3 citations · 4 across the 8 of their papers we have counts for
8 papers · 1 filter
Bridging the Intent Gap: Knowledge-Enhanced Visual Generation
Yi Cheng, Ziwei Xu, Dongyun Lin +5
For visual content generation, discrepancies between user intentions and the generated content have been a longstanding problem. This discrepancy arises from two main factors. Firs…
PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition
Dongyun Lin, Yi Cheng, Shangbo Mao +2
Large vision-language models have impressively promote the performance of 2D visual recognition under zero/few-shot scenarios. In this paper, we focus on exploiting the large visio…
Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering
Yi Cheng, Hehe Fan, Dongyun Lin +3
The main challenge in video question answering (VideoQA) is to capture and understand the complex spatial and temporal relations between objects based on given questions. Existing…
A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023
Yi Cheng, Ziwei Xu, Fen Fang +5
In this technical report, we present our findings from a study conducted on the EPIC-KITCHENS-100 Unsupervised Domain Adaptation task for Action Recognition. Our research focuses o…
SCA-PVNet: Self-and-Cross Attention Based Aggregation of Point Cloud and Multi-View for 3D Object Retrieval
Dongyun Lin, Yi Cheng, Aiyuan Guo +2
To address 3D object retrieval, substantial efforts have been made to generate highly discriminative descriptors of 3D objects represented by a single modality, e.g., voxels, point…
Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022
Yi Cheng, Dongyun Lin, Fen Fang +3
In this report, we present the technical details of our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition 2022. This task ai…
DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
Dongyun Lin, Yiqun Li, Shudong Xie +2
One pivot challenge for image anomaly (AD) detection is to learn discriminative information only from normal class training images. Most image reconstruction based AD methods rely…
Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation
Dongyun Lin, Yanpeng Cao, Wenbing Zhu +1
In industrial product quality assessment, it is essential to determine whether a product is defect-free and further analyze the severity of anomality. To this end, accurate defect…