paper-with-me

Papers

Combining Contrastive and Supervised Learning for Video Super-Resolution Detection

2022-05-20 · Viacheslav Meshchaninov, Ivan Molodetskikh, Dmitriy Vatolin

Upscaled video detection is a helpful tool in multimedia forensics, but it is a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and deep-learning-based super-resolution, and they leave unique traces. In this work, we propose a new upscaled-resolution-detection method based on learning of visual representations using contrastive and cross-entropy losses. To explain how the method detects videos, we systematically review the major components of our framework - in particular, we show that most data-augmentation approaches hinder the learning of the method. Through extensive experiments on various datasets, we demonstrate that our method effectively detects upscaling even in compressed videos and outperforms the state-of-the-art alternatives. The code and models are publicly available at https://github.com/msu-video-group/SRDM

📄 PDF Abstract BibTeX arXiv:2205.10406

Code (1)

msu-video-group/srdm 공식 구현 pytorch

Tasks

Data AugmentationSuper-ResolutionVideo Super-Resolution

Similar Papers 제목 키워드 기반

Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentation

2026-03-17 · Marceau Lafargue-Hauret, Raghav Mehta, Fabio De Sousa Ribeiro, Mélanie Roschewitz 외 arxiv

Image segmentation relies on large annotated datasets, which are expensive and slow to produce. Silver-standard (AI-generated) labels are easier to obtain, but they risk introducing bias. Self-supervised learning, needin…

Medical Image SegmentationSelf-Supervised LearningRepresentation LearningContrastive Learning

Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution

2025-01-01 · CVPR 2025 1 · Shijun Shi, Jing Xu, Lijing Lu, Zhihang Li 외

Existing diffusion-based video super-resolution (VSR) methods are susceptible to introducing complex degradations and noticeable artifacts into high-resolution videos due to their inherent randomness. In this paper, …

Contrastive LearningMambaSelf-Supervised LearningSuper-Resolution+1

Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations

2022-12-06 · Minghao Chen, Renbo Tu, Chenxi Huang, Yuqi Lin 외

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive represent…

Action ClassificationContrastive LearningRepresentation LearningRetrieval+2

3D Human Pose, Shape and Texture from Low-Resolution Images and Videos

2021-03-11 · Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, Laszlo A. Jeni 외

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always avail…

3D human pose and shape estimationContrastive LearningSuper-Resolution

Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning

2020-10-29 · Li Tao, Xueting Wang, Toshihiko Yamasaki

Recently, pretext-task based methods are proposed one after another in self-supervised video feature learning. Meanwhile, contrastive learning methods also yield good performance. Usually, new methods can beat previous o…

Contrastive LearningData AugmentationSelf-Supervised Action RecognitionSelf-Supervised Learning+2