深度学习之视频语音+视频摘要+视频显示检测+视频理解--附带源码和作者主页

我会带着你远行 2022-04-15 06:46 197阅读 0赞

# 视频语音 #

### **Vid2speech: Speech Reconstruction from Silent Video** ###

*  intro: ICASSP 2017
 *  project page: [http://www.vision.huji.ac.il/vid2speech/][http_www.vision.huji.ac.il_vid2speech]
 *  arxiv: [https://arxiv.org/abs/1701.00495][https_arxiv.org_abs_1701.00495]
 *  github(official): [https://github.com/arielephrat/vid2speech][https_github.com_arielephrat_vid2speech]

# 视频摘要 #

Video summarization produces a short summary of a full-length video and ideally encapsulates its most informative parts, alleviates the problem of video browsing, editing and indexing.

### **Video Summarization with Long Short-term Memory** ###

*  arxiv: [http://arxiv.org/abs/1605.08110][http_arxiv.org_abs_1605.08110]

### **DeepVideo: Video Summarization using Temporal Sequence Modelling** ###

*  intro: CS231n student project report
 *  paper: [http://cs231n.stanford.edu/reports2016/216\_Report.pdf][http_cs231n.stanford.edu_reports2016_216_Report.pdf]

### **Semantic Video Trailers** ###

*  arxiv: [http://arxiv.org/abs/1609.01819][http_arxiv.org_abs_1609.01819]

### **Video Summarization using Deep Semantic Features** ###

*  inro: ACCV 2016
 *  arxiv: [http://arxiv.org/abs/1609.08758][http_arxiv.org_abs_1609.08758]

### **CNN-Based Prediction of Frame-Level Shot Importance for Video Summarization** ###

*  intro: International Conference on new Trends in Computer Sciences (ICTCS), Amman-Jordan, 2017
 *  arxiv: [https://arxiv.org/abs/1708.07023][https_arxiv.org_abs_1708.07023]

### **Video Summarization with Attention-Based Encoder-Decoder Networks** ###

[https://arxiv.org/abs/1708.09545][https_arxiv.org_abs_1708.09545]

### **Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward** ###

*  intro: AAAI 2018. Chinese Academy of Sciences & Queen Mary University of London
 *  project page: [https://kaiyangzhou.github.io/project\_vsumm\_reinforce/index.html][https_kaiyangzhou.github.io_project_vsumm_reinforce_index.html]
 *  arxiv: [https://arxiv.org/abs/1801.00054][https_arxiv.org_abs_1801.00054]
 *  github: [https://github.com//KaiyangZhou/vsumm-reinforce][https_github.com_KaiyangZhou_vsumm-reinforce]

### **Viewpoint-aware Video Summarization** ###

*  intro: CVPR 2018
 *  arxiv: [https://arxiv.org/abs/1804.02843][https_arxiv.org_abs_1804.02843]

### **DTR-GAN: Dilated Temporal Relational Adversarial Network for Video Summarization** ###

[https://arxiv.org/abs/1804.11228][https_arxiv.org_abs_1804.11228]

### **Learning Video Summarization Using Unpaired Data** ###

[https://arxiv.org/abs/1805.12174][https_arxiv.org_abs_1805.12174]

### **Video Summarization Using Fully Convolutional Sequence Networks** ###

[https://arxiv.org/abs/1805.10538][https_arxiv.org_abs_1805.10538]

### **Video Summarisation by Classification with Deep Reinforcement Learning** ###

*  intro: BMVC 2018
 *  arxiv: [https://arxiv.org/abs/1807.03089][https_arxiv.org_abs_1807.03089]

### **Query-Conditioned Three-Player Adversarial Network for Video Summarization** ###

*  intro: BMVC 2018
 *  arxiv: [https://arxiv.org/abs/1807.06677][https_arxiv.org_abs_1807.06677]

# 视频突出显示检测 #

### **Unsupervised Extraction of Video Highlights Via Robust Recurrent Auto-encoders** ###

*  intro: ICCV 2015
 *  intro: rely on an assumption that highlights of an event category are more frequently captured in short videos than non-highlights
 *  arxiv: [http://arxiv.org/abs/1510.01442][http_arxiv.org_abs_1510.01442]

### **Highlight Detection with Pairwise Deep Ranking for First-Person Video Summarization** ###

*  keywords: wearable device
 *  paper: [http://www.cv-foundation.org/openaccess/content\_cvpr\_2016/papers/Yao\_Highlight\_Detection\_With\_CVPR\_2016\_paper.pdf][http_www.cv-foundation.org_openaccess_content_cvpr_2016_papers_Yao_Highlight_Detection_With_CVPR_2016_paper.pdf]
 *  paper: [http://research.microsoft.com/apps/pubs/default.aspx?id=264919][http_research.microsoft.com_apps_pubs_default.aspx_id_264919]

### **Using Deep Learning to Find Basketball Highlights** ###

[![228179fe-09f3-11e5-9ea7-31e76c8248fe.png][]][228179fe-09f3-11e5-9ea7-31e76c8248fe.png]

*  blog: [http://public.hudl.com/bits/archives/2015/06/05/highlights/?utm\_source=tuicool&utm\_medium=referral][http_public.hudl.com_bits_archives_2015_06_05_highlights_utm_source_tuicool_utm_medium_referral]

### **Real-Time Video Highlights for Yahoo Esports** ###

*  arxiv: [https://arxiv.org/abs/1611.08780][https_arxiv.org_abs_1611.08780]

### **A Deep Ranking Model for Spatio-Temporal Highlight Detection from a 360 Video** ###

*  intro: AAAI 2018
 *  arxiv: [https://arxiv.org/abs/1801.10312][https_arxiv.org_abs_1801.10312]

### **PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation** ###

*  intro: Nanyang Technological University & Google Research, Zurich
 *  keywords: personalized highlight detection (PHD)
 *  arxiv: [https://arxiv.org/abs/1804.06604][https_arxiv.org_abs_1804.06604]

# 视频理解 #

### **Scale Up Video Understandingwith Deep Learning** ###

*  intro: 2016, Tsinghua University
 *  slides: [iiis.tsinghua.edu.cn/~jianli/courses/ATCS2016spring/talk\_chuang.pptx][iiis.tsinghua.edu.cn_jianli_courses_ATCS2016spring_talk_chuang.pptx]

### **Slicing Convolutional Neural Network for Crowd Video Understanding** ###

*  intro: CVPR 2016
 *  intro: It aims at learning generic spatio-temporal features from crowd videos, especially for long-term temporal learning
 *  project page: [http://www.ee.cuhk.edu.hk/~jshao/SCNN.html][http_www.ee.cuhk.edu.hk_jshao_SCNN.html]
 *  paper: [http://www.ee.cuhk.edu.hk/~jshao/papers\_jshao/jshao\_cvpr16\_scnn.pdf][http_www.ee.cuhk.edu.hk_jshao_papers_jshao_jshao_cvpr16_scnn.pdf]
 *  github: [https://github.com/amandajshao/Slicing-CNN][https_github.com_amandajshao_Slicing-CNN]

### **Rethinking Spatiotemporal Feature Learning For Video Understanding** ###

[https://arxiv.org/abs/1712.04851][https_arxiv.org_abs_1712.04851]

### **Hierarchical Video Understanding** ###

[https://arxiv.org/abs/1809.03316][https_arxiv.org_abs_1809.03316]

[http_www.vision.huji.ac.il_vid2speech]: http://www.vision.huji.ac.il/vid2speech/
[https_arxiv.org_abs_1701.00495]: https://arxiv.org/abs/1701.00495
[https_github.com_arielephrat_vid2speech]: https://github.com/arielephrat/vid2speech
[http_arxiv.org_abs_1605.08110]: http://arxiv.org/abs/1605.08110
[http_cs231n.stanford.edu_reports2016_216_Report.pdf]: http://cs231n.stanford.edu/reports2016/216_Report.pdf
[http_arxiv.org_abs_1609.01819]: http://arxiv.org/abs/1609.01819
[http_arxiv.org_abs_1609.08758]: http://arxiv.org/abs/1609.08758
[https_arxiv.org_abs_1708.07023]: https://arxiv.org/abs/1708.07023
[https_arxiv.org_abs_1708.09545]: https://arxiv.org/abs/1708.09545
[https_kaiyangzhou.github.io_project_vsumm_reinforce_index.html]: https://kaiyangzhou.github.io/project_vsumm_reinforce/index.html
[https_arxiv.org_abs_1801.00054]: https://arxiv.org/abs/1801.00054
[https_github.com_KaiyangZhou_vsumm-reinforce]: https://github.com//KaiyangZhou/vsumm-reinforce
[https_arxiv.org_abs_1804.02843]: https://arxiv.org/abs/1804.02843
[https_arxiv.org_abs_1804.11228]: https://arxiv.org/abs/1804.11228
[https_arxiv.org_abs_1805.12174]: https://arxiv.org/abs/1805.12174
[https_arxiv.org_abs_1805.10538]: https://arxiv.org/abs/1805.10538
[https_arxiv.org_abs_1807.03089]: https://arxiv.org/abs/1807.03089
[https_arxiv.org_abs_1807.06677]: https://arxiv.org/abs/1807.06677
[http_arxiv.org_abs_1510.01442]: http://arxiv.org/abs/1510.01442
[http_www.cv-foundation.org_openaccess_content_cvpr_2016_papers_Yao_Highlight_Detection_With_CVPR_2016_paper.pdf]: http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Yao_Highlight_Detection_With_CVPR_2016_paper.pdf
[http_research.microsoft.com_apps_pubs_default.aspx_id_264919]: http://research.microsoft.com/apps/pubs/default.aspx?id=264919
[228179fe-09f3-11e5-9ea7-31e76c8248fe.png]: /images/20220415/9ca5977607144bb68ab4f247769fc953.png
[http_public.hudl.com_bits_archives_2015_06_05_highlights_utm_source_tuicool_utm_medium_referral]: http://public.hudl.com/bits/archives/2015/06/05/highlights/?utm_source=tuicool&utm_medium=referral
[https_arxiv.org_abs_1611.08780]: https://arxiv.org/abs/1611.08780
[https_arxiv.org_abs_1801.10312]: https://arxiv.org/abs/1801.10312
[https_arxiv.org_abs_1804.06604]: https://arxiv.org/abs/1804.06604
[iiis.tsinghua.edu.cn_jianli_courses_ATCS2016spring_talk_chuang.pptx]: https://github.com/handong1587/handong1587.github.io/blob/master/_posts/deep_learning/iiis.tsinghua.edu.cn/~jianli/courses/ATCS2016spring/talk_chuang.pptx
[http_www.ee.cuhk.edu.hk_jshao_SCNN.html]: http://www.ee.cuhk.edu.hk/~jshao/SCNN.html
[http_www.ee.cuhk.edu.hk_jshao_papers_jshao_jshao_cvpr16_scnn.pdf]: http://www.ee.cuhk.edu.hk/~jshao/papers_jshao/jshao_cvpr16_scnn.pdf
[https_github.com_amandajshao_Slicing-CNN]: https://github.com/amandajshao/Slicing-CNN
[https_arxiv.org_abs_1712.04851]: https://arxiv.org/abs/1712.04851
[https_arxiv.org_abs_1809.03316]: https://arxiv.org/abs/1809.03316