Author name cluster

Chenglong Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

YNIMG Journal 2025 Journal Article

Associations among microbial enterotype, brain structure, and working memory: A combined structural and diffusion MRI study

Zhonghao Rao
Yu Shi
Min She
Chenglong Liu
Jiajia Zhu
Yongqiang Yu

BACKGROUND: Enterotype analysis classifies individuals based on gut microbial community composition using clustering techniques. Despite evidence suggesting the important role of enterotype in affecting brain function and working memory, little is known about the brain structural substrates. METHODS: We collected fecal samples and utilized 16S rDNA amplicon sequencing to identify three enterotypes (Bacteroides, Prevotella, and Ruminococcaceae) among 511 healthy young adults through unsupervised clustering. Structural and diffusion MRI techniques were adopted to assess gray matter morphology and white matter integrity. Inter-enterotype differences in brain structure were tested, followed by correlation and mediation analyses to investigate the potential relationships among enterotype, brain structure, and working memory. RESULTS: The three enterotypes exhibited significant differences in cortical thickness of the prefrontal cortex and mean diffusivity of the cerebral peduncle and cingulum. Moreover, prefrontal cortical thickness was correlated with working memory and further acted as a significant mediator of the association between enterotype and working memory. CONCLUSIONS: Our findings may contribute to the growing literature on the microbiota-brain-cognition relationship, setting the stage for future longitudinal and interventional research.

Details DOI

ECAI Conference 2024 Conference Paper

Detecting Objects as Cascade Corners

Chenglong Liu
Jintao Liu
Haorao Wei
Jinze Yang
Liangyu Xu
Yuchen Guo
Lu Fang 0001

The corner-based detection paradigm enjoys the potential to produce high-quality boxes. But the development is constrained by three factors: 1) Hard to match corners. Heuristic corner matching algorithms can lead to incorrect boxes, especially when similar-looking objects co-occur. 2) Poor instance context. Two separate corners preserve few instance semantics, so it is difficult to guarantee getting both two class-specific corners on the same heatmap channel. 3) Unfriendly backbone. The training cost of the hourglass network is high. Accordingly, we build a novel corner-based framework, named Corner2Net. To achieve the corner-matching-free manner, we devise the cascade corner pipeline which progressively predicts the associated corner pair in two steps instead of synchronously searching two independent corners via parallel heads. Corner2Net decouples corner localization and object classification. Both two corners are class-agnostic and the instance-specific bottom-right corner further simplifies its search space. Meanwhile, RoI features with rich semantics are extracted for classification. Popular backbones (e. g. , ResNeXt) can be easily connected to Corner2Net. Experimental results on COCO show Corner2Net surpasses all existing corner-based detectors by a large margin in accuracy and speed.

Details

AAAI Conference 2024 Conference Paper

GigaHumanDet: Exploring Full-Body Detection on Gigapixel-Level Images

Chenglong Liu
Haoran Wei
Jinze Yang
Jintao Liu
Wenxi Li
Yuchen Guo
Lu Fang

Performing person detection in super-high-resolution images has been a challenging task. For such a task, modern detectors, which usually encode a box using center and width/height, struggle with accuracy due to two factors: 1) Human characteristic: people come in various postures and the center with high freedom is difficult to capture robust visual pattern; 2) Image characteristic: due to vast scale diversity of input (gigapixel-level), distance regression (for width and height) is hard to pinpoint, especially for a person, with substantial scale, who is near the camera. To address these challenges, we propose GigaHumanDet, an innovative solution aimed at further enhancing detection accuracy for gigapixel-level images. GigaHumanDet employs the corner modeling method to avoid the potential issues of a high degree of freedom in center pinpointing. To better distinguish similar-looking persons and enforce instance consistency of corner pairs, an instance-guided learning approach is designed to capture discriminative individual semantics. Further, we devise reliable shape-aware bodyness equipped with a multi-precision strategy as the human corner matching guidance to be appropriately adapted to the single-view large scene. Experimental results on PANDA and STCrowd datasets show the superiority and strong applicability of our design. Notably, our model achieves 82.4% in term of AP, outperforming current state-of-the-arts by more than 10%.

PDF Details DOI

ECAI Conference 2024 Conference Paper

Multi-View Prompt for Fine-Grained Multimodal Named Entity Recognition and Grounding

Jintao Liu
Chenglong Liu
Kaiwen Wei

Fine-Grained Multimodal Named Entity Recognition and Grounding (FMNERG) aims to extract entity name, fine-grained entity type, and its corresponding object from paired text and image. This task demands fundamental reasoning capability for complex language and multimodal comprehension. Despite encouraging results, existing methods face two critical issues: (1) Insufficient knowledge of the entity poses challenges to fine-grained entity recognition; (2) Limited correlations between entities and objects hinder the visual grounding of entities. To tackle these issues, we propose a Multi-View Prompt (MVP) method for the FMNERG task in this paper, which collaborates with Large Language Models (LLMs) and Visual Grounding Models (VGMs) for reasoning. Concretely, MVP constructs a knowledgeable prompt in a chain-of-thought format, progressively refining possible entity types from coarse-grained to fine-grained levels. It leverages a heuristic method to select demonstration examples, which could provide guiding knowledge about entities from LLMs. To establish correlations between entities and potential objects, MVP introduces a grounded prompt that exploits information from guiding knowledge and image caption, enabling VGMs to detect related objects. Experimental results indicate that MVP achieves state-of-the-art performance on the Twitter dataset.

Details

AAAI Conference 2024 Conference Paper

Multimodal Event Causality Reasoning with Scene Graph Enhanced Interaction Network

Jintao Liu
Kaiwen Wei
Chenglong Liu

Multimodal event causality reasoning aims to recognize the causal relations based on the given events and accompanying image pairs, requiring the model to have a comprehensive grasp of visual and textual information. However, existing studies fail to effectively model the relations of the objects within the image and capture the object interactions across the image pair, resulting in an insufficient understanding of visual information by the model. To address these issues, we propose a Scene Graph Enhanced Interaction Network (SEIN) in this paper, which can leverage the interactions of the generated scene graph for multimodal event causality reasoning. Specifically, the proposed method adopts a graph convolutional network to model the objects and their relations derived from the scene graph structure, empowering the model to exploit the rich structural and semantic information in the image adequately. To capture the object interactions between the two images, we design an optimal transport-based alignment strategy to match the objects across the images, which could help the model recognize changes in visual information and facilitate causality reasoning. In addition, we introduce a cross-modal fusion module to combine textual and visual features for causality prediction. Experimental results indicate that the proposed SEIN outperforms state-of-the-art methods on the Vis-Causal dataset.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Corner Affinity: A Robust Grouping Algorithm to Make Corner-guided Detector Great Again

Haoran Wei
Chenglong Liu
Ping Guo
Yangguang Zhu
Jiamei Fu
Bing Wang
Peng Wang

Corner-guided detector enjoys potential ability to yield precise bounding boxes. However, unreliable corner pairs, generated by heuristic grouping guidance, hinder the development of this detector. In this paper, we propose a novel corner grouping algorithm, termed as Corner Affinity, to significantly boost the reliability and robustness of corner grouping. The proposed Corner Affinity is a couple of two interactional factors, namely, 1) the structure affinity (SA), applying to generate preliminary corner pairs through the corresponding object's shallow construction information. 2) the contexts affinity (CA), running as optimizing corner pairs via embedding deeper semantic features of affiliated instances. Equipped with the Corner Affinity, a detector can produce high-quality bounding boxes upon preferable paired corner keypoints. Experimental results show the superiority of our design on multiple benchmark datasets. Specifically, for CornerNet baseline, the proposed Corner Affinity brings AP boostings of 5. 8% on COCO, 35. 8% on Citypersons, and 17. 2% on UCAS-AOD without bells and whistles.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

HumanLiker: A Human-like Object Detector to Model the Manual Labeling Process

Haoran Wei
Ping Guo
Yangguang Zhu
Chenglong Liu
Peng Wang

Popular object detection models generate bounding boxes in a different way than we humans. As an example, modern detectors yield object box either upon the regression of its center and width/height (center-guided detector), or by grouping paired estimated corners (corner-guided detector). However, that is not the pattern we manually label an object due to high degrees of freedom in searching centers or low efficiency of grouping corners. Empirically, humans run two steps to locate an object bounding box manually: 1) click the mouse at the top-left corner of object, and then drag the mouse to the bottom-right corner; 2) refine the corner positions to make the bounding box more precisely, if necessary. Inspired by this manual labeling process, we propose a novel human-like detector, termed as HumanLiker, which is devised as a two-stage end-to-end detector to simulate the two aforementioned. Like we humans in manual labeling, HumanLiker can effectively avert both the thorny center searching and heuristic corner grouping. Different from the mainstream detector branches, i. e. , the center/corner-guided methods, the HumanLiker provides a new paradigm which integrates the advantages of both branches to balance the detection efficiency and bounding box quality. On MS-COCO test-dev set, HumanLiker can achieve 50. 2%/51. 6% and 53. 8%/55. 6% in term of AP with ResNeXt-101 and SwinTransformer backbones in single/multi-scale testing, outperforming current popular center/corner-guided baselines (e. g. , DETR/CornerNet) by a large margin, with much less training epochs and higher inference FPS. Code will be available soon.

PDF Details

YNICL Journal 2015 Journal Article

Reduced neural specificity in middle-aged HIV+ women in the absence of behavioral deficits

Chenglong Liu
Cuiwei Wang
Matthew Leclair
Mary Young
Xiong Jiang

In the post combination antiretroviral therapy (cART) era, the prevalence of mild forms of HIV-associated neurocognitive disorders (HAND) in individuals with HIV-infection remains high. There is a pressing need to find biomarkers that can aid clinical assessment of HAND, especially in those with mild or no neurocognitive symptoms. Here we hypothesized that a reduction in neural specificity, or the specificity of neuronal tuning, could serve as a potential biomarker of asymptomatic HAND. To directly test this hypothesis, we applied two advanced fMRI techniques to examine the difference in neural specificity between middle-aged HIV+ women and age-matched negative controls, with a focus on the fusiform face area (FFA), a critical region in face processing. Face discrimination performance was assessed outside of the scanner. While the behavioral performance of face discrimination was comparable between the two groups, a reduced neural specificity in the FFA of HIV-positive women was revealed by a novel fMRI analysis technique, local regional heterogeneity analysis, or Hcorr , as well as an established technique, fMRI-rapid adaptation. In contrast, conventional fMRI techniques were insensitive to these early changes. These results suggest that, prior to the onset of detectable behavioral deficits, significant neuronal dysfunctions are already present in HIV+ individuals, and these early neuronal dysfunctions can be detected and assessed via neural specificity, which, in combining with the novel Hcorr technique, has a strong potential to serve as a biomarker of asymptomatic HAND and other neurodegenerative diseases.

Details DOI