Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/4ECCV 2026Poster

LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models

Arpita Nema · Hanwei Zhu · Xi Zhang · Weisi Lin

多模态评测与基准Vision-Language Models & Foundation ModelsOpenReview

作者位次 #5/5ECCV 2026Poster

BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment

Shilv Cai · Jian Jin · Tianang Chen · Zhuangzi Li · Weisi Lin

多模态社会与人本Computational Imaging, Medical & Scientific VisionOpenReview

作者位次 #8/8ECCV 2026Poster

BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion

Wang Mark · Kaixin Xu · Xue Geng · Fen Fang · Mohamed Aly · Xulei Yang · Min Wu · Weisi Lin

推理可解释性多模态Vision Foundation Models: Interpretability and ReasoningOpenReview

作者位次 #6/7ECCV 2026Poster

HiChor: Hierarchical Choreography Generation from Pop Music with Choreographic Primitives

Jungsu Kim · Jungwoo Huh · Jeongwook Choi · Wen-Huang Cheng · Jian-Yu Jiang-Lin · Weisi Lin · Sanghoon Lee

多模态Video Generation, Avatars & Dynamic WorldsOpenReview

作者位次 #5/5ECCV 2026Poster

Enhancing prompt-image alignment evaluations via cyclic mutual information maximization

Xingran Liao · Duanyu Feng · Mingliang Zhou · Sam Kwong · Weisi Lin

对齐与偏好多模态评测与基准Open-World Recognition, Segmentation & TransferOpenReview

作者位次 #5/5CVPR 2026Poster· Computer Vision & Pattern Recognition

QD-PCQA: Quality-Aware Domain Adaptation for Point Cloud Quality Assessment

Guohua Zhang · Jian Jin · Meiqin Liu · Chao Yao · Weisi Lin

多模态OpenReview 项目页

作者位次 #4/4CVPR 2026Poster· Computer Vision & Pattern Recognition

R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment

Zhuangzi Li · Jian Jin · Shilv Cai · Weisi Lin

多模态检索与知识OpenReview 项目页

作者位次 #4/5ICRA 2026Oral· Robotics & Automation

MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping

Heng Zhang · Kevin Yuchen Ma · Mike Zheng Shou · Weisi Lin · Yan Wu

OpenReview

作者位次 #4/5AAAI 2026Poster· Artificial Intelligence

DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video

Jeonghaeng Lee · Seokkeun Choi · Zhixuan Li · Weisi Lin · Sanghoon Lee

对齐与偏好多模态OpenReview

作者位次 #4/4AAAI 2026Poster· Artificial Intelligence

Nighttime Flare Removal via Wavelet-Guided and Gated-Enhanced Spatial-Frequency Fusion Network

Yun Liu · Guang Yang · Tao Li · Weisi Lin