2026 顶会论文
11作者位次 #5/5ECCV 2026Poster
Adversarial Score Distillation for Stable One-Step Diffusion in Real-World Image Super-Resolution
Wei Zhu · Kai Zhang · Yu Zheng · Lei Luo · Jian Yang
多模态安全强化学习与后训练Low-Level Vision, Restoration & Generative PriorsOpenReview 作者位次 #5/5ECCV 2026Poster
DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies
renke wang · zhenyu zhang · Ying Tai · Jun Li · Jian Yang
多模态社会与人本Video Generation, Avatars & Dynamic WorldsOpenReview 作者位次 #4/4ECCV 2026Poster
Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalities
Jindi Bao · Jianjun Qian · Mengkai Yan · Jian Yang
可解释性多模态Open-World Recognition, Segmentation & TransferOpenReview 作者位次 #6/6ECCV 2026Poster
OrthoTailor: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation
Zhaotong Yang · Ying Tai · Jiahui Zhan · Yu Zheng · Jianjun Qian · Jian Yang
安全效率与系统Federated, Continual & Efficient Learning; Model SecurityOpenReview 作者位次 #2/3ECCV 2026Poster
Enhancing Interpretability in CLIP with Optimal Transport-based Submodular Optimization for Ophthalmic Imaging
Sihong Lu · Jian Yang · Lei Luo
多模态可解释性Multimodal, Video & Document UnderstandingOpenReview 作者位次 #4/5ECCV 2026Poster
M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection
Chao Wang · Wei Lu · Xiang Li · Jian Yang · Lei Luo
评测与基准数据与预训练Recognition, Tracking, Re-ID & Anomaly DetectionOpenReview 作者位次 #3/3ECCV 2026Poster
IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation
Chaoyi Shi · Shanshan Zhang · Jian Yang
安全Recognition, Tracking, Re-ID & Anomaly DetectionOpenReview 作者位次 #6/6ECCV 2026Poster
PASDiff: Physics-Aware Semantic Guidance for Joint Real-world Low-Light Face Enhancement and Restoration
Yilin Ni · Wenjie Li · Zhengxue Wang · Juncheng Li · Guangwei Gao · Jian Yang
多模态Video Generation, Avatars & Dynamic WorldsOpenReview 作者位次 #3/3CVPR 2026Poster· Computer Vision & Pattern Recognition
CrossHOI: Learning Cross-View Representations for Monocular 3D Human-Object Interaction Reconstruction
Pei Geng · Shanshan Zhang · Jian Yang
作者位次 #3/3CVPR 2026Poster· Computer Vision & Pattern Recognition
Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors
Mingqian Ji · Shanshan Zhang · Jian Yang
作者位次 #4/4CVPR 2026Poster· Computer Vision & Pattern Recognition
FSLoRA: Harmonizing Detection and Re-Identification via Freq-Spatial Low-Rank Adapter for One-Stage Person Search
Yanling Tian · Shanshan Zhang · Di Chen · Jian Yang