To alleviate label scarcity in Named Entity Recognition (NER) task, distantly supervised NER methods are widely applied to automatically label data and identify entities.
For visual representation, a representation driven by a combination of the imageaugmented forward dynamics and the reward is acquired.
Building models to detect vaccine attitudes on social media is challenging because of the composite, often intricate aspects involved, and the limited availability of annotated data.
By using cross-attention, the transformer decoder fuses features and includes more target cues into the current point cloud feature to compute the region attentions, which makes the similarity computing more efficient.
1 code implementation • 17 Oct 2021 • Yuefeng Chen, Xiaofeng Mao, Yuan He, Hui Xue, Chao Li, Yinpeng Dong, Qi-An Fu, Xiao Yang, Tianyu Pang, Hang Su, Jun Zhu, Fangcheng Liu, Chao Zhang, Hongyang Zhang, Yichi Zhang, Shilong Liu, Chang Liu, Wenzhao Xiang, Yajie Wang, Huipeng Zhou, Haoran Lyu, Yidan Xu, Zixuan Xu, Taoyu Zhu, Wenjun Li, Xianfeng Gao, Guoqiu Wang, Huanqian Yan, Ying Guo, Chaoning Zhang, Zheng Fang, Yang Wang, Bingyang Fu, Yunfei Zheng, Yekui Wang, Haorong Luo, Zhen Yang
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
Then, to fuse the information of features in the two branches and obtain their similarity, we propose two cross correlation modules, named Pointcloud-wise and Point-wise respectively.
In this paper, we conceptualize the single-document extractive summarization as a rebalance problem and present a deep differential amplifier framework.
This paper makes the following original contributions.
However, the representation ability of such models is limited due to: (1) shallow GNNs are incapable to capture long-range spatial correlations, (2) only spatial connections are considered and a mass of semantic connections are ignored, which are of great importance for a comprehensive understanding of traffic networks.
Ranked #3 on Traffic Prediction on PeMS07
Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in crowd occlusion scenes.
Ranked #4 on Pedestrian Detection on Caltech
In this paper, we propose an improved Signed Distance Function (SDF) for both 2D SLAM and pure localization to improve the accuracy of mapping and localization.
Further analysis indicates that the locality and globality of the traffic networks are critical to traffic flow prediction and the proposed TSSRGCN model can adapt to the various temporal traffic patterns.
In this paper, we propose an end-to-end visual place recognition network for event cameras, which can achieve good place recognition performance in challenging environments.
This paper considers the problem of testing whether there exists a non-negative solution to a possibly under-determined system of linear equations with known coefficients.
In this work, we design a simple computing library to bridge the gap and decouple the work of ocean modeling from parallel computing.
Based on a monotonicity property afforded by such a geometric structure, we construct a bootstrap procedure that, unlike many studies in nonstandard settings, dispenses with estimation of local parameter spaces, and the critical values are obtained in a way as simple as computing the test statistic.
In this paper, we develop a systematic formulation based on Monte Carlo sampling to achieve such information transfer.
Recovering 3D human body shape and pose from 2D images is a challenging task due to high complexity and flexibility of human body, and relatively less 3D labeled data.
We proceed from a scalar time series $s(t_n); t_n = t_0 + n \Delta t$ and using methods of nonlinear time series analysis show how to produce a $D_E > 1$ dimensional time delay embedding space in which the time series has no false neighbors as does the observed $s(t_n)$ time series.
Entity linking is the task of aligning mentions to corresponding entities in a given knowledge base.
In this paper, we propose a parallel and scalable approach for geodesic distance computation on triangle meshes.
This method utilizes the correlation between map points to separate points that are part of the static scene and points that are part of different moving objects into different groups.
In object recognition, Fisher vector (FV) representation is one of the state-of-art image representations ways at the expense of dense, high dimensional features and increased computation time.