computer-vision-2

Highlight Detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

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

Trend

Dataset

Best Model

Actions

QVHighlights

TvSum

YouTube Highlights

Libraries

i

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

tencentarc/umt

2 papers 176

Datasets

TvSum

QVHighlights

Subtasks

No subtasks available.

Most implemented papers

QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries

Tamara L. Berg, Mohit Bansal, Jie Lei•Mon Jul 19 2021

A transformer encoder-decoder model that views moment retrieval as a direct set prediction problem, taking extracted video and query representations as inputs and predicting moment coordinates and saliency scores end-to-end, MomentDETR substantially outperforms previous methods.

88

Content

0

Paper Graph

Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding

WonJun Moon, Jae-Pil Heo, Sangeek Hyun, Subeen Lee•Sat Dec 31 2022

This paper designs an adaptive cross-attention layer with dummy tokens, and uses a moment-adaptive saliency detector to exploit each video clip’s degrees of text engagement, and validate the superiority of CG-DETR with the state-of-the-art results on various benchmarks for both moment retrieval and highlight detection.

71 0

Paper Graph

AENet: Learning Deep Audio Features for Video Analysis

Michael Gygli, L. Van Gool, Naoya Takahashi•Mon Jan 02 2017

A convolutional neural network operating on a large temporal input allows for an audio event detection system end to end and performs transfer learning and shows that the model learned generic audio features, similar to the way CNNs learn generic features on vision tasks.

160 0

Paper Graph

PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation

Michael Gygli, A. Molino•Tue Apr 17 2018

A global ranking model which can condition on a particular user's interests is presented, which proves more precise than the user-agnostic baselines even with only one single person-specific example.

41 0

Paper Graph

SoccerDB: A Large-Scale Database for Comprehensive Video Understanding

Yudong Jiang, Kaixu Cui, Leilei Chen, Canjin Wang, Changliang Xu•Mon Dec 09 2019

This paper proposes a new soccer video database named SoccerDB, comprising 171,191 video segments from 346 high-quality soccer games, which is the largest database for comprehensive sports video understanding on various aspects.

50 0

Paper Graph

Single Image Highlight Removal with a Sparse and Low-Rank Reflection Model

Limin Wang, Jie Guo, Zuojian Zhou•Fri Sep 07 2018

A sparse and low-rank reflection model for specular highlight detection and removal using a single input image that is competitive with previous methods, especially in some challenging scenarios featuring natural illumination, hue-saturation ambiguity and strong noises.

59 0

Paper Graph

Adaptive Video Highlight Detection by Learning from User History

Yang Wang, Mrigank Rochan, Mahesh Kumar Krishna Reddy, Linwei Ye•Sat Jul 18 2020

A simple yet effective framework that learns to adapt highlight detection to a user by exploiting the user's history in the form of highlights that the user has previously created is proposed.

36 0

Paper Graph

Learning to Detect Specular Highlights from Real-world Images

Gang Fu, Qing Zhang, Qifeng Lin, Lei Zhu, Chunxia Xiao•Sun Oct 11 2020

This paper presents a large-scale real-world highlight dataset containing a rich variety of material categories, with diverse highlight shapes and appearances, and develops a deep learning-based specular highlight detection network (SHDNet) leveraging multi-scale context contrasted features to accurately detect specular highlights of varying scales.

39 0

Paper Graph

A Multi-Task Network for Joint Specular Highlight Detection and Removal

Gang Fu, Qing Zhang, Chunxia Xiao, Lei Zhu, Ping Li•Mon May 31 2021

Specular highlight detection and removal are fundamental and challenging tasks. Although recent methods have achieved promising results on the two tasks by training on synthetic training data in a supervised manner, they are typically solely designed for highlight detection or removal, and their performance usually deteriorates significantly on real-world images. In this paper, we present a novel network that aims to detect and remove highlights from natural images. To remove the domain gap between synthetic training samples and real test images, and support the investigation of learning-based approaches, we first introduce a dataset with about 16K real images, each of which has the corresponding ground truths of highlight detection and removal. Using the presented dataset, we develop a multi-task network for joint highlight detection and removal, based on a new specular highlight image formation model. Experiments on the benchmark datasets and our new dataset show that our approach clearly outperforms state-of-the-art methods for both highlight detection and removal.

70 0

Paper Graph

Adding a benchmark result helps the community track progress.