activity
20172026
most citedSingle Shot Text Detector with Regional Attention

58 citations · 86 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection

Yuang Geng, Junkai Zhou, Kang Yang +5

In this paper, we address the challenging problem of single-scene, fully unsupervised video anomaly detection (VAD), where raw videos containing both normal and abnormal events are…

cs.CV2022

Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions

Pan He, Patrick Emami, Sanjay Ranka +1

In this paper, we present a new self-supervised scene flow estimation approach for a pair of consecutive point clouds. The key idea of our approach is to represent discrete point c…

cs.CV20213 cited

Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations

Patrick Emami, Pan He, Sanjay Ranka +1

Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that met…

cs.CV2020

SparsePipe: Parallel Deep Learning for 3D Point Clouds

Keke Zhai, Pan He, Tania Banerjee +2

We propose SparsePipe, an efficient and asynchronous parallelism approach for handling 3D point clouds with multi-GPU training. SparsePipe is built to support 3D sparse data such a…

cs.CV201925 cited

Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video

Xiaohui Huang, Pan He, Anand Rangarajan +1

In Intelligent Transportation System, real-time systems that monitor and analyze road users become increasingly critical as we march toward the smart city era. Vision-based framewo…

cs.CV2018

Adaptive Adversarial Attack on Scene Text Recognition

Xiaoyong Yuan, Pan He, Xiaolin Andy Li +1

Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles…