Seq-NMS for Video Object Detection

by   Wei Han, et al.
National University of Singapore

Video object detection is challenging because objects that are easily detected in one frame may be difficult to detect in another frame within the same clip. Recently, there have been major advances for doing object detection in a single image. These methods typically contain three phases: (i) object proposal generation (ii) object classification and (iii) post-processing. We propose a modification of the post-processing phase that uses high-scoring object detections from nearby frames to boost scores of weaker detections within the same clip. We show that our method obtains superior results to state-of-the-art single image object detection techniques. Our method placed 3rd in the video object detection (VID) task of the ImageNet Large Scale Visual Recognition Challenge 2015 (ILSVRC2015).


page 2

page 3

page 6

page 7

page 8


Object Detection in Video with Spatial-temporal Context Aggregation

Recent cutting-edge feature aggregation paradigms for video object detec...

Robust and efficient post-processing for video object detection

Object recognition in video is an important task for plenty of applicati...

Issues in Object Detection in Videos using Common Single-Image CNNs

A growing branch of computer vision is object detection. Object detectio...

Object sieving and morphological closing to reduce false detections in wide-area aerial imagery

For object detection in wide-area aerial imagery, post-processing is usu...

Detection Selection Algorithm: A Likelihood based Optimization Method to Perform Post Processing for Object Detection

In object detection, post-processing methods like Non-maximum Suppressio...

Priming Neural Networks

Visual priming is known to affect the human visual system to allow detec...

Detect to Track and Track to Detect

Recent approaches for high accuracy detection and tracking of object cat...

Code Repositories


Object Tracking in Tensorflow ( Localization Detection Classification ) developed to partecipate to ImageNET VID competition

view repo

Please sign up or login with your details

Forgot password? Click here to reset