91 citations · 158 across the 30 of their papers we have counts for
31 papers
Embodied AI for Scientific Discovery: From Physical Action to Scientific Evidence
Wenhao Xu, Changwei Wang, Shunpeng Chen +6
Scientific experiments are increasingly selected, executed and interpreted by learned systems that act through physical interfaces. Robot learning builds physical competence, where…
Close Shortcut Wins Long: Seeking Diverse and Stable Generators for Data-Free Knowledge Distillation
Kailin Lyu, Zherui Zhang, Junhao Dong +11
Data-Free Knowledge Distillation (DFKD) preserves privacy by transferring knowledge without real data access. However, existing generator-based DFKD methods suffer from over-relian…
DialogueVPR: Towards Conversational Visual Place Recognition
Yukun Song, Changwei Wang, Xingtian Pei +8
Inspired by how humans communicate spatial information, language-guided geo-localization has gained significant traction for its intuitive and practical value. Despite this progres…
DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval
Xingtian Pei, Yukun Song, Changwei Wang +4
Composed Image Retrieval (CIR) requires both preserving the visual continuity of the reference image and faithfully executing the semantic variables specified in the modification t…
Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition
Shunpeng Chen, Yukun Song, Changwei Wang +6
Visual Place Recognition (VPR) determines a query image's geographic location by matching it against geotagged databases. However, existing methods struggle with perceptual aliasin…
LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
Zhe Feng, Sen Lian, Changwei Wang +5
The quadratic complexity of softmax attention presents a major obstacle for scaling Transformers to high-resolution vision tasks. Existing linear attention variants often replace t…
HMR-1: Hierarchical Massage Robot with Vision-Language-Model for Embodied Healthcare
Rongtao Xu, Mingming Yu, Xiaofeng Han +7
The rapid advancement of Embodied Intelligence has opened transformative opportunities in healthcare, particularly in physical therapy and rehabilitation. However, critical challen…
MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation
Run Ling, Ke Cao, Jian Lu +15
Multi-subject video generation aims to synthesize videos from textual prompts and multiple reference images, ensuring that each subject preserves natural scale and visual fidelity.…
Explicit Temporal-Semantic Modeling for Dense Video Captioning via Context-Aware Cross-Modal Interaction
Mingda Jia, Weiliang Meng, Zenghuang Fu +7
Dense video captioning jointly localizes and captions salient events in untrimmed videos. Recent methods primarily focus on leveraging additional prior knowledge and advanced multi…
Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion
Rongtao Xu, Jinzhou Lin, Jialei Zhou +6
Camera-based occupancy prediction is a mainstream approach for 3D perception in autonomous driving, aiming to infer complete 3D scene geometry and semantics from 2D images. Almost…
CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion
Jinzhou Lin, Jie Zhou, Wenhao Xu +7
Semantic Scene Completion (SSC) aims to infer complete 3D geometry and semantics from monocular images, serving as a crucial capability for camera-based perception in autonomous dr…
SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition
Shunpeng Chen, Changwei Wang, Rongtao Xu +7
Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fin…
3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering
Rongtao Xu, Han Gao, Mingming Yu +6
With the growing need for diverse and scalable data in indoor scene tasks, such as question answering and dense captioning, we propose 3D-MoRe, a novel paradigm designed to generat…
SAMamba: Adaptive State Space Modeling with Hierarchical Vision for Infrared Small Target Detection
Wenhao Xu, Shuchen Zheng, Changwei Wang +4
Infrared small target detection (ISTD) is vital for long-range surveillance in military, maritime, and early warning applications. ISTD is challenged by targets occupying less than…
FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models Adaptation
Zherui Zhang, Jiaxin Wu, Changwei Wang +6
Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain ex…
Image Recognition with Online Lightweight Vision Transformer: A Survey
Zherui Zhang, Rongtao Xu, Jie Zhou +8
The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networ…
CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation
Zherui Zhang, Changwei Wang, Rongtao Xu +4
Data-Free Knowledge Distillation (DFKD) enables the knowledge transfer from the given pre-trained teacher network to the target student model without access to the real training da…
Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition
Changwei Wang, Shunpeng Chen, Yukun Song +11
Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local re…
Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision
Xiaofeng Han, Shunpeng Chen, Zenghuang Fu +9
Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically revie…
SkinFormer: Learning Statistical Texture Representation with Transformer for Skin Lesion Segmentation
Rongtao Xu, Changwei Wang, Jiguang Zhang +3
Accurate skin lesion segmentation from dermoscopic images is of great importance for skin cancer diagnosis. However, automatic segmentation of melanoma remains a challenging task b…
PSTNet: Enhanced Polyp Segmentation with Multi-scale Alignment and Frequency Domain Integration
Wenhao Xu, Rongtao Xu, Changwei Wang +3
Accurate segmentation of colorectal polyps in colonoscopy images is crucial for effective diagnosis and management of colorectal cancer (CRC). However, current deep learning-based…
Generalization Boosted Adapter for Open-Vocabulary Segmentation
Wenhao Xu, Changwei Wang, Xuxiang Feng +5
Vision-language models (VLMs) have demonstrated remarkable open-vocabulary object recognition capabilities, motivating their adaptation for dense prediction tasks like segmentation…
HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object Detection
Shibiao Xu, ShuChen Zheng, Wenhao Xu +6
Infrared small object detection is an important computer vision task involving the recognition and localization of tiny objects in infrared images, which usually contain only a few…
Local Feature Matching Using Deep Learning: A Survey
Shibiao Xu, Shunpeng Chen, Rongtao Xu +3
Local feature matching enjoys wide-ranging applications in the realm of computer vision, encompassing domains such as image retrieval, 3D reconstruction, and object recognition. Ho…