Search Results for author: Wei Tang

Found 48 papers, 15 papers with code

What Large Language Models Bring to Text-rich VQA?

no code implementations13 Nov 2023 Xuejing Liu, Wei Tang, Xinzhe Ni, Jinghui Lu, Rui Zhao, Zechao Li, Fei Tan

This pipeline achieved superior performance compared to the majority of existing Multimodal Large Language Models (MLLM) on four text-rich VQA datasets.

Image Comprehension Optical Character Recognition (OCR) +2

RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning

no code implementations3 Nov 2023 Ziyu Wang, Wenhao Jiang, Zixuan Zhang, Wei Tang, Junchi Yan

Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms.

feature selection

LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labels

no code implementations31 Jul 2023 Mingcai Chen, Yuntao Du, Wei Tang, Baoming Zhang, Hao Cheng, Shuwei Qian, Chongjun Wang

We introduce LaplaceConfidence, a method that to obtain label confidence (i. e., clean probabilities) utilizing the Laplacian energy.

Dimensionality Reduction Learning with noisy labels

Deeply Coupled Cross-Modal Prompt Learning

1 code implementation29 May 2023 Xuejing Liu, Wei Tang, Jinghui Lu, Rui Zhao, Zhaojun Guo, Fei Tan

Recent advancements in multimodal foundation models (e. g., CLIP) have excelled in zero-shot generalization.

Domain Adaptation Few-Shot Learning +2

Performative Prediction with Bandit Feedback: Learning through Reparameterization

no code implementations1 May 2023 Yatong Chen, Wei Tang, Chien-Ju Ho, Yang Liu

Specifically, we develop a {\em reparameterization} framework that reparametrizes the performative prediction objective as a function of the induced data distribution.

Recommendation Systems

MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking

no code implementations CVPR 2023 Zheng Qin, Sanping Zhou, Le Wang, Jinghai Duan, Gang Hua, Wei Tang

For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target.

motion prediction Multi-Object Tracking

A Global and Patch-wise Contrastive Loss for Accurate Automated Exudate Detection

no code implementations22 Feb 2023 Wei Tang, Yinxiao Wang, Kangning Cui, Raymond H. Chan

In this paper, we propose a loss function that incorporates a global segmentation loss, a patch-wise density loss, and a patch-wise edge-aware loss to improve the performance of these networks on the detection and segmentation of hard exudates.


Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization

1 code implementation ICCV 2023 Kun Xia, Le Wang, Sanping Zhou, Gang Hua, Wei Tang

To this end, we propose a unified framework, termed Noisy Pseudo-Label Learning, to handle both location biases and category errors.

Pseudo Label Temporal Action Localization

Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision

1 code implementation18 Dec 2022 Wei Tang, Weijia Zhang, Min-Ling Zhang

MIPLGP first assigns each instance with a candidate label set in an augmented label space, then transforms the candidate label set into a logarithmic space to yield the disambiguated and continuous labels via an exclusive disambiguation strategy, and last induces a model based on the Gaussian processes.

Gaussian Processes Partial Label Learning

Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shape

no code implementations28 Nov 2022 Linkun Fan, Fazhi He, Qing Guo, Wei Tang, Xiaolin Hong, Bing Li

As a result, backdoor pattern designed for one certain 3D data structure will be disable for other data structures of the same 3D scene.

Backdoor Attack

Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision

no code implementations23 Nov 2022 Jiawei Zhan, Jun Liu, Wei Tang, Guannan Jiang, Xi Wang, Bin-Bin Gao, Tianliang Zhang, Wenlong Wu, Wei zhang, Chengjie Wang, Yuan Xie

This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning.

Multi-Label Image Classification

Fully Digital Second-order Level-crossing Sampling ADC for Data Saving in Sensing Sparse Signals

no code implementations17 Nov 2022 Mario Renteria-Pinon, Xiaochen Tang, Jaime Ramirez-Angulo, Wei Tang

This paper presents a fully integrated second-order level-crossing sampling data converter for real-time data compression and feature extraction.

Data Compression Quantization

Dynamic Predictive Sampling Analog to Digital Converter for Sparse Signal Sensing

no code implementations17 Nov 2022 Xiaochen Tang, Mario Renteria-Pinon, Wei Tang

No quantization is performed for successfully predicted sampling points so that the data throughput and power can be saved.

Data Compression Quantization

UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction

1 code implementation16 Nov 2022 Wei Tang, Benfeng Xu, Yuyue Zhao, Zhendong Mao, Yifeng Liu, Yong Liao, Haiyong Xie

Relational triple extraction is challenging for its difficulty in capturing rich correlations between entities and relations.

Relation Extraction

Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization

no code implementations CVPR 2022 Kun Xia, Le Wang, Sanping Zhou, Nanning Zheng, Wei Tang

The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e. g., context and background, in an untrimmed video.

Temporal Action Localization

Online Bayesian Recommendation with No Regret

no code implementations12 Feb 2022 Yiding Feng, Wei Tang, Haifeng Xu

For each user with her own private preference and belief, the platform commits to a recommendation strategy to utilize his information advantage on the product state to persuade the self-interested user to follow the recommendation.

Time-aware Path Reasoning on Knowledge Graph for Recommendation

1 code implementation5 Aug 2021 Yuyue Zhao, Xiang Wang, Jiawei Chen, Yashen Wang, Wei Tang, Xiangnan He, Haiyong Xie

In this work, we propose a novel Time-aware Path reasoning for Recommendation (TPRec for short) method, which leverages the potential of temporal information to offer better recommendation with plausible explanations.

Explainable Recommendation Relation Extraction

Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction

1 code implementation ICCV 2021 Fang Zheng, Le Wang, Sanping Zhou, Wei Tang, Zhenxing Niu, Nanning Zheng, Gang Hua

Specifically, the proposed unlimited neighborhood interaction module generates the fused-features of all agents involved in an interaction simultaneously, which is adaptive to any number of agents and any range of interaction area.

Graph Attention Trajectory Prediction

Exploit Visual Dependency Relations for Semantic Segmentation

no code implementations CVPR 2021 Mingyuan Liu, Dan Schonfeld, Wei Tang

Inter-class reasoning then performs spatial and semantic reasoning based on the dependency relations among different object categories.

Semantic Segmentation

Optimal Query Complexity of Secure Stochastic Convex Optimization

no code implementations NeurIPS 2020 Wei Tang, Chien-Ju Ho, Yang Liu

The goal of the learner is to optimize the accuracy, i. e., obtaining an accurate estimate of the optimal point, while securing her privacy, i. e., making it difficult for the adversary to infer the optimal point.

Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement

no code implementations11 Mar 2021 Chi Zhang, Zihang Lin, Liheng Xu, Zongliang Li, Wei Tang, Yuehu Liu, Gaofeng Meng, Le Wang, Li Li

The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.

Disentanglement Image Generation +1

Competitive Information Design for Pandora's Box

no code implementations5 Mar 2021 Bolin Ding, Yiding Feng, Chien-Ju Ho, Wei Tang

We study a natural competitive-information-design variant for the Pandora's Box problem (Weitzman 1979), where each box is associated with a strategic information sender who can design what information about the box's prize value to be revealed to the agent when the agent inspects the box.

Computer Science and Game Theory

Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score

1 code implementation28 Sep 2020 He Huang, Shunta Saito, Yuta Kikuchi, Eiichi Matsumoto, Wei Tang, Philip S. Yu

Motivated by the fact that detecting these rare relations can be critical in real-world applications, this paper introduces a novel integrated framework of classification and ranking to resolve the class imbalance problem in scene graph parsing.

The 1st Tiny Object Detection Challenge:Methods and Results

1 code implementation16 Sep 2020 Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi

The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.

Human Detection object-detection +1

Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge

no code implementations30 Jul 2020 He Huang, Yuanwei Chen, Wei Tang, Wenhao Zheng, Qing-Guo Chen, Yao Hu, Philip Yu

On the other hand, there is a large semantic gap between seen and unseen classes in the existing multi-label classification datasets.

Classification General Classification +3

Continuous matrix product operator approach to finite temperature quantum states

2 code implementations27 Apr 2020 Wei Tang, Hong-Hao Tu, Lei Wang

We present an algorithm for studying quantum systems at finite temperature using continuous matrix product operator representation.

Strongly Correlated Electrons Statistical Mechanics Computational Physics

Combining Visible Light and Infrared Imaging for Efficient Detection of Respiratory Infections such as COVID-19 on Portable Device

no code implementations15 Apr 2020 Zheng Jiang, Menghan Hu, Lei Fan, Yaling Pan, Wei Tang, Guangtao Zhai, Yong Lu

In this work, we perform the health screening through the combination of the RGB and thermal videos obtained from the dual-mode camera and deep learning architecture. We first accomplish a respiratory data capture technique for people wearing masks by using face recognition.

Face Recognition

Bandit Learning with Delayed Impact of Actions

no code implementations NeurIPS 2021 Wei Tang, Chien-Ju Ho, Yang Liu

In this paper, we formulate this delayed and long-term impact of actions within the context of multi-armed bandits.

Fairness Multi-Armed Bandits

MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation

no code implementations19 Oct 2018 Wei Tang, Gui Li, Xinyuan Bao, Teng Li

One generator transforms the conditional person image into a coarse image of the target pose globally, and the other is to enhance the detailed quality of the synthetic person image through a local reinforcement network.

Image Generation

Deeply Learned Compositional Models for Human Pose Estimation

no code implementations ECCV 2018 Wei Tang, Pei Yu, Ying Wu

This results in a network with a hierarchical compositional architecture and bottom-up/top-down inference stages.

Pose Estimation

ReabsNet: Detecting and Revising Adversarial Examples

no code implementations21 Dec 2017 Jiefeng Chen, Zihang Meng, Changtian Sun, Wei Tang, Yinglun Zhu

Though deep neural network has hit a huge success in recent studies and applica- tions, it still remains vulnerable to adversarial perturbations which are imperceptible to humans.

General Classification

Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification

no code implementations ICCV 2017 Jiahuan Zhou, Pei Yu, Wei Tang, Ying Wu

In contrast to these methods, this paper advocates a different paradigm: part of the learning can be performed online but with nominal costs, so as to achieve online metric adaptation for different input probes.

Metric Learning Person Re-Identification

A 20-Liter Test Stand with Gas Purification for Liquid Argon Research

1 code implementation4 Feb 2016 Yichen Li, Craig Thorn, Wei Tang, Jyoti Joshi, Xin Qian, Milind Diwan, Steve Kettell, William Morse, Triveni Rao, James Stewart, Thomas Tsang, Lige Zhang

We describe the design of a 20-liter test stand constructed to study fundamental properties of liquid argon (LAr).

Instrumentation and Detectors High Energy Physics - Experiment

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