Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-2

Boundary Detection

3260 papers • 126 benchmarks • 313 datasets

Boundary Detection is a vital part of extracting information encoded in images, allowing for the computation of quantities of interest including density, velocity, pressure, etc. Source: A Locally Adapting Technique for Boundary Detection using Image Segmentation

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in boundary-detection-2

Trend

Dataset

Best Model

Actions

Kinetics-400

Kinetics-400

NYU-Depth V2

NYU-Depth V2

PASCAL Context

PASCAL Context

Libraries

i

Use these libraries to find boundary-detection-2 models and implementations

soCzech/TransNetV2

3 papers 336

Datasets

Kinetics

NYUv2

Kinetics 400

PASCAL Context

SoccerNet-v2

MDBD

Subtasks

Junction Detection

Most implemented papers

Holistically-Nested Edge Detection

Saining Xie, Z. Tu•Wed Apr 22 2015

HED performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets, and automatically learns rich hierarchical representations that are important in order to resolve the challenging ambiguity in edge and object boundary detection.

3725

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

petteriTeikari/vesselNN

2 papers 12

UruDendro

UruDendro

Contour Drawing Dataset

Contour Drawing Dataset

CaFFe

Oxford Road Boundaries

Oxford Road Boundaries

0

Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks

Michael Gygli•Mon May 22 2017

This work proposes a Convolutional Neural Network (CNN) which is fully convolutional in time, thus allowing to use a large temporal context without the need to repeatedly processing frames.

78 0

Deeply Supervised Salient Object Detection with Short Connections

Philip H. S. Torr, Z. Tu, Ming-Ming Cheng, A. Borji, Qibin Hou, Xiaowei Hu•Mon Nov 14 2016

This paper proposes a new salient object detection method by introducing short connections to the skip-layer structures within the HED architecture, which takes full advantage of multi-level and multi-scale features extracted from FCNs, providing more advanced representations at each layer, a property that is critically needed to perform segment detection.

1411 0

Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks

W. Matusik, Mohamed A. Elgharib, Ahmed Hassanien, Ahmed A. S. Seleim, M. Hefeeda•Mon May 08 2017

This work presents an SBD technique based on spatio-temporal Convolutional Neural Networks, and performs the largest evaluation to date for one SBD algorithm, on real and synthetic data, containing more than 4.85 million frames.

55 0

TransNet: A deep network for fast detection of common shot transitions

Tomás Soucek, Jaroslav Moravec, Jakub Lokoč•Fri Jun 07 2019

A simple modular convolutional neural network architecture that achieves state-of-the-art results on the RAI dataset with well above real-time inference speed even on a single mediocre GPU is presented.

34 0

TransNet V2: An Effective Deep Network Architecture for Fast Shot Transition Detection

Tomás Soucek, Jakub Lokoč•Mon Aug 10 2020

The current version of the deep network TransNet V2 that reaches state-of-the-art performance on respected benchmarks is shared and a trained instance of the model is provided so it can be instantly utilized by the community for a highly efficient analysis of large video archives.

183 0

Deep Voice: Real-time Neural Text-to-Speech

Shubho Sengupta, G. Diamos, Jonathan Raiman, Adam Coates, Mike Chrzanowski, Sercan Ö. Arik, M. Shoeybi, Andrew Gibiansky, Yongguo Kang, Xian Li, John Miller, Andrew Ng•Fri Feb 24 2017

Deep Voice lays the groundwork for truly end-to-end neural speech synthesis and shows that inference with the system can be performed faster than real time and describes optimized WaveNet inference kernels on both CPU and GPU that achieve up to 400x speedups over existing implementations.

645 0

Photo-Sketching: Inferring Contour Drawings From Images

Zhe L. Lin, Deva Ramanan, R. Měch, Ersin Yumer, Mengtian Li•Mon Dec 31 2018

Surprisingly, when the model fine-tunes on BSDS500, the model achieves the state-of-the-art performance in salient boundary detection, suggesting contour drawing might be a scalable alternative to boundary annotation, which at the same time is easier and more interesting for annotators to draw.

147 0

Boundary Loss for Remote Sensing Imagery Semantic Segmentation

E. Burnaev, Alexey Bokhovkin•Sun May 19 2019

A novel loss function, namely a differentiable surrogate of a metric accounting accuracy of boundary detection, which can be used with any neural network for binary segmentation and which outperform baseline methods in terms of IoU score.

125 0

Adding a benchmark result helps the community track progress.

Boundary Detection | State-of-the-Art