Deep Learning for Computer Vision: Video Analytics (UPC 2016)
9 likes2,395 views
The document outlines a lecture on video analytics presented by Xavier Giró-i-Nieto, covering topics such as scene classification, object detection, and tracking using convolutional neural networks (CNNs). It examines current methods, including 3D convolutional networks for spatiotemporal features and discusses various architectures and results from related research. The presentation emphasizes the importance of deep learning in analyzing video data and incorporates findings from multiple research studies.
![Day 4 Lecture 4
Video Analytics
Xavier Giró-i-Nieto
xavier.giro@upc.edu
[course site]](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-1-320.jpg)
![11
Unsupervised learning [Le at al’11] Supervised learning [Karpathy et al’14]
Scene Classification: DeepVideo: Features
(Slides by Victor Campos) Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L.
(2014, June). Large-scale video classification with convolutional neural networks. CVPR 2014](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-11-320.jpg)
![23
Based on Deconvnets by Zeiler and Fergus [ECCV 2014] - See [ReadCV Slides] for
more details.
Scene Classification: C3D: Visualization
Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal
features with 3D convolutional networks." CVPR 2015](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-23-320.jpg)
![30
Classification & Detection: Proposals + C3D
(Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal
Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code]](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-30-320.jpg)
![31
Classification & Detection: Proposals + C3D
(Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal
Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code]
(1) Binary classification: Action or No Action](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-31-320.jpg)
![32
Classification & Detection: Proposals + C3D
(Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal
Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code]
(2) One-vs-all Action classification](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-32-320.jpg)
![33
Classification & Detection: Proposals + C3D
(Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal
Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code]
(3) Refinement with temporal-aware loss function](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-33-320.jpg)
![34
Classification & Detection: Proposals + C3D
(Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal
Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code]
Post-processing](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-34-320.jpg)
![35
Classification & Detection: Proposals + C3D
(Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal
Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code]](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-35-320.jpg)
![37
Scene Classification & Detection: C3D + LSTM
Montes A. “Temporal Activity Detection in Untrimmed Videos with Recurrent Neural
Networks”. BSc thesis submitted to ETSETB (2016) [code available in Keras]](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-37-320.jpg)
![39[ILSVRC 2015 Slides and videos]
Objects: ImageNet Video](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-39-320.jpg)
![40[ILSVRC 2015 Slides and videos]
Objects: ImageNet Video](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-40-320.jpg)
![41
(Slides by Andrea Ferri): Kai Kang, Hongsheng Li, Junjie Yan, Xingyu Zeng, Bin Yang, Tong Xiao, Cong Zhang, Zhe Wang,
Ruohui Wang, Xiaogang Wang, and Wanli Ouyang, “Object Detection From Video Tubelets With Convolutional Neural
Networks”, CVPR 2016 [code]
Objects: ImageNet Video: T-CNN
Object
Detection
Object
Tracking](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-41-320.jpg)
![44
Objects: Tracking: FCNT
Wang, Lijun, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu. "Visual Tracking with Fully Convolutional Networks." CVPR 2015 [code]
Focus on conv4-3 and conv5-3 of VGG-16 network pre-trained for ImageNet image
classification.
conv4-3 conv5-3](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-44-320.jpg)
![45Wang, Lijun, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu. "Visual Tracking with Fully Convolutional Networks." In Proceedings of the IEEE
International Conference on Computer Vision, pp. 3119-3127. 2015 [code]
Despite trained for image classification, feature maps in conv5-3 enable object
localization...but are not discriminative enough to different instances of the same
class.
Objects: Tracking: FCNT: Localization](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-45-320.jpg)
![46Wang, Lijun, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu. "Visual Tracking with Fully Convolutional Networks." In Proceedings of the IEEE
International Conference on Computer Vision, pp. 3119-3127. 2015 [code]
On the other hand, feature maps from conv4-3 are more sensitive to intra-class
appearance variation…
Objects: Tracking: FCNT: Localization
conv4-3 conv5-3](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-46-320.jpg)
![47Wang, Lijun, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu. "Visual Tracking with Fully Convolutional Networks." In Proceedings of the IEEE
International Conference on Computer Vision, pp. 3119-3127. 2015 [code]
SNet=Specific Network (online update)
GNet=General Network (fixed)
Objects: Tracking: FCNT: Localization](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-47-320.jpg)
![49
Objects: Tracking: DeepTracking
P. Ondruska and I. Posner, “Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks,” AAAI 2016. [code]](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-49-320.jpg)
![50P. Ondruska and I. Posner, “Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks,” AAAI 2016. [code]
Objects: Tracking: DeepTracking](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-50-320.jpg)
![51
Objects: Tracking: DeepTracking
P. Ondruska and I. Posner, “Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks,” AAAI 2016. [code]](https://image.slidesharecdn.com/dlcvd4l4videoanalytics-160803172459/85/Deep-Learning-for-Computer-Vision-Video-Analytics-UPC-2016-51-320.jpg)
Deep Learning for Computer Vision: Video Analytics (UPC 2016)
- 1. Day 4 Lecture 4 Video Analytics Xavier Giró-i-Nieto [email protected] [course site]
- 2. 2 Motivation Slide credit: Alberto Montes
- 3. 3 Motivation
- 4. 4 Motivation
- 5. 5 Outline 1. Scene Classification 2. Object Detection & Tracking
- 6. 6 Scene Classification (Slides by Victor Campos) Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014, June). Large-scale video classification with convolutional neural networks. CVPR 2014
- 7. 7 Figure: Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." In Proceedings of the IEEE International Conference on Computer Vision, pp. 4489-4497. 2015 Scene Classification
- 8. 8 Figure: Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." In Proceedings of the IEEE International Conference on Computer Vision, pp. 4489-4497. 2015 Previous lectures Scene Classification
- 9. 9 Figure: Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." In Proceedings of the IEEE International Conference on Computer Vision, pp. 4489-4497. 2015 Scene Classification
- 10. 10 Scene Classification: DeepVideo: Architectures (Slides by Victor Campos) Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014, June). Large-scale video classification with convolutional neural networks. CVPR 2014
- 11. 11 Unsupervised learning [Le at al’11] Supervised learning [Karpathy et al’14] Scene Classification: DeepVideo: Features (Slides by Victor Campos) Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014, June). Large-scale video classification with convolutional neural networks. CVPR 2014
- 12. 12 Scene Classification: DeepVideo: Multires (Slides by Victor Campos) Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014, June). Large-scale video classification with convolutional neural networks. CVPR 2014
- 13. 13 Scene Classification: DeepVideo: Results (Slides by Victor Campos) Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014, June). Large-scale video classification with convolutional neural networks. CVPR 2014
- 14. 14 Figure: Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015 Scene Classification
- 15. 15 Scene Classification: C3D Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 16. 16K. Simonyan, A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition” ICLR 2015. Scene Classification: C3D: Spatial Dimensions
- 17. 17 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets Temporal depth 2D ConvNets Scene Classification: C3D: Temporal dimension Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 18. 18 A homogeneous architecture with small 3 × 3 × 3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets Scene Classification: C3D: Temporal dimension Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 19. 19 No gain when varying the temporal depth across layers. Scene Classification: C3D: Temporal dimension Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 20. 20 Feature vector Scene Classification: C3D: Network Architecture Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 21. 21 Video sequence 16 frames-long clips 8 frames-long overlap Scene Classification: C3D: Feature Vector Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 22. 22 16-frame clip 16-frame clip 16-frame clip 16-frame clip ... Average 4096-dimvideodescriptor 4096-dimvideodescriptor L2 norm Scene Classification: C3D: Feature Vector Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 23. 23 Based on Deconvnets by Zeiler and Fergus [ECCV 2014] - See [ReadCV Slides] for more details. Scene Classification: C3D: Visualization Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 24. 24 C3D + simple linear classifier outperformed state-of-the-art methods on 4 different benchmarks, and were comparable with state of the art methods on other 2 benchmarks Scene Classification: C3D: Visualization Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 25. 25 Implementation by Michael Gygli (GitHub) Scene Classification: C3D: Software Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning spatiotemporal features with 3D convolutional networks." CVPR 2015
- 26. 26 Yue-Hei Ng, Joe, Matthew Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga, and George Toderici. "Beyond short snippets: Deep networks for video classification." CVPR 2015 Classification: Image & Optical Flow CNN + LSTM
- 27. 27 (Scene Classification: Image &) Optical Flow Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D. and Brox, T., FlowNet: Learning Optical Flow With Convolutional Networks. CVPR 2015
- 28. 28 (Scene Classification: Image &) Optical Flow Since existing ground truth datasets are not sufficiently large to train a Convnet, a synthetic dataset is generated… and augmented (translation, rotation, scaling transformations; additive Gaussian noise; changes in brightness, contrast, gamma and color). Data augmentation Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D. and Brox, T., FlowNet: Learning Optical Flow With Convolutional Networks. CVPR 2015
- 29. 29 Scene Classification & Detection “Biking” CNN RNN+ Slide credit: Albero Montes
- 30. 30 Classification & Detection: Proposals + C3D (Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code]
- 31. 31 Classification & Detection: Proposals + C3D (Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code] (1) Binary classification: Action or No Action
- 32. 32 Classification & Detection: Proposals + C3D (Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code] (2) One-vs-all Action classification
- 33. 33 Classification & Detection: Proposals + C3D (Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code] (3) Refinement with temporal-aware loss function
- 34. 34 Classification & Detection: Proposals + C3D (Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code] Post-processing
- 35. 35 Classification & Detection: Proposals + C3D (Slidecast and Slides by Alberto Montes) Shou, Zheng, Dongang Wang, and Shih-Fu Chang. "Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs." CVPR 2016 [code]
- 36. 36 Classification & Detection: Image + RNN + Reinforce Yeung, Serena, Olga Russakovsky, Greg Mori, and Li Fei-Fei. "End-to-end Learning of Action Detection from Frame Glimpses in Videos." CVPR 2016
- 37. 37 Scene Classification & Detection: C3D + LSTM Montes A. “Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks”. BSc thesis submitted to ETSETB (2016) [code available in Keras]
- 38. 38 Outline 1. Scene Classification 2. Object Detection & Tracking
- 39. 39[ILSVRC 2015 Slides and videos] Objects: ImageNet Video
- 40. 40[ILSVRC 2015 Slides and videos] Objects: ImageNet Video
- 41. 41 (Slides by Andrea Ferri): Kai Kang, Hongsheng Li, Junjie Yan, Xingyu Zeng, Bin Yang, Tong Xiao, Cong Zhang, Zhe Wang, Ruohui Wang, Xiaogang Wang, and Wanli Ouyang, “Object Detection From Video Tubelets With Convolutional Neural Networks”, CVPR 2016 [code] Objects: ImageNet Video: T-CNN Object Detection Object Tracking
- 42. 42 Domain-specific layers are used during training for each sequence, but are replaced by a single one at test time. Objects: Tracking: MDNet Nam, Hyeonseob, and Bohyung Han. "Learning multi-domain convolutional neural networks for visual tracking." ICCV VOT Workshop (2015)
- 43. 43 Objects: Tracking: MDNet Nam, Hyeonseob, and Bohyung Han. "Learning multi-domain convolutional neural networks for visual tracking." ICCV VOT Workshop (2015)
- 44. 44 Objects: Tracking: FCNT Wang, Lijun, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu. "Visual Tracking with Fully Convolutional Networks." CVPR 2015 [code] Focus on conv4-3 and conv5-3 of VGG-16 network pre-trained for ImageNet image classification. conv4-3 conv5-3
- 45. 45Wang, Lijun, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu. "Visual Tracking with Fully Convolutional Networks." In Proceedings of the IEEE International Conference on Computer Vision, pp. 3119-3127. 2015 [code] Despite trained for image classification, feature maps in conv5-3 enable object localization...but are not discriminative enough to different instances of the same class. Objects: Tracking: FCNT: Localization
- 46. 46Wang, Lijun, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu. "Visual Tracking with Fully Convolutional Networks." In Proceedings of the IEEE International Conference on Computer Vision, pp. 3119-3127. 2015 [code] On the other hand, feature maps from conv4-3 are more sensitive to intra-class appearance variation… Objects: Tracking: FCNT: Localization conv4-3 conv5-3
- 47. 47Wang, Lijun, Wanli Ouyang, Xiaogang Wang, and Huchuan Lu. "Visual Tracking with Fully Convolutional Networks." In Proceedings of the IEEE International Conference on Computer Vision, pp. 3119-3127. 2015 [code] SNet=Specific Network (online update) GNet=General Network (fixed) Objects: Tracking: FCNT: Localization
- 48. 48Zhou, Bolei, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. "Object detectors emerge in deep scene cnns." ICLR 2015. Other works have also highlighted how features maps in convolutional layers allow object localization. Objects: Tracking: FCNT: Localization
- 49. 49 Objects: Tracking: DeepTracking P. Ondruska and I. Posner, “Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks,” AAAI 2016. [code]
- 50. 50P. Ondruska and I. Posner, “Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks,” AAAI 2016. [code] Objects: Tracking: DeepTracking
- 51. 51 Objects: Tracking: DeepTracking P. Ondruska and I. Posner, “Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks,” AAAI 2016. [code]
- 52. 52 Summary ● Works on video are normally extensions from principles previously tested on still images. ● RNNs can naturally handle the diversity in video lengths, and capture its temporal dependencies. ● Trick: Init your networks to predict the next frame.
- 53. 53 Thanks ! Q&A ? Follow me at https://imatge.upc.edu/web/people/xavier-giro @DocXavi /ProfessorXavi