no code implementations • NAACL (ACL) 2022 • Qi Yu
Earlier NLP studies on framing in political discourse have focused heavily on shallow classification of issue framing, while framing effect arising from pragmatic cues remains neglected.
no code implementations • NAACL (CMCL) 2021 • Qi Yu, Aikaterini-Lida Kalouli, Diego Frassinelli
This paper describes the submission of the team KonTra to the CMCL 2021 Shared Task on eye-tracking prediction.
no code implementations • 19 Sep 2023 • Wentao Bao, Qi Yu, Yu Kong
A recent trend in OSR shows the benefit of generative models to discriminative unknown detection.
no code implementations • 18 Sep 2023 • Xinmiao Lin, Wentao Bao, Qi Yu, Yu Kong
Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model.
1 code implementation • 19 Jun 2023 • Deep Pandey, Qi Yu
To unveil the real cause of this undesired behavior, we theoretically investigate evidential models and identify a fundamental limitation that explains the inferior performance: existing evidential activation functions create zero evidence regions, which prevent the model to learn from training samples falling into such regions.
1 code implementation • 5 Feb 2023 • Omar Shindi, Qi Yu, Parth Girdhar, Daoyi Dong
The proposed framework relies only on the measurement at the end of the control process and offers the ability to find the optimal control policy without access to quantum systems during the learning process.
1 code implementation • 30 Nov 2022 • Deep Shankar Pandey, Qi Yu
The Conditional Neural Process (CNP) family of models offer a promising direction to tackle few-shot problems by achieving better scalability and competitive predictive performance.
no code implementations • 23 Aug 2022 • Yuansheng Zhu, Wentao Bao, Qi Yu
We develop a novel weakly supervised method for the OpenVAD problem by integrating evidential deep learning (EDL) and normalizing flows (NFs) into a multiple instance learning (MIL) framework.
1 code implementation • 15 Aug 2022 • Jintang Li, Zhouxin Yu, Zulun Zhu, Liang Chen, Qi Yu, Zibin Zheng, Sheng Tian, Ruofan Wu, Changhua Meng
We explore a new direction in that we can capture the evolving dynamics of temporal graphs with spiking neural networks (SNNs) instead of RNNs.
1 code implementation • 12 Jun 2022 • Hitesh Sapkota, Qi Yu
We propose to conduct novel active deep multiple instance learning that samples a small subset of informative instances for annotation, aiming to significantly boost the instance-level prediction.
1 code implementation • 5 May 2022 • Zulun Zhu, Jiaying Peng, Jintang Li, Liang Chen, Qi Yu, Siqiang Luo
Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information.
no code implementations • 3 Apr 2022 • Krishna Prasad Neupane, Ervine Zheng, Yu Kong, Qi Yu
We present a novel dynamic recommendation model that focuses on users who have interactions in the past but turn relatively inactive recently.
1 code implementation • CVPR 2022 • Hitesh Sapkota, Qi Yu
BN-SVP essentially performs dynamic non-parametric hierarchical clustering with an enhanced self-transition that groups segments in a video into temporally consistent and semantically coherent hidden states that can be naturally interpreted as scenes.
1 code implementation • CVPR 2022 • Deep Pandey, Qi Yu
The proposed model formulates a multidimensional belief measure, which can quantify the known uncertainty and lower bound the unknown uncertainty of any given task.
1 code implementation • CVPR 2022 • Wentao Bao, Qi Yu, Yu Kong
The OpenTAL is general to enable existing TAL models for open set scenarios, and experimental results on THUMOS14 and ActivityNet1. 3 benchmarks show the effectiveness of our method.
no code implementations • NeurIPS 2021 • Weishi Shi, Dayou Yu, Qi Yu
However, data annotation for training MLC models becomes much more labor-intensive due to the correlated (hence non-exclusive) labels and a potential large and sparse label space.
1 code implementation • 21 Nov 2021 • Dingrong Wang, Hitesh Sapkota, Xumin Liu, Qi Yu
Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) aims at finding a specific image from a large gallery given a query sketch.
no code implementations • 16 Nov 2021 • Yuansheng Zhu, Weishi Shi, Deep Shankar Pandey, Yang Liu, Xiaofan Que, Daniel E. Krutz, Qi Yu
We propose a novel framework to classify large-scale time series data with long duration.
no code implementations • 14 Nov 2021 • Qi Yu, Shota Yokoyama, Daoyi Dong, David McManus, Hidehiro Yonezawa
In this paper, we consider the filtering problem of an optical parametric oscillator (OPO).
no code implementations • 29 Sep 2021 • Hitesh Sapkota, Qi Yu
We propose a novel active deep multiple instance learning (ADMIL) model that samples a small subset of informative instances for annotation, aiming to significantly boost the instance-level prediction.
2 code implementations • ICCV 2021 • Wentao Bao, Qi Yu, Yu Kong
Different from image data, video actions are more challenging to be recognized in an open-set setting due to the uncertain temporal dynamics and static bias of human actions.
1 code implementation • ICCV 2021 • Wentao Bao, Qi Yu, Yu Kong
Traffic accident anticipation aims to accurately and promptly predict the occurrence of a future accident from dashcam videos, which is vital for a safety-guaranteed self-driving system.
1 code implementation • AISTATS 2021 • Hitesh Sapkota, Qi Yu
However, solely focusing on a single instance in a bag makes the model less robust to outliers or multi-modal scenarios, where a single bag contains a diverse set of positive instances.
no code implementations • NeurIPS 2020 • Weishi Shi, Xujiang Zhao, Feng Chen, Qi Yu
We present a novel multi-source uncertainty prediction approach that enables deep learning (DL) models to be actively trained with much less labeled data.
no code implementations • NeurIPS 2020 • Ervine Zheng, Qi Yu, Rui Li, Pengcheng Shi, Anne Haake
We propose to jointly analyze experts' eye movements and verbal narrations to discover important and interpretable knowledge patterns to better understand their decision-making processes.
2 code implementations • 1 Aug 2020 • Wentao Bao, Qi Yu, Yu Kong
The derived uncertainty-based ranking loss is found to significantly boost model performance by improving the quality of relational features.
Ranked #2 on Accident Anticipation on CCD
no code implementations • 20 Jul 2020 • Wentao Bao, Qi Yu, Yu Kong
Monocular 3D object detection aims to detect objects in a 3D physical world from a single camera.
no code implementations • 23 Apr 2020 • Jeffrey Palmerino, Qi Yu, Travis Desell, Daniel E. Krutz
Unfortunately, current self-adaptive approaches do not account for tactic volatility in their decision-making processes, and merely assume that tactics do not experience volatility.
no code implementations • NeurIPS 2019 • Weishi Shi, Qi Yu
We propose a novel active learning (AL) model that integrates Bayesian and discriminative kernel machines for fast and accurate multi-class data sampling.
no code implementations • 25 Sep 2019 • Weishi Shi, Xujiang Zhao, Feng Chen, Qi Yu
We present a novel multi-source uncertainty prediction approach that enables deep learning (DL) models to be actively trained with much less labeled data.
1 code implementation • 24 Jun 2019 • Qi Yu, Wei Dai, Zoran Cvetkovic, Jubo Zhu
BLOTLESS updates a block of dictionary elements and the corresponding sparse coefficients simultaneously.
1 code implementation • BMC Systems Biology 2019 • Kishan KC, Rui Li, Feng Cui, Qi Yu, Anne R. Haake
However, it is still a challenging task to aggregate heterogeneous biological information such as gene expression and gene interactions to achieve more accurate inference for prediction and discovery of new gene interactions.
Ranked #1 on Gene Interaction Prediction on BioGRID(yeast) (using extra training data)
1 code implementation • 7 Sep 2018 • Zheng Gao, Gang Fu, Chunping Ouyang, Satoshi Tsutsui, Xiaozhong Liu, Jeremy Yang, Christopher Gessner, Brian Foote, David Wild, Qi Yu, Ying Ding
We propose this method for its added value relative to existing graph analytical methodology, and in the real world context of biomedical knowledge discovery applicability.
no code implementations • 23 May 2016 • Chao Wang, Qi Yu, Lei Gong, Xi Li, Yuan Xie, Xuehai Zhou
As the emerging field of machine learning, deep learning shows excellent ability in solving complex learning problems.