no code implementations • 26 Jun 2022 • Jiashun Cheng, Man Li, Jia Li, Fugee Tsung
A novel graph decoder named Wiener Graph Deconvolutional Network is correspondingly designed to perform information reconstruction from augmented latent representations.
no code implementations • 21 Jun 2022 • Hongyu Li, Jia Li, Xin Ren, Long Xu
Inspired by the haze formation process on Earth, we formulate a similar visual degradation process on clean images and synthesize dusty images sharing a similar feature distribution with realistic dusty images.
no code implementations • 11 Jun 2022 • Jia Li, Yongfeng Huang, Heng Chang, Yu Rong
We study the node classification problem in the hierarchical graph where a 'node' is a graph instance.
1 code implementation • 31 May 2022 • Jianheng Tang, Jiajin Li, Ziqi Gao, Jia Li
Graph Neural Networks (GNNs) are widely applied for graph anomaly detection.
1 code implementation • 31 May 2022 • Wenzhuo Yang, Jia Li, Caiming Xiong, Steven C. H. Hoi
Counterfactual explanation is an important Explainable AI technique to explain machine learning predictions.
no code implementations • 17 May 2022 • Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet
In this paper, we study the design and analysis of a class of efficient algorithms for computing the Gromov-Wasserstein (GW) distance tailored to large-scale graph learning tasks.
1 code implementation • CVPR 2022 • Chenxi Xie, Changqun Xia, Mingcan Ma, Zhirui Zhao, Xiaowu Chen, Jia Li
An attention-based Cross-Model Grafting Module (CMGM) is proposed to enable CNN branch to combine broken detailed information more holistically, guided by different source feature during decoding process.
no code implementations • CVPR 2022 • Peng Dai, Xin Yu, Lan Ma, Baoheng Zhang, Jia Li, Wenbo Li, Jiajun Shen, Xiaojuan Qi
Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras.
1 code implementation • 5 Apr 2022 • Yongjun Chen, Jia Li, Caiming Xiong
A generator, as an auxiliary model, is trained jointly with the discriminator to sample plausible alternative next items and will be thrown out after training.
1 code implementation • 25 Mar 2022 • Zhiwei Liu, Yongjun Chen, Jia Li, Man Luo, Philip S. Yu, Caiming Xiong
However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.
no code implementations • ACL 2022 • Wenpeng Yin, Jia Li, Caiming Xiong
This work defines a new learning paradigm ConTinTin (Continual Learning from Task Instructions), in which a system should learn a sequence of new tasks one by one, each task is explained by a piece of textual instruction.
no code implementations • Multimedia Systems 2022 • Chunxiao Fan, zhenxing Wang, Jia Li, Shanshan Wang, Xiao Sun
In the proposed method, (1) the topological structure information and texture feature of regions of interest (ROIs) are modeled as graphs and processed with graph convolutional network (GCN) to remain the topological features.
no code implementations • 2 Mar 2022 • Jia Li, Jie Cao, Junxian Duan, Ran He
We propose a new challenging task namely IDentity Stylization (IDS) across heterogeneous domains.
no code implementations • 18 Feb 2022 • Zhuomin Zhang, Elizabeth C. Mansfield, Jia Li, John Russell, George S. Young, Catherine Adams, James Z. Wang
European artists have sought to create life-like images since the Renaissance.
1 code implementation • 5 Feb 2022 • Yongjun Chen, Zhiwei Liu, Jia Li, Julian McAuley, Caiming Xiong
Specifically, we introduce a latent variable to represent users' intents and learn the distribution function of the latent variable via clustering.
1 code implementation • 12 Jan 2022 • Zohreh Ovaisi, Shelby Heinecke, Jia Li, Yongfeng Zhang, Elena Zheleva, Caiming Xiong
Robust machine learning is an increasingly important topic that focuses on developing models resilient to various forms of imperfect data.
no code implementations • 20 Nov 2021 • Wenpeng Yin, Shelby Heinecke, Jia Li, Nitish Shirish Keskar, Michael Jones, Shouzhong Shi, Stanislav Georgiev, Kurt Milich, Joseph Esposito, Caiming Xiong
The distribution gap between training datasets and data encountered in production is well acknowledged.
no code implementations • NeurIPS 2021 • Jia Li, Jiajin Li, Yang Liu, Jianwei Yu, Yueting Li, Hong Cheng
In this paper, we consider an inverse problem in graph learning domain -- ``given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal?"
no code implementations • 15 Oct 2021 • Mingcan Ma, Changqun Xia, Chenxi Xie, Xiaowu Chen, Jia Li
Moreover, Unlike multi-path parallel training, MHB randomly selects one branch each time for gradient back propagation in a boosting way.
no code implementations • 14 Oct 2021 • Shuyuan Xu, Juntao Tan, Shelby Heinecke, Jia Li, Yongfeng Zhang
Experiments on real-world e-commerce datasets show that our method is able to deconfound unobserved confounders to achieve better recommendation performance.
no code implementations • ICCV 2021 • Jiawei Zhao, Ke Yan, Yifan Zhao, Xiaowei Guo, Feiyue Huang, Jia Li
Different from these researches, in this paper, we propose a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i. e., structural relation graph and semantic relation graph.
no code implementations • 3 Oct 2021 • Jia Li, Huaibo Huang, Xiaofei Jia, Ran He
Blind face restoration (BFR) is a challenging problem because of the uncertainty of the degradation patterns.
no code implementations • 29 Sep 2021 • Chenyu Liu, Jia Li, Junxian Duan, Huaibo Huang
The first is that capturing the general clue of artifacts is difficult.
no code implementations • 29 Sep 2021 • Zhiwei Liu, Yongjun Chen, Jia Li, Man Luo, Philip S. Yu, Caiming Xiong
However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.
no code implementations • 23 Sep 2021 • Yongjun Chen, Jia Li, Chenghao Liu, Chenxi Li, Markus Anderle, Julian McAuley, Caiming Xiong
However, properly integrating them into user interest models is challenging since attribute dynamics can be diverse such as time-interval aware, periodic patterns (etc.
1 code implementation • ICCV 2021 • Jiajian Zhao, Yifan Zhao, Jia Li, Ke Yan, Yonghong Tian
The crucial problem in vehicle re-identification is to find the same vehicle identity when reviewing this object from cross-view cameras, which sets a higher demand for learning viewpoint-invariant representations.
1 code implementation • 15 Sep 2021 • Dong Zhao, Jia Li, Hongyu Li, Long Xu
In this paper, firstly, we propose a new complementary feature enhanced framework, in which the complementary features are learned by several complementary subtasks and then together serve to boost the performance of the primary task.
no code implementations • 8 Sep 2021 • Yifan Zhao, Jiawei Zhao, Jia Li, Xiaowu Chen
To construct our framework as well as achieving accurate salient detection results, we propose a Ubiquitous Target Awareness (UTA) network to solve three important challenges in RGB-D SOD task: 1) a depth awareness module to excavate depth information and to mine ambiguous regions via adaptive depth-error weights, 2) a spatial-aware cross-modal interaction and a channel-aware cross-level interaction, exploiting the low-level boundary cues and amplifying high-level salient channels, and 3) a gated multi-scale predictor module to perceive the object saliency in different contextual scales.
1 code implementation • 8 Sep 2021 • Zhongxing Ma, Yifan Zhao, Jia Li
Therefore, we propose a Pose-guided inter-and intra-part relational transformer (Pirt) for occluded person Re-Id, which builds part-aware long-term correlations by introducing transformers.
1 code implementation • ICCV 2021 • Guangyao Chen, Peixi Peng, Li Ma, Jia Li, Lin Du, Yonghong Tian
This observation leads to more explanations of the CNN's generalization behaviors in both robustness to common perturbations and out-of-distribution detection, and motivates a new perspective on data augmentation designed by re-combing the phase spectrum of the current image and the amplitude spectrum of the distracter image.
Ranked #5 on
Out-of-Distribution Detection
on CIFAR-10
1 code implementation • 14 Aug 2021 • Zhiwei Liu, Yongjun Chen, Jia Li, Philip S. Yu, Julian McAuley, Caiming Xiong
In this paper, we investigate the application of contrastive Self-Supervised Learning (SSL) to the sequential recommendation, as a way to alleviate some of these issues.
no code implementations • 5 Aug 2021 • Beomseok Seo, Lin Lin, Jia Li
Our main idea is a mixture of discriminative models that is trained with the guidance from a DNN.
1 code implementation • 7 Jul 2021 • Jia Li, Linhua Xiang, Jiwei Chen, Zengfu Wang
Given an image, we employ an Hourglass Network to infer all the keypoints from different persons indiscriminately as well as the guiding offsets connecting the adjacent keypoints belonging to the same persons.
Ranked #4 on
Pose Estimation
on CrowdPose
no code implementations • CVPR 2021 • Yifan Zhao, Ke Yan, Feiyue Huang, Jia Li
Fine-grained object recognition aims to learn effective features that can identify the subtle differences between visually similar objects.
Ranked #17 on
Fine-Grained Image Classification
on CUB-200-2011
no code implementations • CVPR 2021 • Jia Li, Zhaoyang Li, Jie Cao, Xingguang Song, Ran He
In this work, we propose a novel two-stage framework named FaceInpainter to implement controllable Identity-Guided Face Inpainting (IGFI) under heterogeneous domains.
no code implementations • CVPR 2021 • Luwei Hou, Yu Zhang, Kui Fu, Jia Li
Cross-domain weakly supervised object detection aims to adapt object-level knowledge from a fully labeled source domain dataset (i. e. with object bounding boxes) to train object detectors for target domains that are weakly labeled (i. e. with image-level tags).
Ranked #3 on
Weakly Supervised Object Detection
on Clipart1k
1 code implementation • 18 May 2021 • Jinming Su, Changqun Xia, Jia Li
In this network, we construct an attentionbased knowledge transfer module to make up the knowledge difference.
no code implementations • 19 Apr 2021 • Vincent Pisztora, Yanglan Ou, Xiaolei Huang, Francesca Chiaromonte, Jia Li
In this paper we propose $\epsilon$-Consistent Mixup ($\epsilon$mu).
no code implementations • 30 Mar 2021 • Jia Li, Ilias Rentzeperis, Cees van Leeuwen
The prominence of minimizing wiring distance in the dynamic evolution of the network determines the extent to which the core is encapsulated from the rest of the network, i. e., the context-sensitivity of its computations.
no code implementations • 23 Feb 2021 • Hongzhen Zhong, Hai Wan, Weilin Luo, Zhanhao Xiao, Jia Li, Biqing Fang
By taking experiments on a set of cases, we show that LOGION effectively exploits the structural similarity of BCs.
1 code implementation • 8 Feb 2021 • Jia Li, Mengzhou Liu, Honglei Zhang, Pengyun Wang, Yong Wen, Lujia Pan, Hong Cheng
We present Mask-GVAE, a variational generative model for blind denoising large discrete graphs, in which "blind denoising" means we don't require any supervision from clean graphs.
no code implementations • 22 Dec 2020 • Jia Li, Tomas Yu, Da-Cheng Juan, Arjun Gopalan, Hong Cheng, Andrew Tomkins
Recent studies have indicated that Graph Convolutional Networks (GCNs) act as a \emph{low pass} filter in spectral domain and encode smoothed node representations.
no code implementations • 11 Nov 2020 • Jia Li, Xiaowei Jia, HaoYu Yang, Vipin Kumar, Michael Steinbach, Gyorgy Simon
Specifically, we first describe a Causal-Temporal Structure for temporal EHR data; then based on this structure, we estimate sequential ITE along the timeline, using sequential Propensity Score Matching (PSM); and finally, we propose a knowledge-guided neural network methodology to incorporate estimated ITE.
1 code implementation • ECCV 2020 • Guangyao Chen, Limeng Qiao, Yemin Shi, Peixi Peng, Jia Li, Tiejun Huang, ShiLiang Pu, Yonghong Tian
In this process, one of the key challenges is to reduce the risk of generalizing the inherent characteristics of numerous unknown samples learned from a small amount of known data.
1 code implementation • ICLR 2021 • Shiyang Li, Semih Yavuz, Kazuma Hashimoto, Jia Li, Tong Niu, Nazneen Rajani, Xifeng Yan, Yingbo Zhou, Caiming Xiong
Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood.
Ranked #2 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Dialogue State Tracking
Multi-domain Dialogue State Tracking
1 code implementation • 21 Oct 2020 • Zhiruo Wang, Haoyu Dong, Ran Jia, Jia Li, Zhiyi Fu, Shi Han, Dongmei Zhang
First, we devise a unified tree-based structure, called a bi-dimensional coordinate tree, to describe both the spatial and hierarchical information of generally structured tables.
1 code implementation • NeurIPS 2020 • Jia Li, Tomasyu Yu, Jiajin Li, Honglei Zhang, Kangfei Zhao, Yu Rong, Hong Cheng, Junzhou Huang
In this work, we present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors.
1 code implementation • 17 Sep 2020 • Xin Guo, Yifan Zhao, Jia Li
To explore the relationship between music and dance movements, we propose a cross-modal alignment module that focuses on dancing video clips, accompanied on pre-designed music, to learn a system that can judge the consistency between the visual features of pose sequences and the acoustic features of music.
no code implementations • 2 Sep 2020 • Kui Fu, Jia Li, Lin Ma, Kai Mu, Yonghong Tian
In this paper, we propose a novel context reasoning approach for small object detection which models and infers the intrinsic semantic and spatial layout relationships between objects.
1 code implementation • 10 Aug 2020 • Zeyuan Wang, Yifan Zhao, Jia Li, Yonghong Tian
Given base classes with sufficient labeled samples, the target of few-shot classification is to recognize unlabeled samples of novel classes with only a few labeled samples.
no code implementations • 20 Jul 2020 • Federico A. Bugni, Jia Li, Qiyuan Li
Under a high-level condition that the observed data can be coupled by a collection of conditionally independent variables, we establish the asymptotic validity of the permutation test, allowing the sizes of the local subsamples to be either be fixed or grow to infinity.
1 code implementation • 9 Jun 2020 • Yafei Song, Ling Cai, Jia Li, Yonghong Tian, Mingyang Li
Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks.
1 code implementation • 30 May 2020 • Jia-Wei Zhao, Yifan Zhao, Jia Li, Xiaowu Chen
To solve this, many recent RGBD-based networks are proposed by adopting the depth map as an independent input and fuse the features with RGB information.
Ranked #1 on
RGB-D Salient Object Detection
on RGBD135
no code implementations • 1 Apr 2020 • Yanglan Ou, Yuan Xue, Ye Yuan, Tao Xu, Vincent Pisztora, Jia Li, Xiaolei Huang
In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance.
no code implementations • 27 Feb 2020 • Lichao Sun, Kazuma Hashimoto, Wenpeng Yin, Akari Asai, Jia Li, Philip Yu, Caiming Xiong
There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously.
1 code implementation • 22 Jan 2020 • Jia Li, Honglei Zhang, Zhichao Han, Yu Rong, Hong Cheng, Junzhou Huang
It has been demonstrated that adversarial graphs, i. e., graphs with imperceptible perturbations added, can cause deep graph models to fail on node/graph classification tasks.
no code implementations • 15 Jan 2020 • Yafei Song, Jia Li, Xiaogang Wang, Xiaowu Chen
To obtain effective features for single image dehazing, this paper presents a novel Ranking Convolutional Neural Network (Ranking-CNN).
1 code implementation • 18 Dec 2019 • Jia Li, Jinming Su, Changqun Xia, Mingcan Ma, Yonghong Tian
Through these two attentions, we use the Purificatory Mechanism to impose strict weights with different regions of the whole salient objects and purify results from hard-to-distinguish regions, thus accurately predicting the locations and details of salient objects.
no code implementations • 12 Dec 2019 • Jia Li, Tong Shen, Wei zhang, Hui Ren, Dan Zeng, Tao Mei
The stunning progress in face manipulation methods has made it possible to synthesize realistic fake face images, which poses potential threats to our society.
no code implementations • 7 Dec 2019 • Lixiang Zhang, Lin Lin, Jia Li
In this paper, we propose a framework that imposes on blocks of variables a chain structure obtained by step-wise greedy search so that the DNN architecture can leverage the constructed grid.
5 code implementations • 24 Nov 2019 • Jia Li, Wen Su, Zengfu Wang
We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one.
Ranked #8 on
Multi-Person Pose Estimation
on COCO test-dev
no code implementations • IJCNLP 2019 • Jia Li, Chongyang Tao, Wei Wu, Yansong Feng, Dongyan Zhao, Rui Yan
We study how to sample negative examples to automatically construct a training set for effective model learning in retrieval-based dialogue systems.
no code implementations • ICCV 2019 • Limeng Qiao, Yemin Shi, Jia Li, Yao-Wei Wang, Tiejun Huang, Yonghong Tian
By solving the problem with its closed-form solution on the fly with the setup of transduction, our approach efficiently tailors an episodic-wise metric for each task to adapt all features from a shared task-agnostic embedding space into a more discriminative task-specific metric space.
no code implementations • 25 Sep 2019 • Zhichao Han, Jia Li, Xu Li, Hong Cheng
Such linear transformation will result in these good properties.
no code implementations • 25 Sep 2019 • Lichao Sun, Yingbo Zhou, Jia Li, Richard Socher, Philip S. Yu, Caiming Xiong
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
no code implementations • 18 Sep 2019 • Changqun Xia, Jia Li, Jinming Su, Yonghong Tian
Typically, objects with the same semantics are not always prominent in images containing different backgrounds.
no code implementations • 11 Sep 2019 • Jia Li, Jinming Su, Changqun Xia, Yonghong Tian
Moreover, benchmarking results of the proposed baseline approach and other methods on 360$^\circ$ SOD dataset show the proposed dataset is very challenging, which also validate the usefulness of the proposed dataset and approach to boost the development of SOD on 360$^\circ$ omnidirectional scenes.
no code implementations • 3 Aug 2019 • Yafei Song, Di Zhu, Jia Li, Yonghong Tian, Mingyang Li
For better performance, the features used for open-loop localization are required to be short-term globally static, and the ones used for re-localization or loop closure detection need to be long-term static.
1 code implementation • 31 Jul 2019 • Yi Zheng, Yifan Zhao, Mengyuan Ren, He Yan, Xiangju Lu, Junhui Liu, Jia Li
Recent years have witnessed increasing attention in cartoon media, powered by the strong demands of industrial applications.
no code implementations • 6 Jun 2019 • Peilin Chen, Hai Wan, Shaowei Cai, Weilin Luo, Jia Li
Based on the BLP and DTCC, we develop a local search algorithm named BDCC and improve it by a hyperheuristic strategy.
no code implementations • 5 Jun 2019 • Lichao Sun, Yingbo Zhou, Ji Wang, Jia Li, Richard Sochar, Philip S. Yu, Caiming Xiong
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information.
1 code implementation • 10 May 2019 • Jia Li, Zhichao Han, Hong Cheng, Jiao Su, Pengyun Wang, Jianfeng Zhang, Lujia Pan
Through experiments on a real-world telecommunication network and a traffic network in California, we demonstrate the superiority of LRGCN to other competing methods in path failure prediction, and prove the effectiveness of SAPE on path representation.
no code implementations • 17 Apr 2019 • Jia Li, Xing Wei, Guoqiang Yang, Xiao Sun, Changliang Li
A multiscale shared convolution structure is adopted in the discriminator network to further supervise training the generator.
no code implementations • 17 Apr 2019 • Jia Li, Xiao Sun, Xing Wei, Changliang Li, Jian-Hua Tao
In recent years, the generation of conversation content based on deep neural networks has attracted many researchers.
1 code implementation • 10 Apr 2019 • Jia Li, Yu Rong, Hong Cheng, Helen Meng, Wenbing Huang, Junzhou Huang
We study the node classification problem in the hierarchical graph where a `node' is a graph instance, e. g., a user group in the above example.
Ranked #10 on
Graph Classification
on D&D
no code implementations • 10 Apr 2019 • Kaiwen Yu, Jia Li, Yu Zhang, Yifan Zhao, Long Xu
Along with the development of virtual reality (VR), omnidirectional images play an important role in producing multimedia content with immersive experience.
no code implementations • 10 Apr 2019 • Jia Li, Kui Fu, Shengwei Zhao, Shiming Ge
In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model.
no code implementations • 9 Apr 2019 • Kui Fu, Peipei Shi, Yafei Song, Shiming Ge, Xiangju Lu, Jia Li
To address these issues, we design an extremely light-weight network with ultrafast speed, named UVA-Net.
no code implementations • ICLR 2019 • Rui Zhang, Tomas Pfister, Jia Li
The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the presence of artifacts and degenerated transformations.
no code implementations • ICCV 2019 • Jinming Su, Jia Li, Yu Zhang, Changqun Xia, Yonghong Tian
In this network, the feature selectivity at boundaries is enhanced by incorporating a boundary localization stream, while the feature invariance at interiors is guaranteed with a complex interior perception stream.
no code implementations • 25 Nov 2018 • Jia Li, Daowei Li, Kui Fu, Long Xu
Visual attention prediction is a classic problem that seems to be well addressed in the deep learning era.
no code implementations • 25 Nov 2018 • Shiming Ge, Shengwei Zhao, Chenyu Li, Jia Li
In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively.
no code implementations • 23 Nov 2018 • Jia Li, Junjie Wu, Anlin Zheng, Yafei Song, Yu Zhang, Xiaowu Chen
Segmenting primary objects in a video is an important yet challenging problem in computer vision, as it exhibits various levels of foreground/background ambiguities.
no code implementations • 14 Nov 2018 • Kui Fu, Jia Li, Yu Zhang, Hongze Shen, Yonghong Tian
After that, the visual saliency knowledge encoded in the most representative paths is selected and aggregated to improve the capability of MM-Net in predicting spatial saliency in aerial scenarios.
no code implementations • 12 Nov 2018 • Long Nguyen, Zhou Yang, Jiazhen Zhu, Jia Li, Fang Jin
To improve the efficiency of the emergency response in the immediate aftermath of a disaster, we propose a heuristic multi-agent reinforcement learning scheduling algorithm, named as ResQ, which can effectively schedule the rapid deployment of volunteers to rescue victims in dynamic settings.
no code implementations • 12 Nov 2018 • Long Nguyen, Zhou Yang, Jia Li, Guofeng Cao, Fang Jin
Our proposed sequence to sequence method forecast people's needs more successfully than either of the other models.
no code implementations • 5 Nov 2018 • Jia Li, Cong Fang, Zhouchen Lin
LPOM is block multi-convex in all layer-wise weights and activations.
no code implementations • 2 Nov 2018 • Jia Li, Yafei Song, Jianfeng Zhu, Lele Cheng, Ying Su, Lin Ye, Pengcheng Yuan, Shumin Han
In this manner, the influence of bias and noise in the web data can be gradually alleviated, leading to the steadily improving performance of URNet.
1 code implementation • EMNLP 2018 • Wei Wei, Quoc Le, Andrew Dai, Jia Li
However, current datasets are limited in size, and the environment for training agents and evaluating progress is relatively unsophisticated.
no code implementations • 12 Sep 2018 • Lei Yang, Jia Li, Defeng Sun, Kim-Chuan Toh
When the support points of the barycenter are pre-specified, this problem can be modeled as a linear programming (LP) problem whose size can be extremely large.
1 code implementation • 28 Aug 2018 • Yu Luo, Jianbo Ye, Reginald B. Adams, Jr., Jia Li, Michelle G. Newman, James Z. Wang
A system to model the emotional expressions based on bodily movements, named ARBEE (Automated Recognition of Bodily Expression of Emotion), has also been developed and evaluated.
no code implementations • 27 Jun 2018 • Jia Li, Pengcheng Yuan, Daxin Gu, Yonghong Tian
Primary object segmentation plays an important role in understanding videos generated by unmanned aerial vehicles.
no code implementations • 27 Jun 2018 • Changqun Xia, Jia Li, Jinming Su, Ali Borji
Due to the effectiveness of the learned metric, it also can be used to facilitate the development of new models for fixation prediction.
1 code implementation • 27 Jun 2018 • Lishi Zhang, Chenghan Fu, Jia Li
In this paper, we propose a human-agent collaborative annotation approach that can efficiently generate per-pixel masks of semantic objects in tagged images with multi-granularity supervisions.
no code implementations • 15 May 2018 • Wei Teng, Yu Zhang, Xiaowu Chen, Jia Li, Zhiqiang He
Image co-segmentation is a challenging task in computer vision that aims to segment all pixels of the objects from a predefined semantic category.
no code implementations • 25 Feb 2018 • Xinye Zheng, Jianbo Ye, Yukun Chen, Stephen Wistar, Jia Li, Jose A. Piedra-Fernández, Michael A. Steinberg, James Z. Wang
Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms.
no code implementations • 12 Nov 2017 • Yukun Chen, Jianbo Ye, Jia Li
This distance quantifies the dissimilarity of GMM-HMMs by measuring both the difference between the two marginal GMMs and that between the two transition matrices.
no code implementations • ICCV 2017 • Xiaowu Chen, Anlin Zheng, Jia Li, Feng Lu
Toward this end, this paper proposes two-stream fixation-semantic CNNs, whose architecture is inspired by the fact that salient objects in complex images can be unambiguously annotated by selecting the pre-segmented semantic objects that receive the highest fixation density in eye-tracking experiments.
no code implementations • ICCV 2017 • Jia Li, Anlin Zheng, Xiaowu Chen, Bin Zhou
By applying CCNN on each video frame, the spatial foregroundness and backgroundness maps can be initialized, which are then propagated between various frames so as to segment primary video objects and suppress distractors.
no code implementations • ICCV 2017 • Yafei Song, Xiaowu Chen, Jia Li, Qinping Zhao
One stream, named AppNet, is to extract 2D appearance features from the input image.
no code implementations • ACL 2017 • Jianbo Ye, Yan-ran Li, Zhaohui Wu, James Z. Wang, Wenjie Li, Jia Li
The new clustering method is easy to use and consistently outperforms other methods on a variety of data sets.
no code implementations • CVPR 2017 • Changqun Xia, Jia Li, Xiaowu Chen, Anlin Zheng, Yu Zhang
Finding what is and what is not a salient object can be helpful in developing better features and models in salient object detection (SOD).
no code implementations • CVPR 2017 • Shiming Ge, Jia Li, Qiting Ye, Zhao Luo
Detecting masked faces (i. e., faces with occlusions) is a challenging task due to two main reasons: 1)the absence of large datasets of masked faces, and 2)the absence of facial cues from the masked regions.
no code implementations • 16 Apr 2017 • Wenxiang Cong, Ge Wang, Qingsong Yang, Jiang Hsieh, Jia Li, Rongjie Lai
In this paper, we propose a CT image reconstruction method based on the prior knowledge of the low-dimensional manifold of CT image.
no code implementations • 9 Feb 2017 • Rongjie Lai, Jia Li
Low-rank structures play important role in recent advances of many problems in image science and data science.
1 code implementation • 4 Jan 2017 • Jianbo Ye, Jia Li, Michelle G. Newman, Reginald B. Adams, Jr., James Z. Wang
We proposed a probabilistic approach to joint modeling of participants' reliability and humans' regularity in crowdsourced affective studies.
no code implementations • 17 Nov 2016 • Shenlong Wang, Linjie Luo, Ning Zhang, Jia Li
We propose AutoScaler, a scale-attention network to explicitly optimize this trade-off in visual correspondence tasks.
no code implementations • 1 Nov 2016 • Jia Li, Changqun Xia, Xiaowu Chen
Based on this dataset, this paper proposes an unsupervised baseline approach for video-based SOD by using saliency-guided stacked autoencoders.
1 code implementation • 5 Aug 2016 • Yukun Chen, Jianbo Ye, Jia Li
We refer to such HMMs as Gaussian mixture model-HMM (GMM-HMM).
no code implementations • 31 May 2016 • Zihan Zhou, Siqiong He, Jia Li, James Z. Wang
The capacity of automatically modeling photographic composition is valuable for many real-world machine vision applications such as digital photography, image retrieval, image understanding, and image aesthetics assessment.
no code implementations • 1 Mar 2016 • Yu Zhang, Stephen Wistar, Jia Li, Michael Steinberg, James Z. Wang
In our system, we extract and summarize important visual storm evidence from satellite image sequences in the way that meteorologists interpret the images.
no code implementations • ICCV 2015 • Jia Li, Changqun Xia, Yafei Song, Shu Fang, Xiaowu Chen
To address this problem, we propose a data-driven metric for comprehensive evaluation of saliency models.
2 code implementations • 30 Sep 2015 • Jianbo Ye, Panruo Wu, James Z. Wang, Jia Li
In a variety of research areas, the weighted bag of vectors and the histogram are widely used descriptors for complex objects.
no code implementations • 26 Aug 2015 • Mu Qiao, Jia Li
This motivates us to find a subspace by applying weighted principal component analysis to the modes of a kernel density and the class means.
no code implementations • JEPTALNRECITAL 2015 • Johan Ferguth, Aur{\'e}lie Jouannet, Asma Zamiti, Yunhe Wu, Jia Li, Antonina Bondarenko, Damien Nouvel, Mathieu Valette
Dans cet article, nous pr{\'e}sentons une m{\'e}thodologie pour l{'}identification de messages suspect{\'e}s d{'}{\^e}tre produits par des Community Managers {\`a} des fins commerciales d{\'e}guis{\'e}es dans des documents du Web 2. 0.
no code implementations • CVPR 2015 • Yu Zhang, Xiaowu Chen, Jia Li, Chen Wang, Changqun Xia
Semantic object segmentation in video is an important step for large-scale multimedia analysis.
no code implementations • 5 Jan 2015 • Ali Borji, Ming-Ming Cheng, Huaizu Jiang, Jia Li
We extensively compare, qualitatively and quantitatively, 40 state-of-the-art models (28 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over 6 challenging datasets for the purpose of benchmarking salient object detection and segmentation methods.
no code implementations • 18 Nov 2014 • Ali Borji, Ming-Ming Cheng, Qibin Hou, Huaizu Jiang, Jia Li
Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision.