48 citations · 55 across the 10 of their papers we have counts for
10 papers
Set-Valued Transformer Network for High-Emission Mobile Source Identification
Yunning Cao, Lihong Pei, Jian Guo +3
Identifying high-emission vehicles is a crucial step in regulating urban pollution levels and formulating traffic emission reduction strategies. However, in practical monitoring da…
Scale-Disentangled spatiotemporal Modeling for Long-term Traffic Emission Forecasting
Yan Wu, Lihong Pei, Yukai Han +3
Long-term traffic emission forecasting is crucial for the comprehensive management of urban air pollution. Traditional forecasting methods typically construct spatiotemporal graph…
Learning Multi-view Multi-class Anomaly Detection
Qianzi Yu, Yang Cao, Yu Kang
The latest trend in anomaly detection is to train a unified model instead of training a separate model for each category. However, existing multi-class anomaly detection (MCAD) mod…
VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
Huilin Deng, Hongchen Luo, Wei Zhai +2
Zero-shot anomaly detection (ZSAD) recognizes and localizes anomalies in previously unseen objects by establishing feature mapping between textual prompts and inspection images, de…
PEAR: Phrase-Based Hand-Object Interaction Anticipation
Zichen Zhang, Hongchen Luo, Wei Zhai +2
First-person hand-object interaction anticipation aims to predict the interaction process over a forthcoming period based on current scenes and prompts. This capability is crucial…
Bidirectional Progressive Transformer for Interaction Intention Anticipation
Zichen Zhang, Hongchen Luo, Wei Zhai +2
Interaction intention anticipation aims to jointly predict future hand trajectories and interaction hotspots. Existing research often treated trajectory forecasting and interaction…
Benchmarking General-Purpose In-Context Learning
Fan Wang, Chuan Lin, Yang Cao +1
In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly, without relying on any artificially crafted optimization technique…
E-MLB: Multilevel Benchmark for Event-Based Camera Denoising
Saizhe Ding, Jinze Chen, Yang Wang +4
Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and lo…
Phrase-Based Affordance Detection via Cyclic Bilateral Interaction
Liangsheng Lu, Wei Zhai, Hongchen Luo +2
Affordance detection, which refers to perceiving objects with potential action possibilities in images, is a challenging task since the possible affordance depends on the person's…
Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning
Fan Wang, Hao Tian, Haoyi Xiong +5
Artificial neural networks (ANNs) are typically confined to accomplishing pre-defined tasks by learning a set of static parameters. In contrast, biological neural networks (BNNs) c…