Search Results for author: Bing Li

Found 62 papers, 24 papers with code

When does Further Pre-training MLM Help? An Empirical Study on Task-Oriented Dialog Pre-training

1 code implementation EMNLP (insights) 2021 Qi Zhu, Yuxian Gu, Lingxiao Luo, Bing Li, Cheng Li, Wei Peng, Minlie Huang, Xiaoyan Zhu

Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks’ performances.

Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completion

1 code implementation15 Sep 2022 Chen Chen, YuFei Wang, Bing Li, Kwok-Yan Lam

To remedy the KG structure information loss from the "flat" text, we further improve the input representations of entities and relations, and the inference algorithm in KG-S2S.

Knowledge Graph Completion

Combating Mode Collapse in GANs via Manifold Entropy Estimation

1 code implementation25 Aug 2022 Haozhe Liu, Bing Li, Haoqian Wu, Hanbang Liang, Yawen Huang, Yuexiang Li, Bernard Ghanem, Yefeng Zheng

Different from existing methods, we propose to generalize the discriminator as feature embedding, and maximize the entropy of distributions in the embedding space learned by the discriminator.

Cross-Architecture Knowledge Distillation

no code implementations12 Jul 2022 Yufan Liu, Jiajiong Cao, Bing Li, Weiming Hu, Jingting Ding, Liang Li

However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN.

Knowledge Distillation

Nonlinear Sufficient Dimension Reduction for Distribution-on-Distribution Regression

no code implementations11 Jul 2022 Qi Zhang, Bing Li, Lingzhou Xue

We introduce a novel framework for nonlinear sufficient dimension reduction where both the predictor and the response are distributional data, which are modeled as members of a metric space.

Dimensionality Reduction

Narrowing the Gap: Improved Detector Training with Noisy Location Annotations

1 code implementation12 Jun 2022 Shaoru Wang, Jin Gao, Bing Li, Weiming Hu

Experiments for both synthesized and real-world scenarios consistently demonstrate the effectiveness of our approach, e. g., our method increases the degraded performance of the FCOS detector from 33. 6% AP to 35. 6% AP on COCO.

object-detection Object Detection

SubGraph Networks based Entity Alignment for Cross-lingual Knowledge Graph

no code implementations7 May 2022 Shanqing Yu, Shihan Zhang, Jianlin Zhang, Jiajun Zhou, Qi Xuan, Bing Li, Xiaojuan Hu

Cross-lingual knowledge graph entity alignment aims to discover the cross-lingual links in the multi-language KGs, which is of great significance to the NLP applications and multi-language KGs fusion.

Entity Alignment Knowledge Graphs

Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement

no code implementations7 May 2022 Bing Li, Jiaxin Chen, Dongming Zhang, Xiuguo Bao, Di Huang

To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net).

Action Recognition Denoising +1

Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning

1 code implementation CVPR 2022 Li Yang, Yan Xu, Chunfeng Yuan, Wei Liu, Bing Li, Weiming Hu

They base the visual grounding on the features from pre-generated proposals or anchors, and fuse these features with the text embeddings to locate the target mentioned by the text.

object-detection Object Detection +1

CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation

no code implementations31 Mar 2022 Ziqi Zhang, Yuxin Chen, Zongyang Ma, Zhongang Qi, Chunfeng Yuan, Bing Li, Ying Shan, Weiming Hu

In this paper, we propose to CREATE, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration benchmark, to facilitate research and application in video titling and video retrieval in Chinese.

Video Captioning Video Retrieval

Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth

1 code implementation29 Mar 2022 Ziyue Feng, Liang Yang, Longlong Jing, HaiYan Wang, YingLi Tian, Bing Li

Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions.

Depth Prediction Disentanglement +2

Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels

no code implementations23 Mar 2022 Bing Li, Cheng Zheng, Guohao Li, Bernard Ghanem

To provide an alternative, we propose a novel approach that utilizes monocular RGB images and point clouds to generate pseudo scene flow labels for training scene flow networks.

pseudo label Self-Supervised Learning

Continual Prompt Tuning for Dialog State Tracking

1 code implementation ACL 2022 Qi Zhu, Bing Li, Fei Mi, Xiaoyan Zhu, Minlie Huang

A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle.

Continual Learning Transfer Learning

Learning Target-aware Representation for Visual Tracking via Informative Interactions

no code implementations7 Jan 2022 Mingzhe Guo, Zhipeng Zhang, Heng Fan, Liping Jing, Yilin Lyu, Bing Li, Weiming Hu

The proposed GIM module and InBN mechanism are general and applicable to different backbone types including CNN and Transformer for improvements, as evidenced by our extensive experiments on multiple benchmarks.

Representation Learning Visual Tracking

An additive graphical model for discrete data

no code implementations29 Dec 2021 Jun Tao, Bing Li, Lingzhou Xue

We introduce a nonparametric graphical model for discrete node variables based on additive conditional independence.

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

2 code implementations CVPR 2020 Jin Gao, Yan Lu, Xiaojuan Qi, Yutong Kou, Bing Li, Liang Li, Shan Yu, Weiming Hu

In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot online adaptation without requiring offline training.

Continual Learning One-Shot Learning +2

Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos

1 code implementation5 Nov 2021 Minglang Qiao, Yufan Liu, Mai Xu, Xin Deng, Bing Li, Weiming Hu, Ali Borji

In this paper, we propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information.

Saliency Prediction

Multimodal Semi-Supervised Learning for 3D Objects

1 code implementation22 Oct 2021 Zhimin Chen, Longlong Jing, Yang Liang, YingLi Tian, Bing Li

This paper explores how the coherence of different modelities of 3D data (e. g. point cloud, image, and mesh) can be used to improve data efficiency for both 3D classification and retrieval tasks.

3D Classification

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction

1 code implementation Findings (ACL) 2022 Linhan Zhang, Qian Chen, Wen Wang, Chong Deng, Shiliang Zhang, Bing Li, Wei Wang, Xin Cao

In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document.

Contrastive Learning Document Embedding +3

Dimension Reduction and Data Visualization for Fréchet Regression

no code implementations1 Oct 2021 Qi Zhang, Lingzhou Xue, Bing Li

In this paper, we introduce a flexible sufficient dimension reduction (SDR) method for Fr\'echet regression to achieve two purposes: to mitigate the curse of dimensionality caused by high-dimensional predictors, and to provide a tool for data visualization for Fr\'echet regression.

Data Visualization Dimensionality Reduction

Self-Supervised Modality-Invariant and Modality-Specific Feature Learning for 3D Objects

no code implementations29 Sep 2021 Longlong Jing, Zhimin Chen, Bing Li, YingLi Tian

Our proposed novel self-supervised model learns two types of distinct features: modality-invariant features and modality-specific features.

3D Object Recognition Cross-Modal Retrieval

Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR

2 code implementations20 Sep 2021 Ziyue Feng, Longlong Jing, Peng Yin, YingLi Tian, Bing Li

Unlike the existing methods that use sparse LiDAR mainly in a manner of time-consuming iterative post-processing, our model fuses monocular image features and sparse LiDAR features to predict initial depth maps.

Depth Completion Depth Prediction +3

SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction

no code implementations18 Sep 2021 Zekun Li, Yufan Liu, Bing Li, Weiming Hu, Kebin Wu, Pei Wang

CDI builds the global attention and interaction among different levels in decoupled space which also solves the problem of heavy computation.

Sent2Span: Span Detection for PICO Extraction in the Biomedical Text without Span Annotations

1 code implementation Findings (EMNLP) 2021 Shifeng Liu, Yifang Sun, Bing Li, Wei Wang, Florence T. Bourgeois, Adam G. Dunn

The rapid growth in published clinical trials makes it difficult to maintain up-to-date systematic reviews, which requires finding all relevant trials.


Learn to Match: Automatic Matching Network Design for Visual Tracking

1 code implementation ICCV 2021 Zhipeng Zhang, Yihao Liu, Xiao Wang, Bing Li, Weiming Hu

Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants.

Visual Tracking

PSE-Match: A Viewpoint-free Place Recognition Method with Parallel Semantic Embedding

no code implementations1 Aug 2021 Peng Yin, Lingyun Xu, Ziyue Feng, Anton Egorov, Bing Li

Accurate localization on autonomous driving cars is essential for autonomy and driving safety, especially for complex urban streets and search-and-rescue subterranean environments where high-accurate GPS is not available.

Autonomous Driving

Automatic Construction of Enterprise Knowledge Base

no code implementations EMNLP (ACL) 2021 Junyi Chai, Yujie He, Homa Hashemi, Bing Li, Daraksha Parveen, Ranganath Kondapally, Wenjin Xu

In this paper, we present an automatic knowledge base construction system from large scale enterprise documents with minimal efforts of human intervention.

SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation

1 code implementation10 May 2021 Bing Li, Cheng Zheng, Silvio Giancola, Bernard Ghanem

We propose a novel scene flow estimation approach to capture and infer 3D motions from point clouds.

Scene Flow Estimation

A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Tracking

no code implementations6 May 2021 Zhenbang Li, Yaya Shi, Jin Gao, Shaoru Wang, Bing Li, Pengpeng Liang, Weiming Hu

In this paper, we show the existence of universal perturbations that can enable the targeted attack, e. g., forcing a tracker to follow the ground-truth trajectory with specified offsets, to be video-agnostic and free from inference in a network.

Visual Tracking

PDNet: Towards Better One-stage Object Detection with Prediction Decoupling

no code implementations28 Apr 2021 Li Yang, Yan Xu, Shaoru Wang, Chunfeng Yuan, Ziqi Zhang, Bing Li, Weiming Hu

However, the most suitable positions for inferring different targets, i. e., the object category and boundaries, are generally different.

object-detection Object Detection

Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model

1 code implementation ECCV 2020 Yufan Liu, Minglang Qiao, Mai Xu, Bing Li, Weiming Hu, Ali Borji

Inspired by the findings of our investigation, we propose a novel multi-modal video saliency model consisting of three branches: visual, audio and face.

Saliency Prediction

Open-book Video Captioning with Retrieve-Copy-Generate Network

no code implementations CVPR 2021 Ziqi Zhang, Zhongang Qi, Chunfeng Yuan, Ying Shan, Bing Li, Ying Deng, Weiming Hu

Due to the rapid emergence of short videos and the requirement for content understanding and creation, the video captioning task has received increasing attention in recent years.

Video Captioning

AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation

3 code implementations24 Feb 2021 Bing Li, Yuanlue Zhu, Yitong Wang, Chia-Wen Lin, Bernard Ghanem, Linlin Shen

Specifically, a new generator architecture is proposed to simultaneously transfer color/texture styles and transform local facial shapes into anime-like counterparts based on the style of a reference anime-face, while preserving the global structure of the source photo-face.

Face Generation Translation

On Forward Sufficient Dimension Reduction for Categorical and Ordinal Responses

no code implementations11 Feb 2021 Harris Quach, Bing Li

Like other forward regression-based sufficient dimension reduction methods, our approach avoids the relatively stringent distributional requirements necessary for inverse regression alternatives.

Dimensionality Reduction Methodology

FGNET-RH: Fine-Grained Named Entity Typing via Refinement in Hyperbolic Space

no code implementations27 Jan 2021 Muhammad Asif Ali, Yifang Sun, Bing Li, Wei Wang

Fine-Grained Named Entity Typing (FG-NET) aims at classifying the entity mentions into a wide range of entity types (usually hundreds) depending upon the context.

Entity Typing

Cross-Lingual Named Entity Recognition Using Parallel Corpus: A New Approach Using XLM-RoBERTa Alignment

no code implementations26 Jan 2021 Bing Li, Yujie He, Wenjin Xu

We built an entity alignment model on top of XLM-RoBERTa to project the entities detected on the English part of the parallel data to the target language sentences, whose accuracy surpasses all previous unsupervised models.

Entity Alignment named-entity-recognition +2

Named Entity Recognition in the Style of Object Detection

no code implementations26 Jan 2021 Bing Li

In this work, we propose a two-stage method for named entity recognition (NER), especially for nested NER.

named-entity-recognition NER +4

High Quality Disparity Remapping With Two-Stage Warping

no code implementations ICCV 2021 Bing Li, Chia-Wen Lin, Cheng Zheng, Shan Liu, Junsong Yuan, Bernard Ghanem, C.-C. Jay Kuo

In the second stage, we derive another warping model to refine warping results in less important regions by eliminating serious distortions in shape, disparity and 3D structure.

Rethinking the competition between detection and ReID in Multi-Object Tracking

4 code implementations23 Oct 2020 Chao Liang, Zhipeng Zhang, Xue Zhou, Bing Li, Shuyuan Zhu, Weiming Hu

However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm.

Multi-Object Tracking

Towards Accurate Pixel-wise Object Tracking by Attention Retrieval

1 code implementation6 Aug 2020 Zhipeng Zhang, Bing Li, Weiming Hu, Houwen Peng

We first build a look-up-table (LUT) with the ground-truth mask in the starting frame, and then retrieves the LUT to obtain an attention map for spatial constraints.

Object Tracking

Object Relational Graph with Teacher-Recommended Learning for Video Captioning

no code implementations CVPR 2020 Ziqi Zhang, Yaya Shi, Chunfeng Yuan, Bing Li, Peijin Wang, Weiming Hu, Zheng-Jun Zha

In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy.

 Ranked #1 on Video Captioning on MSR-VTT (using extra training data)

Language Modelling Video Captioning

HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition

no code implementations3 Dec 2019 Shifeng Liu, Yifang Sun, Bing Li, Wei Wang, Xiang Zhao

To tackle Named Entity Recognition (NER) tasks, supervised methods need to obtain sufficient cleanly annotated data, which is labor and time consuming.

Boundary Detection named-entity-recognition +1

An Overview of In-memory Processing with Emerging Non-volatile Memory for Data-intensive Applications

no code implementations15 Jun 2019 Bing Li, Bonan Yan, Hai, Li

The conventional von Neumann architecture has been revealed as a major performance and energy bottleneck for rising data-intensive applications.

Multimodal Semantic Attention Network for Video Captioning

no code implementations8 May 2019 Liang Sun, Bing Li, Chunfeng Yuan, Zheng-Jun Zha, Weiming Hu

Inspired by the fact that different modalities in videos carry complementary information, we propose a Multimodal Semantic Attention Network(MSAN), which is a new encoder-decoder framework incorporating multimodal semantic attributes for video captioning.

General Classification Multi-Label Classification +1

Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification

no code implementations ECCV 2018 Yang Du, Chunfeng Yuan, Bing Li, Lili Zhao, Yangxi Li, Weiming Hu

Furthermore, since different layers in a deep network capture feature maps of different scales, we use these feature maps to construct a spatial pyramid and then utilize multi-scale information to obtain more accurate attention scores, which are used to weight the local features in all spatial positions of feature maps to calculate attention maps.

Action Classification Classification +1

Depth-Aware Stereo Video Retargeting

no code implementations CVPR 2018 Bing Li, Chia-Wen Lin, Boxin Shi, Tiejun Huang, Wen Gao, C. -C. Jay Kuo

As compared with traditional video retargeting, stereo video retargeting poses new challenges because stereo video contains the depth information of salient objects and its time dynamics.

Spatio-Temporal Self-Organizing Map Deep Network for Dynamic Object Detection From Videos

no code implementations CVPR 2017 Yang Du, Chunfeng Yuan, Bing Li, Weiming Hu, Stephen Maybank

In dynamic object detection, it is challenging to construct an effective model to sufficiently characterize the spatial-temporal properties of the background.

object-detection Object Detection

Linear Contour Learning: A Method for Supervised Dimension Reduction

no code implementations13 Aug 2014 Bing Li, Hongyuan Zha, Francesca Chiaromonte

We propose a novel approach to sufficient dimension reduction in regression, based on estimating contour directions of negligible variation for the response surface.

Dimensionality Reduction

Removing Mixture of Gaussian and Impulse Noise by Patch-Based Weighted Means

no code implementations11 Mar 2014 Haijuan Hu, Bing Li, Quansheng Liu

We first establish a law of large numbers and a convergence theorem in distribution to show the rate of convergence of the non-local means filter for removing Gaussian noise.

Illumination Estimation Based on Bilayer Sparse Coding

no code implementations CVPR 2013 Bing Li, Weihua Xiong, Weiming Hu, Houwen Peng

In this paper, we propose a novel bilayer sparse coding model for illumination estimation that considers image similarity in terms of both low level color distribution and high level image scene content simultaneously.

Color Constancy

Cannot find the paper you are looking for? You can Submit a new open access paper.