25.8k citations
- Tsinghua UniversityCN93 papers
- Peking UniversityCN92 papers
- State Key Laboratory of Networking and Switching Technology83 papers
- Chinese Academy of SciencesCN64 papers
- State Key Laboratory of Information Photonics and Optical Communications46 papers
- Beijing Normal UniversityCN44 papers
- Queen Mary University of LondonGB43 papers
- University of SouthamptonGB32 papers
- Beihang UniversityCN30 papers
- University of Chinese Academy of SciencesCN28 papers
- Beijing Institute of TechnologyCN27 papers
- University of Technology SydneyAU26 papers
182 papers · 1 filter
Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision
Weijian Jian, Xiaoyue Zhang, Bin Xiao +5
The Segment Anything Model (SAM) relies heavily on massive manual annotations, creating a fundamental bottleneck for model scaling. While unsupervised methods attempt to learn obje…
MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis
Di Dai, Bo Liu, Youcheng Li +9
Mammography is an essential tool for breast cancer detection, with millions of examinations conducted annually. However, publicly available high-quality mammography datasets for AI…
TriDP-PTM: a three-stage distortion-perception tradeoff guides the pre-training model for radar cardiac sensing
Jinye Li, Aidong Men, Yang Liu +1
Cardiovascular diseases (CVDs) remain a leading cause of death globally, necessitating continuous, accurate non-invasive cardiac monitoring. While non-contact radar-based approache…
High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation
Tongyu Yang, Heng Guo, Yasuyuki Matsushita +3
Previous multi-view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrins…
Affinity Contrastive Learning for Skeleton-based Human Activity Understanding
Hongda Liu, Yunfan Liu, Min Ren +3
In skeleton-based human activity understanding, existing methods often adopt the contrastive learning paradigm to construct a discriminative feature space. However, many of these a…
FinMMDocR: Benchmarking Financial Multimodal Reasoning with Scenario Awareness, Document Understanding, and Multi-Step Computation
Zichen Tang, Haihong E, Rongjin Li +18
We introduce FinMMDocR, a novel bilingual multimodal benchmark for evaluating multimodal large language models (MLLMs) on real-world financial numerical reasoning. Compared to exis…