From the 10 of 311 papers with an AI index.
53 citations
- Peking UniversityCN92 papers
- University of Science and Technology of ChinaCN92 papers
- Tsinghua UniversityCN88 papers
- Carnegie Mellon UniversityUS80 papers
- South China Normal UniversityCN79 papers
- Institute of Modern PhysicsCN78 papers
- University of BristolGB78 papers
- University of TurinIT78 papers
- Beihang UniversityCN77 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT77 papers
- Nanjing Normal UniversityCN77 papers
- National Centre for Nuclear ResearchPL77 papers
21 papers · 1 filter
MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding
Kun Li, Dan Guo, Jihao Gu +6
Micro-Actions (MAs) are subtle and spontaneous human behaviors that provide important non-verbal cues in social interaction and affective communication. However, their short durati…
Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing
Wanglong Lu, Lingming Su, Kaijie Shi +4
Recent diffusion-based generative models have shown impressive performance in image generation and editing. However, due to memory limitations and the high cost of collecting high-…
Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning
Ji Cao, Yu Wang, Tongya Zheng +6
Trajectory representation learning (TRL) aims to encode raw trajectory data into low-dimensional embeddings for downstream tasks such as travel time estimation, mobility prediction…
Flow6D: Discrete-to-Continuous Flow Matching for Efficient and Accurate Category-Level 6D Pose Estimation
Mingyu Mei, Li Zhang, Zibo Dai +4
6D pose estimation is a key task in computer vision and embodied AI, widely used in robotic manipulation, augmented reality, etc. Existing methods directly regress in a high-dimens…
DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark
Ruofan Hu, Menghui Zhu, Jieming Zhu +8
Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual e…
Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations
Ruoxi Guo, Huaijin Pi, Zehong Shen +8
Text-driven human motion synthesis has showcased its potential for revolutionizing motion design in the movie and game industry. Existing methods often rely on 3D motion capture da…