihan Yang, Pingchuan Ma, Shauharda Khadka, Somdeb Majumdar, Zach Dwiel, Yinyin Liu, Evren Tumer, Jeremy Watson, Marcel Salathé, Sergey Levine, Scott Delp
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector.
1 code implementation • 1 Feb 2019 • Fan Wang, Xiaomin Fang, Lihang Liu, Yaxue Chen, Jiucheng Tao, Zhiming Peng, Cihang Jin, Hao Tian
On the one hand of this framework, an evaluation model is trained to evaluate the expected overall utility, by fully considering the user, item information and the correlations among the co-exposed items.
no code implementations • 15 Nov 2018 • Fan Wang, Bo Zhou, Ke Chen, Tingxiang Fan, Xi Zhang, Jiangyong Li, Hao Tian, Jia Pan
We built neural networks as our policy to map sensor readings to control signals on the UAV.
1 code implementation • 2 Aug 2018 • Fan Wang, Sach Mukherjee, Sylvia Richardson, Steven M. Hill
Our empirical results complement existing theory and provide a resource to compare methods across a range of scenarios and metrics.
1 code implementation • 3 Apr 2017 • Jinghao Lu, Chunyuan Li, Fan Wang
Miniscope calcium imaging is increasingly being used to monitor large populations of neuronal activities in freely behaving animals.
Neurons and Cognition Quantitative Methods
no code implementations • ICCV 2015 • Hao Su, Fan Wang, Eric Yi, Leonidas J. Guibas
Comparing two images from different views has been a long-standing challenging problem in computer vision, as visual features are not stable under large view point changes.
no code implementations • ICCV 2015 • Hsin-I Chen, Yi-Ling Chen, Wei-Tse Lee, Fan Wang, Bing-Yu Chen
In this paper, an inter-video mapping approach is proposed to integrate video footages from two dashcams installed on a preceding and its following vehicle to provide the illusion that the driver of the following vehicle can see-through the preceding one.
no code implementations • 26 Nov 2014 • Hao Su, Fan Wang, Li Yi, Leonidas Guibas
In this paper, given a single input image of an object, we synthesize new features for other views of the same object.
no code implementations • CVPR 2014 • Fan Wang, Qi-Xing Huang, Maks Ovsjanikov, Leonidas J. Guibas
Joint segmentation of image sets is a challenging problem, especially when there are multiple objects with variable appearance shared among the images in the collection and the set of objects present in each particular image is itself varying and unknown.