IP Library › Granted Patent US 12,711,388
Granted Patent B2
US 12,711,388 · App. 17/295,286 · Granted Aug 18, 2026

Aligning sequences by generating encoded representations of data items

Inventors: Yusuf Aytar (London, GB); Debidatta Dwibedi (Sunnyvale, CA); Andrew Zisserman (London, GB); Jonathan Tompson (Mountain View, CA); Pierre Sermanet (Palo Alto, CA)
Assignee: GDM Holding LLC
G06N3/088G06F18/214G06F18/24147G06F18/2431G06N3/0455G06T7/97G06V10/74G06V10/761G06V10/82G06V20/41G06V20/44G06V20/48G06T2207/10016G06T2207/20081G06T2207/20084
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,711,388
App. No.
17/295,286
Granted
Aug 18, 2026
Kind
B2
Abstract

An encoder neural network is described which can encode a data item, such as a frame of a video, to form a respective encoded data item. Data items of a first data sequence are associated with respective data items of a second sequence, by determining which of the encoded data items of the second sequence is closest to the encoded data item produced from each data item of the first sequence. Thus, the two data sequences are aligned. The encoder neural network is trained automatically using a training set of data sequences, by an iterative process of successively increasing cycle consistency between pairs of the data sequences.

Claims (41)

1 . A method of aligning two video sequences of events using a single encoder neural network, a first video sequence of the two video sequences being a sequence of first video frames each comprising image data captured by at least one video camera, and a second video sequence of the two video sequences being a sequence of second video frames each comprising image data captured by at least one video camera, the sequence of first video frames depicting respective first events which occur in a first environment at successive first times, and the sequence of second video frames depicting respective second events which occur in a second environment at successive second times, the first video sequence depicting a first task and the second video sequence depicting a second task, the first task and the second task each having a plurality of corresponding phases that are performed in the same order in the first and second video sequences, the method comprising the steps of:

encoding the first video sequence using an encoder neural network to form, from each first video frame of the sequence of first video frames, a corresponding first encoded video frame;

attributing annotation data to one or more first video frames of the first video sequence, wherein the annotation data specifies a phase of the first task performed in an environment to which a video frame to which it is attributed relates;

encoding the second video sequence using the encoder neural network to form, from each second video frame of the sequence of second video frames, a corresponding second encoded video frame; and

for at least one first video frame of the sequence of first video frames:

(i) for each of a plurality of the second video frames, determining a respective distance value indicative of a distance between the corresponding first encoded video frame and the corresponding second encoded video frame according to a distance measure;

(ii) determining one of the plurality of second video frames for which the corresponding distance value is lowest;

(iii) associating the first video frame and the determined one of the plurality of second video frames, to associate the corresponding first event with the corresponding second event, the first and second events being events of a same type;

(iv) based on the association of the first event and the second event, associating the annotation data with second video frames of the second video sequence; and

(v) using the annotation data associated with the second video frames of the second video sequence as an input to a control program to determine that a first phase of the second task has been completed and to initiate a second phase of the second task.

2 . A method according to claim 1 in which the steps are performed while the sequence of first video frames of the first video sequence are datasets successively captured by at least one sensor and characterizing a real world environment at successive times.

3 . A method according to claim 2 , wherein using the annotation data associated with the second video frames of the second video sequence as an input to a control program comprises: in response to capturing a video frame of the first video sequence, and associating the first video frame and the determined one of the plurality of second video frames,

identifying the annotation data associated with the determined one of the plurality of second video frames, using the annotation data to generate control signals, and based on the control signals, modifying the real world environment.

4 . A method according to claim 1 further comprising determining whether one or more of the distance values meet an anomaly criterion, and if the anomaly criterion is met transmitting a warning message.

5 . A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations for aligning two video sequences of events using a single encoder neural network, a first video sequence of the two video sequences being a sequence of first video frames each comprising image data captured by at least one video camera, and a second video sequence of the two video sequences being a sequence of second video frames each comprising image data captured by at least one video camera, the sequence of first video frames depicting respective first events which occur in a first environment at successive first times, and the sequence of second video frames depicting respective second events which occur in a second environment at successive second times, the first video sequence depicting a first task and the second video sequence depicting a second task, the first task and the second task each having a plurality of corresponding phases that are performed in the same order in the first and second video sequences, the operations comprising:

encoding the first video sequence using an encoder neural network to form, from each first video frame of the sequence of first video frames, a corresponding first encoded video frame;

attributing annotation data to one or more first video frames of the first video sequence, wherein the annotation data specifies a phase of the first task performed in an environment to which a video frame to which it is attributed relates;

encoding the second video sequence using the encoder neural network to form, from each second video frame of the sequence of second video frames, a corresponding second encoded video frame; and

for at least one first video frame of the sequence of first video frames:

(i) for each of a plurality of the second video frames, determining a respective distance value indicative of a distance between the corresponding first encoded video frame and the corresponding second encoded video frame according to a distance measure;

(ii) determining one of the plurality of second video frames for which the corresponding distance value is lowest;

(iii) associating the first video frame and the determined one of the plurality of second video frames, to associate the corresponding first event with the corresponding second event, the first and second events being events of a same type;

(iv) based on the association of the first event and the second event, associating the annotation data with second video frames of the second video sequence; and

(v) using the annotation data associated with the second video frames of the second video sequence as an input to a control program to determine that a first phase of the second task has been completed and to initiate a second phase of the second task.

6 . A system according to claim 5 in which the operations are performed while the sequence of first video frames of the first video sequence are datasets successively captured by at least one sensor and characterizing a real world environment at successive times.

7 . A system according to claim 6 wherein using the annotation data associated with the second video frames of the second video sequence as an input to a control program comprises: in response to capturing a video frame of the first video sequence, and associating the first video frame and the determined one of the plurality of second video frames,

identifying the annotation data associated with the determined one of the plurality of second video frames, using the annotation data to generate control signals, and based on the control signals, modifying the real world environment.

8 . One or more non-transitory computer storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations for aligning two video sequences of events using a single encoder neural network, a first video sequence of the two video sequences being a sequence of first video frames each comprising image data captured by at least one video camera, and a second video sequence of the two video sequences being a sequence of second video frames each comprising image data captured by at least one video camera, the sequence of first video frames depicting respective first events which occur in a first environment at successive first times, and the sequence of second video frames depicting respective second events which occur in a second environment at successive second times, the first video sequence depicting a first task and the second video sequence depicting a second task, the first task and the second task each having a plurality of corresponding phases that are performed in the same order in the first and second video sequences, the operations comprising:

encoding the first video sequence using an encoder neural network to form, from each first video frame of the sequence of first video frames, a corresponding first encoded video frame;

attributing annotation data to one or more first video frames of the first video sequence, wherein the annotation data specifies a phase of the first task performed in an environment to which a video frame to which it is attributed relates;

encoding the second video sequence using the encoder neural network to form, from each second video frame of the sequence of second video frames, a corresponding second encoded video frame; and

for at least one first video frame of the sequence of first video frames:

(i) for each of a plurality of the second video frames, determining a respective distance value indicative of a distance between the corresponding first encoded video frame and the corresponding second encoded video frame according to a distance measure;

(ii) determining one of the plurality of second video frames for which the corresponding distance value is lowest;

(iii) associating the first video frame and the determined one of the plurality of second video frames, to associate the corresponding first event with the corresponding second event, the first and second events being events of a same type;

(iv) based on the association of the first event and the second event, associating the annotation data with second video frames of the second video sequence; and

(v) using the annotation data associated with the second video frames of the second video sequence as an input to a control program to determine that a first phase of the second task has been completed and to initiate a second phase of the second task.

9 . One or more non-transitory computer storage media according to claim 8 in which the operations are performed while the sequence of first video frames of the first video sequence are datasets successively captured by at least one sensor and characterizing a real world environment at successive times.

10 . One or more non-transitory computer storage media according to claim 8 , wherein using the annotation data associated with the second video frames of the second video sequence as an input to a control program comprises: in response to capturing a video frame of the first video sequence, and associating the first video frame and the determined one of the plurality of second video frames,

identifying the annotation data associated with the determined one of the plurality

of second video frames, using the annotation data to generate control signals, and based on the control signals, modifying a real world environment.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 6, 2025
From: DEEPMIND TECHNOLOGIES LIMITED
To: GDM HOLDING LLC
Reel/Frame 071498/0210 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 26, 2021
From: AYTAR, YUSUF; DWIBEDI, DEBIDATTA; ZISSERMAN, ANDREW; TOMPSON, JONATHAN; SERMANET, PIERRE
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 056365/0466 →
Continuity (2)
Provisional Application 62770595 · Nov 21, 2018
Related Publication 20220004883A1 · Jan 6, 2022
References Cited (91)
US 10726313B2 · Lee · 2020 [cited by examiner]
US 10766137B1 · Porter · 2020 [cited by examiner]
US 11630996B1 · O'Shea · 2023 [cited by examiner]
US 20140333775A1 · Naikal · 2014 [cited by examiner]
US 20170103264A1 · Javan Roshtkhari · 2017 [cited by examiner]
US 20170178345A1 · Pham · 2017 [cited by applicant]
US 20170308787A1 · Corrado · 2017 [cited by examiner]
US 20180129974A1 · Giering · 2018 [cited by examiner]
US 20180247201A1 · Liu et al. · 2018 [cited by applicant]
US 20180308522A1 · Ramey · 2018 [cited by examiner]
US 20190297392A1 · Farre Guiu · 2019 [cited by examiner]
US 20200149998A1 · Ayyagari · 2020 [cited by examiner]
CN 108182657 · 2018 [cited by applicant]
Abadi et al., “Tensorflow: A system for large-scale machine learning,” 12th {USENIX} Symposium on Operating Systems Design and Implementation, Savannah, GA, USA, Nov. 2-4, 2016, Nov. 2016, 21 pages. [cited by applicant]
Alayrac et al., “Learning from narrated instruction videos,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Sep. 2017, 40(9):1-14. [cited by applicant]
Anderson et al., “An introduction to multivariate statistical analysis,” Wiley, New York, Dec. 1958, 7 pages. [cited by applicant]
Andrew et al., “Deep canonical correlation analysis,” International Conference on Machine Learning, Atlanta, GA, USA, Jun. 16-21, 2013, May 2013, 9 pages. [cited by applicant]
Arandjelovic et al., “Look, listen and learn,” Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, Oct. 22-29, 2017, 2017, 9 pages. [cited by applicant]
Assael et al., “Lipnet: End-to-end sentence-level lipreading,” arXiv, Nov. 2016, 13 pages. [cited by applicant]
Aytar et al., “Playing hard exploration games by watching youtube,” arXiv, May 2018, 15 pages. [cited by applicant]
Aytar et al., “See, hear, and read: Deep aligned representations,” arXiv, Jun. 2017, 9 pages. [cited by applicant]
Aytar et al., “Soundnet: Learning sound representations from unlabeled video,” Advances in Neural Information Processing Systems, Oct. 2016, 29:1-9. [cited by applicant]
Bahdanau et al., “Neural machine translation by jointly learning to align and translate,” arXiv, Sep. 2014, 15 pages. [cited by applicant]
Becattini et al., “Am I done? Predicting action progress in videos,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Dec. 2020, 16(4):1-21. [cited by applicant]
Bojanowski et al., “Weakly supervised action labeling in videos under ordering constraints,” European Conference on Computer Vision, Zurich, Switzerland, Sep. 6-12, 2014, Sep. 2014, 16 pages. [cited by applicant]
Carreira et al., “Quo vadis, action recognition? a new model and the kinetics dataset,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, Jul. 21-26, 2017, 2017, 10 pa… [cited by applicant]
Chatfield et al., “Return of the devil in the details: Delving deep into convolutional nets,” arXiv, May 2014, 11 pages. [cited by applicant]
Damen et al., “Scaling egocentric vision: The epic-kitchens dataset,” Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, Sep. 8-14, 2018, 2018, 17 pages. [cited by applicant]
Del Pero et al., “Articulated motion discovery using pairs of trajectories,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, Jun. 7-12, 2015, 2015, 10 pages. [cited by applicant]
Doersch et al., “Multi-task self-supervised visual learning,” Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, Oct. 22-29, 2017, 2017, 10 pages. [cited by applicant]
Doersch et al., “Unsupervised visual representation learning by context prediction,” Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, Dec. 7-13, 2015, 2015, 9 pages. [cited by applicant]
Fang et al., “High-quality nonparallel voice conversion based on cycle-consistent adversarial network,” 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Alberta, Canada, A… [cited by applicant]
Fernando et al., “Self-supervised video representation learning with odd-one-out networks,” Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, Jul. 21-26, 2017, 20… [cited by applicant]
Girdhar et al., “Actionvlad: Learning spatio-temporal aggregation for action classification,” Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, Jul. 21-26, 2017, … [cited by applicant]
Goldberger et al., “Neighborhood components analysis,” Advances in Neural Information Processing Systems, 2004, 17:1-8. [cited by applicant]
Graves et al., “Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,” Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, Pennsylvania,… [cited by applicant]
He et al., “Deep residual learning for image recognition,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, Jun. 26-Jul. 1, 2016, 2016, 9 pages. [cited by applicant]
Heidarivincheh et al., “Action completion: A temporal model for moment detection,” arXiv, May 2018, 15 pages. [cited by applicant]
Hoffman et al., “Cycada: Cycle-consistent adversarial domain adaptation,” International Conference on Machine Learning 2018, Stockholmsmässan, Stockholm, Sweden, Jul. 2018, 10 pages. [cited by applicant]
Hori et al., “Cycle-consistency training for end-to-end speech recognition,” ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, May 12-17, 2019,… [cited by applicant]
Hyvarinen et al., “Unsupervised feature extraction by time-contrastive learning and nonlinear ica,” Advances in Neural Information Processing Systems, May 2016, 29:1-11. [cited by applicant]
Krizhevsky et al., “Imagenet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, 2012, 25:1-9. [cited by applicant]
Lan et al., “Action recognition by hierarchical mid-level action elements,” Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Chile, Dec. 7-13, 2015, 2015, 9 pages. [cited by applicant]
Lea et al., “Segmental spatiotemporal cnns for fine-grained action segmentation,” European Conference on Computer Vision, Amsterdam, Netherlands, Oct. 8-16, 2016, Oct. 2016, 17 pages. [cited by applicant]
Ma et al., “Learning activity progression in lstms for activity detection and early detection,” Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, Jun. 27-30, 201… [cited by applicant]
Misra et al., “Shuffle and learn: unsupervised learning using temporal order verification,” European Conference on Computer Vision, Amsterdam, Netherlands, Oct. 8-16, 2016, Oct. 2016, 21 pages. [cited by applicant]
Movshovitz-Attias et al., “No fuss distance metric learning using proxies,” Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy, Oct. 22-29, 2017, 2017, 9 pages. [cited by applicant]
Owens et al., “Ambient sound provides supervision for visual learning,” European Conference on Computer Vision, Amsterdam, Netherlands, Oct. 8-16, 2016, Oct. 2016, 20 pages. [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/082086, dated Jun. 3, 2021, 12 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/082086, dated Jun. 22, 2020, 21 pages. [cited by applicant]
Pirsiavash et al., “Parsing videos of actions with segmental grammars,” Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, USA, Jun. 24-27, 2014, 2014, 8 pages. [cited by applicant]
Revaud et al., “Event retrieval in large video collections with circulant temporal encoding,” Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, Jun. 23-28, 2013, 20… [cited by applicant]
Rocco et al., “Neighborhood consensus networks,” arXiv, Oct. 2018, 20 pages. [cited by applicant]
Sanakoyeu et al., “Deep unsupervised learning of visual similarities,” Pattern Recognition, Jun. 2018, 78:1-12. [cited by applicant]
Santa Cruz et al., “DeepPermNet: Visual permutation learning,” Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, Jul. 21-27, 2017, 2017, 9 pages. [cited by applicant]
Sener et al., “Unsupervised learning and segmentation of complex activities from video,” Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, Jun. 18-22, 2018, 9… [cited by applicant]
Sener et al., “Unsupervised semantic parsing of video collections,” Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Chile, Dec. 7-13, 2015, 2015, 9 pages. [cited by applicant]
Sermanet et al., “Time-contrastive networks: Self-supervised learning from video,” 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, May 21-25, 2018, May 2018, 15 pages. [cited by applicant]
Shechtman et al., “Matching local self-similarities across images and videos,” 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, Minnesota, USA, Jun. 18-23, 2007, Jun. 2007, 8 pages. [cited by applicant]
Sigurdsson et al., “Actor and observer: Joint modeling of first and third-person videos,” Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, Jun. 18-22, 2018, … [cited by applicant]
Sigurdsson et al., “Asynchronous temporal fields for action recognition,” Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, Jul. 21-27, 2017, 2017, 10 pages. [cited by applicant]
Simonyan et al., “Very deep convolutional networks for large-scale image recognition,” arXiv, Sep. 2014, 14 pages. [cited by applicant]
Snell et al., “Prototypical networks for few-shot learning,” arXiv, Mar. 2017, 13 pages. [cited by applicant]
Sohn et al., “Improved deep metric learning with multi-class n-pair loss objective,” Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, Dec. 5, 2016, Dec. 2016, … [cited by applicant]
Soltau et al., “Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition,” arXiv, Oct. 2016, 6 pages. [cited by applicant]
Soomro et al., “UCF101: A dataset of 101 human actions classes from videos in the wild,” arXiv, Dec. 2012, 7 pages. [cited by applicant]
Sutskever et al., “Sequence to sequence learning with neural networks,” Advances in Neural Information Processing Systems, Sep. 2014, 9 pages. [cited by applicant]
Wang et al., “Action recognition with improved trajectories,” Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Australia, Dec. 1-8, 2013, 2013, 8 pages. [cited by applicant]
Wang et al., “Image co-segmentation via consistent functional maps,” Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Australia, Dec. 1-8, 2013, 2013, 8 pages. [cited by applicant]
Wang et al., “Temporal segment networks: Towards good practices for deep action recognition,” European Conference on Computer Vision, European Conference on Computer Vision, Amsterdam, Netherlands, Oct. 8-16, 2016, Oct.… [cited by applicant]
Wang et al., “Unsupervised multi-class joint image segmentation,” Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, USA, Jun. 24-27, 2014, 2014, 8 pages. [cited by applicant]
Wikipedia.com [online], “Coefficient of determination,” Apr. 2020, retrieved on May 26, 2021, retrieved from URL<https://en.wikipedia.org/wiki/Coefficient_of_determination>, 13 pages. [cited by applicant]
Wikipedia.com [online], “Kendall rank correlation coefficient,” Nov. 2016, retrieved on May 26, 2021, retrieved from URL<https://en.wikipedia.org/wiki/Kendall_rank_correlation_coefficient>, 8 pages. [cited by applicant]
Wilson et al., “Network principles for sfm: Disambiguating repeated structures with local context,” Proceedings of the 2013 IEEE International Conference on Computer Vision, Australia, Dec. 1-8, 2013, 2013, 8 pages. [cited by applicant]
Yeung et al., “Every moment counts: Dense detailed labeling of actions in complex videos,” International Journal of Computer Vision, Apr. 2018, 15 pages. [cited by applicant]
Zach et al., “Disambiguating visual relations using loop constraints,” 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, California, Jun. 13-18, 2010, Jun. 2010, 9 pages. [cited by applicant]
Zhang et al., “From actemes to action: A strongly-supervised representation for detailed action understanding,” Proceedings of the 2013 IEEE International Conference on Computer Vision, Australia, Dec. 1-8, 2013, 2013, … [cited by applicant]
Zhao et al., “Temporal action detection with structured segment networks,” Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy, Oct. 22-29, 2017, 2017, 10 pages. [cited by applicant]
Zhou et al., “Flowweb: Joint image set alignment by weaving consistent, pixel-wise correspondences,” Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, Jun. 7-12, 2015, … [cited by applicant]
Zhou et al., “Learning dense correspondence via 3d-guided cycle consistency,” Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, Jun. 26-Jul. 1, 2016, 2016, 10 pa… [cited by applicant]
Zhou et al., “Multi-image matching via fast alternating minimization,” Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Chile, Dec. 7-13, 2015, 2015, 9 pages. [cited by applicant]
Zhu et al., “Unpaired image-to-image translation using cycle-consistent adversarial networks,” Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy, Oct. 22-29, 2017, 2017, 10 pages. [cited by applicant]
Office Action in Chinese Appln. No. 201980075332.7, dated Jul. 8, 2024, 22 pages (with English translation). [cited by applicant]
Office Action in European Appln. No. 19817969.9, dated Jun. 25, 2024, 10 pages. [cited by applicant]
He et al., “Unpaired image-to-image conversion based on improved CycleGAN model Journal of Yulin Normal University,” Journal of Yulin Normal University, 2018, 39(2):122-126 (with machine translation). [cited by applicant]
Office Action in Chinese Appln. No. 201980075332.7, dated Dec. 27, 2023, 35 pages (with English translation). [cited by applicant]
Office Action in European Appln. No. 19817969.9, dated Feb. 6, 2024, 12 pages. [cited by applicant]
Vo et al., “Self-supervised Multi-view Person Association and Its Applications,” CoRR, arXiv:1805.08717v3, Apr. 18, 2020, 14 pages. [cited by applicant]
Brief Communication in European Appln. No. 19817969.9, dated Nov. 19, 2024, 10 pages. [cited by applicant]
Extended Search Report in European Appln. No. 25178660.4, mailed on Jun. 16, 2025, 16 pages. [cited by applicant]
Vo et al., “Automatic adaptation of person association for multiview tracking in group activities,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Aug. 1, 2021, 43(8):2794-2808. [cited by applicant]