22 citations · 83 across the 41 of their papers we have counts for
15 papers · 1 filter
CoANeRV: Coordinate-Aware Token-Space Neural Video Representation
Jialong Guo, Ke Liu, Mengxuan Li +2
Neural representations for videos (NeRV) have shown strong reconstruction fidelity by storing video-specific information in network weights. However, existing formulations typicall…
CAER: Conflict-Aware Evidence Routing with Dual Prefix Experts for Multimodal Large Language Models
Zixuan Liu, Juntao Cai, Xiaoxu Cai +2
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in multimodal understanding and generation. However, when textual inputs conflict with visual evi…
Morphology-Aware Multimodal Representation Learning for Insect Phylogenetic Reconstruction
Zixuan Liu, Kaijie Yu, Chun He +5
Morphological traits provide important evidence for phylogenetic reconstruction and evolutionary relationship analysis. Recent image-based approaches have introduced deep learning,…
Deep Reprogramming Distillation for Medical Foundation Models
Siyuan Du, Yuhang Zhou, Haolin Li +5
Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scena…
Directed Ordinal Diffusion Regularization for Progression-Aware Diabetic Retinopathy Grading
Huangwei Chen, Junhao Jia, Ruocheng Li +7
Diabetic Retinopathy (DR) progresses as a continuous and irreversible deterioration of the retina, following a well-defined clinical trajectory from mild to severe stages. However,…
One Head Eight Arms: Block Matrix based Low Rank Adaptation for CLIP-based Few-Shot Learning
Chunpeng Zhou, Qianqian Shen, Zhi Yu +2
Recent advancements in fine-tuning Vision-Language Foundation Models (VLMs) have garnered significant attention for their effectiveness in downstream few-shot learning tasks.While…
MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal Guidance
Jialong Guo, Ke liu, Jiangchao Yao +3
Neural Representations for Videos (NeRV) has emerged as a promising implicit neural representation (INR) approach for video analysis, which represents videos as neural networks wit…
SAM-SP: Self-Prompting Makes SAM Great Again
Chunpeng Zhou, Kangjie Ning, Qianqian Shen +3
The recently introduced Segment Anything Model (SAM), a Visual Foundation Model (VFM), has demonstrated impressive capabilities in zero-shot segmentation tasks across diverse natur…
Attention Beats Linear for Fast Implicit Neural Representation Generation
Shuyi Zhang, Ke Liu, Jingjun Gu +4
Implicit Neural Representation (INR) has gained increasing popularity as a data representation method, serving as a prerequisite for innovative generation models. Unlike gradient-b…
Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis
Ke Liu, Feng Liu, Haishuai Wang +3
(INRs) aim to learn a (i.e., a neural network) to represent an image, where the input and output of the fu…
Multi-View Fusion and Distillation for Subgrade Distresses Detection based on 3D-GPR
Chunpeng Zhou, Kangjie Ning, Haishuai Wang +3
The application of 3D ground-penetrating radar (3D-GPR) for subgrade distress detection has gained widespread popularity. To enhance the efficiency and accuracy of detection, pione…
Hilbert Distillation for Cross-Dimensionality Networks
Dian Qin, Haishuai Wang, Zhe Liu +3
3D convolutional neural networks have revealed superior performance in processing volumetric data such as video and medical imaging. However, the competitive performance by leverag…
Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy
Jingru Li, Sheng Zhou, Liangcheng Li +3
Data-free knowledge distillation (DFKD) is a widely-used strategy for Knowledge Distillation (KD) whose training data is not available. It trains a lightweight student model with t…
Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
Ning Ma, Jiajun Bu, Zhen Zhang +1
Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not al…
Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification
Jing Wang, Weiqing Min, Sujuan Hou +4
Logo classification has gained increasing attention for its various applications, such as copyright infringement detection, product recommendation and contextual advertising. Compa…