Search Results for author: Tao Han

Found 32 papers, 11 papers with code

Traffic Sign Interpretation in Real Road Scene

no code implementations17 Nov 2023 Chuang Yang, Kai Zhuang, Mulin Chen, Haozhao Ma, Xu Han, Tao Han, Changxing Guo, Han Han, Bingxuan Zhao, Qi Wang

Following the above issues, we propose a traffic sign interpretation (TSI) task, which aims to interpret global semantic interrelated traffic signs (e. g.,~driving instruction-related texts, symbols, and guide panels) into a natural language for providing accurate instruction support to autonomous or assistant driving.

Instruction Following Multi-Task Learning

STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning

1 code implementation ICCV 2023 Tao Han, Lei Bai, Lingbo Liu, Wanli Ouyang

Scale variation is a deep-rooted problem in object counting, which has not been effectively addressed by existing scale-aware algorithms.

feature selection Object Counting

FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead

1 code implementation6 Apr 2023 Kang Chen, Tao Han, Junchao Gong, Lei Bai, Fenghua Ling, Jing-Jia Luo, Xi Chen, Leiming Ma, Tianning Zhang, Rui Su, Yuanzheng Ci, Bin Li, Xiaokang Yang, Wanli Ouyang

We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI).

Atlas: Automate Online Service Configuration in Network Slicing

1 code implementation30 Oct 2022 Qiang Liu, Nakjung Choi, Tao Han

First, we design a learning-based simulator to reduce the sim-to-real discrepancy, which is accomplished by a new parameter searching method based on Bayesian optimization.

Bayesian Optimization Safe Exploration +1

Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition

no code implementations28 Oct 2022 Yist Y. Lin, Tao Han, HaiHua Xu, Van Tung Pham, Yerbolat Khassanov, Tze Yuang Chong, Yi He, Lu Lu, Zejun Ma

One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched.

Action Detection Activity Detection +5

DR.VIC: Decomposition and Reasoning for Video Individual Counting

2 code implementations CVPR 2022 Tao Han, Lei Bai, Junyu Gao, Qi Wang, Wanli Ouyang

Instead of relying on the Multiple Object Tracking (MOT) techniques, we propose to solve the problem by decomposing all pedestrians into the initial pedestrians who existed in the first frame and the new pedestrians with separate identities in each following frame.

Crowd Counting Density Estimation +2

DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets

no code implementations15 Jan 2022 Yongjie Guan, Xueyu Hou, Nan Wu, Bo Han, Tao Han

In this paper, we propose DeepMix, a mobility-aware, lightweight, and hybrid 3D object detection framework for improving the user experience of AR/MR on mobile headsets.

3D Object Detection Mixed Reality +1

OnSlicing: Online End-to-End Network Slicing with Reinforcement Learning

no code implementations2 Nov 2021 Qiang Liu, Nakjung Choi, Tao Han

As online learning is converged, OnSlicing reduces 12. 5% usage without any violations as compared to the state-of-the-art online DRL solution.

reinforcement-learning Reinforcement Learning (RL)

LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds

no code implementations10 Oct 2021 Qi Wang, Tao Han, Junyu Gao, Yuan Yuan, Xuelong Li

The rapid development in visual crowd analysis shows a trend to count people by positioning or even detecting, rather than simply summing a density map.

Visual Crowd Analysis

Supervised Contrastive Learning for Accented Speech Recognition

no code implementations2 Jul 2021 Tao Han, Hantao Huang, Ziang Yang, Wei Han

Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents.

Accented Speech Recognition Contrastive Learning +2

MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations

1 code implementation14 May 2021 Taojiannan Yang, Sijie Zhu, Matias Mendieta, Pu Wang, Ravikumar Balakrishnan, Minwoo Lee, Tao Han, Mubarak Shah, Chen Chen

MutualNet is a general training methodology that can be applied to various network structures (e. g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e. g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets.

Action Recognition Image Classification +2

References of References: How Far is the Knowledge Ancestry

no code implementations21 Jan 2021 Chao Min, Yi Bu, Tao Han

Scientometrics studies have extended from direct citations to high-order citations, as simple citation count is found to tell only part of the story regarding scientific impact.

Information Retrieval Digital Libraries

Electroweak Phase Transition with an SU(2) Dark Sector

no code implementations17 Dec 2020 Tathagata Ghosh, Huai-Ke Guo, Tao Han, Hongkai Liu

We investigate two different scenarios of the dark sector scalars with $Z_2$ symmetry, with Higgs portal interactions that can introduce mixing between the SM Higgs boson and the SM singlet scalars in the dark sector.

High Energy Physics - Phenomenology Cosmology and Nongalactic Astrophysics

LiveMap: Real-Time Dynamic Map in Automotive Edge Computing

no code implementations16 Dec 2020 Qiang Liu, Tao Han, Jiang, Xie, BaekGyu Kim

In this paper, we propose LiveMap, a real-time dynamic map, that detects, matches, and tracks objects on the road with crowdsourcing data from connected vehicles in sub-second.

Autonomous Driving Edge-computing +3

Learning Independent Instance Maps for Crowd Localization

1 code implementation8 Dec 2020 Junyu Gao, Tao Han, Qi Wang, Yuan Yuan, Xuelong Li

Furthermore, to improve the segmentation quality for different density regions, we present a differentiable Binarization Module (BM) to output structured instance maps.

Binarization Segmentation

Answer-checking in Context: A Multi-modal FullyAttention Network for Visual Question Answering

no code implementations17 Oct 2020 Hantao Huang, Tao Han, Wei Han, Deep Yap, Cheng-Ming Chiang

From the human perspective, to answer a visual question, one needs to read the question and then refer to the image to generate an answer.

Question Answering Visual Question Answering

Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning

1 code implementation NeurIPS 2020 Tao Han, Junyu Gao, Yuan Yuan, Qi Wang

In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating.

Template Matching

A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View

no code implementations29 Sep 2020 Zhiyuan Zhao, Tao Han, Junyu. Gao, Qi. Wang, Xuelong. Li

Drones shooting can be applied in dynamic traffic monitoring, object detecting and tracking, and other vision tasks.

Crowd Counting Density Estimation +1

DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing

no code implementations17 Aug 2020 Qiang Liu, Tao Han, Ning Zhang, Ye Wang

Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond.

reinforcement-learning Reinforcement Learning (RL)

Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting

1 code implementation5 Apr 2020 Qi. Wang, Tao Han, Junyu. Gao, Yuan Yuan

Specifically, for a specific neuron of a source model, NLT exploits few labeled target data to learn domain shift parameters.

Crowd Counting Domain Adaptation +1

Focus on Semantic Consistency for Cross-domain Crowd Understanding

no code implementations20 Feb 2020 Tao Han, Junyu. Gao, Yuan Yuan, Qi. Wang

According to the semantic consistency, a similar distribution in deep layer's features of the synthetic and real-world crowd area, we first introduce a semantic extractor to effectively distinguish crowd and background in high-level semantic information.

Domain Adaptation

Robust Shape Estimation for 3D Deformable Object Manipulation

1 code implementation26 Sep 2018 Tao Han, Xuan Zhao, Peigen Sun, Jia Pan

Existing shape estimation methods for deformable object manipulation suffer from the drawbacks of being off-line, model dependent, noise-sensitive or occlusion-sensitive, and thus are not appropriate for manipulation tasks requiring high precision.


Type-II 2HDM under the Precision Measurements at the $Z$-pole and a Higgs Factory

1 code implementation6 Aug 2018 Ning Chen, Tao Han, Shufang Su, Wei Su, Yongcheng Wu

We also find that the expected accuracies at the $Z$-pole and at a Higgs factory are quite complementary in constraining mass splittings of heavy Higgs bosons.

High Energy Physics - Phenomenology

Higgs Couplings at High Scales

no code implementations26 Mar 2018 Dorival Goncalves, Tao Han, Satyanarayan Mukhopadhyay

We study the off-shell production of the Higgs boson at the LHC to probe Higgs physics at higher energy scales utilizing the process $g g \rightarrow h^{*} \rightarrow ZZ$.

High Energy Physics - Phenomenology High Energy Physics - Experiment

Off-shell Higgs Probe to Naturalness

no code implementations5 Oct 2017 Dorival Goncalves, Tao Han, Satyanarayan Mukhopadhyay

Examining the Higgs sector at high energy scales through off-shell Higgs production can potentially shed light on the naturalness problem of the Higgs mass.

High Energy Physics - Phenomenology High Energy Physics - Experiment

Bi-objective Optimization for Robust RGB-D Visual Odometry

no code implementations27 Nov 2014 Tao Han, Chao Xu, Ryan Loxton, Lei Xie

This paper considers a new bi-objective optimization formulation for robust RGB-D visual odometry.

Visual Odometry

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