activity
20172022
most citedFCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras

24 citations · 24 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2023

ParGANDA: Making Synthetic Pedestrians A Reality For Object Detection

Daria Reshetova, Guanhang Wu, Marcel Puyat +2

Object detection is the key technique to a number of Computer Vision applications, but it often requires large amounts of annotated data to achieve decent results. Moreover, for pe…

cs.CV2022

TDT: Teaching Detectors to Track without Fully Annotated Videos

Shuzhi Yu, Guanhang Wu, Chunhui Gu +1

Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art r…

cs.CV2021

Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts

Kunpeng Li, Zizhao Zhang, Guanhang Wu +5

Learning visual knowledge from massive weakly-labeled web videos has attracted growing research interests thanks to the large corpus of easily accessible video data on the Internet…

cs.CV2019

Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection

Sara Beery, Guanhang Wu, Vivek Rathod +2

In static monitoring cameras, useful contextual information can stretch far beyond the few seconds typical video understanding models might see: subjects may exhibit similar behavi…

cs.CV201724 cited

FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras

Shanghang Zhang, Guanhang Wu, João P. Costeira +1

In this paper, we develop deep spatio-temporal neural networks to sequentially count vehicles from low quality videos captured by city cameras (citycams). Citycam videos have low r…