activity
20162021
most citedOn the detection-to-track association for online multi-object tracking

44 citations · 47 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV202144 cited

On the detection-to-track association for online multi-object tracking

Xufeng Lin, Chang-Tsun Li, Victor Sanchez +1

Driven by recent advances in object detection with deep neural networks, the tracking-by-detection paradigm has gained increasing prevalence in the research community of multi-obje…

cs.CV20201 cited

Video Anomaly Detection by Estimating Likelihood of Representations

Yuqi Ouyang, Victor Sanchez

Video anomaly detection is a challenging task not only because it involves solving many sub-tasks such as motion representation, object localization and action recognition, but als…

cs.CV2020

Ensemble Network for Ranking Images Based on Visual Appeal

Sachin Singh, Victor Sanchez, Tanaya Guha

We propose a computational framework for ranking images (group photos in particular) taken at the same event within a short time span. The ranking is expected to correspond with hu…

cs.CV20201 cited

Multi-Camera Trajectory Forecasting: Pedestrian Trajectory Prediction in a Network of Cameras

Olly Styles, Tanaya Guha, Victor Sanchez +1

We introduce the task of multi-camera trajectory forecasting (MCTF), where the future trajectory of an object is predicted in a network of cameras. Prior works consider forecasting…

cs.CV2019

Multiple Object Forecasting: Predicting Future Object Locations in Diverse Environments

Olly Styles, Tanaya Guha, Victor Sanchez

This paper introduces the problem of multiple object forecasting (MOF), in which the goal is to predict future bounding boxes of tracked objects. In contrast to existing works on o…

cs.CV2019

Forecasting Pedestrian Trajectory with Machine-Annotated Training Data

Olly Styles, Arun Ross, Victor Sanchez

Reliable anticipation of pedestrian trajectory is imperative for the operation of autonomous vehicles and can significantly enhance the functionality of advanced driver assistance…