Search Results for author: Shuqiang Jiang

Found 33 papers, 15 papers with code

Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection

1 code implementation14 Feb 2024 Pengfei Zhou, Weiqing Min, Jiajun Song, Yang Zhang, Shuqiang Jiang

The complexity of food semantic attributes further makes it more difficult for current ZSD methods to distinguish various food categories.

Attribute Nutrition

Vision-based Food Nutrition Estimation via RGB-D Fusion Network

1 code implementation journal 2023 Wenjing Shao, Weiqing Min, Sujuan Hou, Mengjiang Luo, TianHao Li, Yuanjie Zheng, Shuqiang Jiang

In this paper, we designed one RGB-D fusion network, which integrated multimodal feature fusion (MMFF) and multi-scale fusion for visioin-based nutrition assessment.

Nutrition

GridMM: Grid Memory Map for Vision-and-Language Navigation

1 code implementation ICCV 2023 Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Shuqiang Jiang

Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments.

Navigate Vision and Language Navigation

Vision-Based Fruit Recognition via Multi-Scale Attention CNN

1 code implementation journal 2023 Weiqing Min, Zhiling Wang, Jiahao Yang, Chunlin Liu, Shuqiang Jiang

Fruit quality assessment, grading and sorting are of vital importance to fruit processing, and all these involve fruit recognition.

Layout-Based Causal Inference for Object Navigation

no code implementations CVPR 2023 Sixian Zhang, Xinhang Song, Weijie Li, Yubing Bai, Xinyao Yu, Shuqiang Jiang

The experience performs a positive effect on helping the agent infer the likely location of the goal when the layout gap between the unseen environments of the test and the prior knowledge obtained in training is minor.

Causal Inference Object

Bi-Level Meta-Learning for Few-Shot Domain Generalization

no code implementations CVPR 2023 Xiaorong Qin, Xinhang Song, Shuqiang Jiang

We address FSDG problem by meta-learning two levels of meta-knowledge, where the lower-level meta-knowledge are domain-specific embedding spaces as subspaces of a base space for intra-domain generalization, and the upper-level meta-knowledge is the base space and a prior subspace over domain-specific spaces for inter-domain generalization.

Domain Generalization Few-Shot Learning

Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint

1 code implementation CVPR 2023 Shikang Yu, Jiachen Chen, Hu Han, Shuqiang Jiang

Therefore, we propose mSARC to assure the student network can imitate not only the logit output but also the spatial activation region of the teacher network in order to alleviate the influence of unwanted noises in diverse synthetic images on distillation learning.

Data Augmentation Data-free Knowledge Distillation +1

Deep Learning for Logo Detection: A Survey

no code implementations10 Oct 2022 Sujuan Hou, Jiacheng Li, Weiqing Min, Qiang Hou, Yanna Zhao, Yuanjie Zheng, Shuqiang Jiang

When logos are increasingly created, logo detection has gradually become a research hotspot across many domains and tasks.

Hierarchical Object-to-Zone Graph for Object Navigation

1 code implementation ICCV 2021 Sixian Zhang, Xinhang Song, Yubing Bai, Weijie Li, Yakui Chu, Shuqiang Jiang

In this paper, we propose a hierarchical object-to-zone (HOZ) graph to guide the agent in a coarse-to-fine manner, and an online-learning mechanism is also proposed to update HOZ according to the real-time observation in new environments.

Object

Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection

1 code implementation31 Aug 2021 Baisong Zhang, Weiqing Min, Jing Wang, Sujuan Hou, Qiang Hou, Yuanjie Zheng, Shuqiang Jiang

Unlike general object detection, logo detection is a challenging task, especially for small logo objects and large aspect ratio logo objects in the real-world scenario.

Management object-detection +1

FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network

1 code implementation10 Aug 2021 Qiang Hou, Weiqing Min, Jing Wang, Sujuan Hou, Yuanjie Zheng, Shuqiang Jiang

For that, we propose a novel food logo detection method Multi-scale Feature Decoupling Network (MFDNet), which decouples classification and regression into two branches and focuses on the classification branch to solve the problem of distinguishing multiple food logo categories.

Food recommendation

A review on vision-based analysis for automatic dietary assessment

no code implementations6 Aug 2021 Wei Wang, Weiqing Min, TianHao Li, Xiaoxiao Dong, Haisheng Li, Shuqiang Jiang

We also provide the latest ideas for future development of VBDA, e. g., fine-grained food analysis and accurate volume estimation.

Food Recognition Nutrition

Applications of knowledge graphs for food science and industry

no code implementations13 Jul 2021 Weiqing Min, Chunlin Liu, Leyi Xu, Shuqiang Jiang

The deployment of various networks (e. g., Internet of Things [IoT] and mobile networks), databases (e. g., nutrition tables and food compositional databases), and social media (e. g., Instagram and Twitter) generates huge amounts of food data, which present researchers with an unprecedented opportunity to study various problems and applications in food science and industry via data-driven computational methods.

Data Visualization graph construction +4

Large Scale Visual Food Recognition

no code implementations30 Mar 2021 Weiqing Min, Zhiling Wang, Yuxin Liu, Mengjiang Luo, Liping Kang, Xiaoming Wei, Xiaolin Wei, Shuqiang Jiang

Food2K can be further explored to benefit more food-relevant tasks including emerging and more complex ones (e. g., nutritional understanding of food), and the trained models on Food2K can be expected as backbones to improve the performance of more food-relevant tasks.

Fine-Grained Visual Recognition Food Recognition +3

Dataset Bias in Few-shot Image Recognition

no code implementations18 Aug 2020 Shuqiang Jiang, Yaohui Zhu, Chenlong Liu, Xinhang Song, Xiang-Yang Li, Weiqing Min

Second, we investigate performance differences on different datasets from dataset structures and different few-shot learning methods.

Few-Shot Learning

ISIA Food-500: A Dataset for Large-Scale Food Recognition via Stacked Global-Local Attention Network

no code implementations13 Aug 2020 Weiqing Min, Linhu Liu, Zhiling Wang, Zhengdong Luo, Xiaoming Wei, Xiaolin Wei, Shuqiang Jiang

To encourage further progress in food recognition, we introduce the dataset ISIA Food- 500 with 500 categories from the list in the Wikipedia and 399, 726 images, a more comprehensive food dataset that surpasses existing popular benchmark datasets by category coverage and data volume.

Food Recognition Management

LogoDet-3K: A Large-Scale Image Dataset for Logo Detection

1 code implementation12 Aug 2020 Jing Wang, Weiqing Min, Sujuan Hou, Shengnan Ma, Yuanjie Zheng, Shuqiang Jiang

LogoDet-3K creates a more challenging benchmark for logo detection, for its higher comprehensive coverage and wider variety in both logo categories and annotated objects compared with existing datasets.

Management Object Detection +1

Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification

1 code implementation11 Nov 2019 Jing Wang, Weiqing Min, Sujuan Hou, Shengnan Ma, Yuanjie Zheng, Haishuai Wang, Shuqiang Jiang

Moreover, we propose a Discriminative Region Navigation and Augmentation Network (DRNA-Net), which is capable of discovering more informative logo regions and augmenting these image regions for logo classification.

Classification Data Augmentation +2

Scene Recognition with Prototype-agnostic Scene Layout

no code implementations7 Sep 2019 Gongwei Chen, Xinhang Song, Haitao Zeng, Shuqiang Jiang

Due to the large intra-class structural diversity, building and modeling flexible structural layout to adapt various image characteristics is a challenge.

Scene Recognition Semantic Similarity +1

Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition

no code implementations11 Jul 2019 Xiang-Yang Li, Luis Herranz, Shuqiang Jiang

In this paper, we introduce and systematically investigate several factors that influence the performance of fine-tuning for visual recognition.

Food Recommendation: Framework, Existing Solutions and Challenges

no code implementations15 May 2019 Weiqing Min, Shuqiang Jiang, Ramesh Jain

A growing proportion of the global population is becoming overweight or obese, leading to various diseases (e. g., diabetes, ischemic heart disease and even cancer) due to unhealthy eating patterns, such as increased intake of food with high energy and high fat.

Food recommendation Multimedia recommendation

Learning Effective RGB-D Representations for Scene Recognition

no code implementations17 Sep 2018 Xinhang Song, Shuqiang Jiang, Luis Herranz, Chengpeng Chen

We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scene.

Scene Recognition Video Recognition

A Survey on Food Computing

no code implementations22 Aug 2018 Weiqing Min, Shuqiang Jiang, Linhu Liu, Yong Rui, Ramesh Jain

This is the first comprehensive survey that targets the study of computing technology for the food area and also offers a collection of research studies and technologies to benefit researchers and practitioners working in different food-related fields.

Computers and Society Multimedia

Food recognition and recipe analysis: integrating visual content, context and external knowledge

no code implementations22 Jan 2018 Luis Herranz, Weiqing Min, Shuqiang Jiang

The central role of food in our individual and social life, combined with recent technological advances, has motivated a growing interest in applications that help to better monitor dietary habits as well as the exploration and retrieval of food-related information.

Food Recognition Food recommendation +1

Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs

1 code implementation21 Jan 2018 Xinhang Song, Luis Herranz, Shuqiang Jiang

However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features.

Scene Recognition

Scene recognition with CNNs: objects, scales and dataset bias

no code implementations CVPR 2016 Luis Herranz, Shuqiang Jiang, Xiang-Yang Li

Thus, adapting the feature extractor to each particular scale (i. e. scale-specific CNNs) is crucial to improve recognition, since the objects in the scenes have their specific range of scales.

Scene Recognition

Multi-level Discriminative Dictionary Learning towards Hierarchical Visual Categorization

no code implementations CVPR 2013 Li Shen, Shuhui Wang, Gang Sun, Shuqiang Jiang, Qingming Huang

For each internode of the hierarchical category structure, a discriminative dictionary and a set of classification models are learnt for visual categorization, and the dictionaries in different layers are learnt to exploit the discriminative visual properties of different granularity.

Dictionary Learning

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