paper-with-me

Papers

Two-Stream Action Recognition-Oriented Video Super-Resolution

2019-03-13 · ICCV 2019 10 · Haochen Zhang, Dong Liu, Zhiwei Xiong

We study the video super-resolution (SR) problem for facilitating video analytics tasks, e.g. action recognition, instead of for visual quality. The popular action recognition methods based on convolutional networks, exemplified by two-stream networks, are not directly applicable on video of low spatial resolution. This can be remedied by performing video SR prior to recognition, which motivates us to improve the SR procedure for recognition accuracy. Tailored for two-stream action recognition networks, we propose two video SR methods for the spatial and temporal streams respectively. On the one hand, we observe that regions with action are more important to recognition, and we propose an optical-flow guided weighted mean-squared-error loss for our spatial-oriented SR (SoSR) network to emphasize the reconstruction of moving objects. On the other hand, we observe that existing video SR methods incur temporal discontinuity between frames, which also worsens the recognition accuracy, and we propose a siamese network for our temporal-oriented SR (ToSR) training that emphasizes the temporal continuity between consecutive frames. We perform experiments using two state-of-the-art action recognition networks and two well-known datasets--UCF101 and HMDB51. Results demonstrate the effectiveness of our proposed SoSR and ToSR in improving recognition accuracy.

📄 PDF Abstract BibTeX arXiv:1903.05577

Code (1)

AlanZhang1995/TwoStreamSR 공식 구현 tf

Tasks

Action RecognitionOptical Flow EstimationSuper-ResolutionTemporal Action LocalizationVideo Super-ResolutionVocal Bursts Valence Prediction

Methods 이 논문이 사용한 방법론

Siamese Network 설명 없음

Similar Papers 제목 키워드 기반

Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation

2021-09-30 · ICCV 2021 10 · Jay Patravali, Gaurav Mittal, Ye Yu, Fuxin Li 외

We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition. MetaUVFS leverages over 550K unlabeled videos to train a two-stream 2D and 3D CNN architecture via contrastive …

Action RecognitionContrastive LearningFew-Shot action recognitionFew Shot Action Recognition+1

Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering

2021-06-25 · Long Hoang Dang, Thao Minh Le, Vuong Le, Truyen Tran

Video Question Answering (Video QA) is a powerful testbed to develop new AI capabilities. This task necessitates learning to reason about objects, relations, and events across visual and linguistic domains in space-time.…

ObjectQuestion AnsweringVideo Question Answering

Self-Supervised Video Representation Learning via Latent Time Navigation

2023-05-10 · Di Yang, Yaohui Wang, Quan Kong, Antitza Dantcheva 외

Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. This leads to loss of pertinent informatio…

Action ClassificationAction RecognitionContrastive LearningRepresentation Learning

Non-Semantics Suppressed Mask Learning for Unsupervised Video Semantic Compression

2023-01-01 · ICCV 2023 1 · Yuan Tian, Guo Lu, Guangtao Zhai, Zhiyong Gao

Most video compression methods aim to improve the decoded video visual quality, instead of particularly guaranteeing the semantic-completeness, which deteriorates downstream video analysis tasks, e.g., action recogni…

Action RecognitionSemantic CompressionVideo Compression

A Training Method For VideoPose3D With Ideology of Action Recognition

2022-06-13 · Hao Bai

Action recognition and pose estimation from videos are closely related to understand human motions, but more literature focuses on how to solve pose estimation tasks alone from action recognition. This research shows a f…

Action RecognitionPose Estimation