IP Library › Granted Patent US 12,737,594
Granted Patent B2
US 12,737,594 · App. 18/253,416 · Granted Sep 15, 2026

Processing of sequential data via machine learning models featuring temporal residual connections

Inventors: Liangzhe Yuan (Los Angeles, CA); Yongzhe Wang (San Francisco, CA)
Assignee: GOOGLE LLC
G06N3/0464
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 12,737,594
App. No.
18/253,416
Granted
Sep 15, 2026
Kind
B2
Abstract

Systems and methods can include or leverage a machine-learned model (e.g., a convolutional neural network) that includes one or more temporal residual connections. In particular, each temporal residual connection can respectively supply one or more sets of intermediate feature data generated by a current instantiation of the model from a current sequential input to one or more other instantiations of the machine-learned model applied to process one or more other sequential inputs. For example, the other instantiations of the machine-learned model can include subsequent instantiations of the machine-learned model applied to process one or more subsequent sequential inputs that follow the current sequential input in a sequence and/or preceding instantiations of the machine-learned model applied to process one or more preceding sequential inputs that precede the current sequential input in a sequence.

Claims (53)

1 . A computing system for improved temporal processing of sequential data, the computing system comprising:

one or more processors; and

one or more non-transitory computer-readable media that collectively store:

a machine-learned convolutional neural network that comprises one or more temporal residual connections that respectively supply one or more sets of intermediate feature data generated from a current sequential input to a plurality of other instantiations of the machine-learned convolutional neural network applied to process a plurality of other sequential inputs; and

instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:

for each of a plurality of sequential inputs included in a sequence:

processing the current sequential input with at least a portion of a current instantiation of the machine-learned convolutional neural network to generate a current set of intermediate feature data;

storing the current set of intermediate feature data for provision to a plurality of subsequent instantiations of the machine-learned convolutional neural network applied to process a plurality of subsequent sequential inputs that are subsequent to the current sequential input in the sequence;

accessing a plurality of sets of preceding intermediate feature data generated by a plurality of preceding instantiations of the machine-learned convolutional neural network applied to process a plurality of preceding sequential inputs that precede the current sequential input in the sequence, wherein the plurality of sets of preceding intermediate feature data comprise feature maps from a plurality of different previous timestamps; and

generating a model output from the current instantiation of the machine-learned convolutional neural network based at least in part on the current set of intermediate feature data and the plurality of sets of preceding intermediate feature data.

2 . The computing system of claim 1 , wherein the one or more temporal residual connections consist only of forward-propagating temporal residual connections that supply the one or more sets of intermediate feature data generated from the current sequential input to the subsequent instantiations of the machine-learned convolutional neural network.

3 . The computing system of claim 1 , wherein the machine-learned convolutional neural network comprises both:

forward-propagating temporal residual connections that supply the one or more sets of intermediate feature data generated from the current sequential input to the subsequent instantiations of the machine-learned convolutional neural network; and

backward-propagating temporal residual connections that supply the one or more sets of intermediate feature data generated from the current sequential input to the preceding instantiations of the machine-learned convolutional neural network.

4 . The computing system of claim 1 , wherein at least one of the one or more temporal residual connections is configured to supply the one or more sets of intermediate feature data to a same layer of the plurality of instantiations of the machine-learned convolutional neural network.

5 . The computing system of claim 1 , wherein at least one of the one or more temporal residual connections is configured to supply the one or more sets of intermediate feature data to a different layer of the plurality of other instantiations of the machine-learned convolutional neural network.

6 . The computing system of claim 1 , wherein the one or more temporal residual connections comprise a plurality of temporal residual connections present at different respective depths within the machine-learned convolutional neural network.

7 . The computing system of claim 1 , wherein generating the model output from the current instantiation of the machine-learned convolutional neural network based at least in part on the current set of intermediate feature data and the plurality of sets of preceding intermediate feature data comprises:

combining at least one of the sets of preceding intermediate feature data with at least one existing set of feature data to form a combined set of feature data; and

generating the model output from the current instantiation of the machine-learned convolutional neural network based at least in part on the combined set of feature data.

8 . The computing system of claim 7 , wherein combining the at least one of the sets of preceding intermediate feature data with the at least one existing set of feature data to form the combined set of feature data comprises summing the at least one of the sets of preceding intermediate feature data with the at least one existing set of feature data.

9 . The computing system of claim 7 , wherein combining the at least one of the sets of preceding intermediate feature data with the at least one existing set of feature data to form the combined set of feature data comprises:

concatenating the at least one of the sets of preceding intermediate feature data with the at least one existing set of feature data; and

applying one or more convolutions to the concatenated data.

10 . The computing system of claim 7 , wherein combining the at least one of the sets of preceding intermediate feature data with the at least one existing set of feature data to form the combined set of feature data comprises:

concatenating the at least one of the sets of preceding intermediate feature data with the at least one existing set of feature data;

applying multiple convolutional filters to the concatenated data in parallel; and

combining the outputs of the multiple convolutional filters.

11 . The computing system of claim 10 , wherein the multiple convolutional filters have different respective filter sizes.

12 . The computing system of claim 10 , wherein the multiple convolutional filters have different respective dilation rates.

13 . The computing system of claim 7 , wherein the at least one existing set of feature data comprises the current set of intermediate feature data.

14 . The computing system of claim 1 , wherein the plurality of subsequent instantiations of the machine-learned convolutional neural network applied to process the plurality of subsequent sequential inputs comprise a next sequential instantiation of the machine-learned convolutional neural network applied to process a next sequential input in the sequence.

15 . The computing system of claim 1 , wherein the plurality of subsequent instantiations of the machine-learned convolutional neural network applied to process the plurality of subsequent sequential inputs comprise a greater-than-next sequential instantiation of the machine-learned convolutional neural network applied to process a greater-than-next sequential input in the sequence.

16 . The computing system of claim 1 , wherein the current set of intermediate feature data comprises an activation map for a convolutional layer of the machine-learned convolutional neural network.

17 . The computing system of claim 1 , wherein the machine-learned convolutional neural network comprises one or more convolutional layers followed by a long short term memory layer, wherein the one or more temporal residual connections are present at the one or more convolutional layers.

18 . The computing system of claim 1 , wherein the plurality of sequential inputs included in the sequence comprise a plurality of image frames included in a video.

19 . The computing system of claim 1 , wherein the plurality of sequential inputs included in the sequence comprise a plurality of sets of Light Detection and Ranging (LiDAR) data included in a LiDAR data sequence.

20 . The computing system of claim 1 , wherein the machine-learned convolutional neural network is configured to perform a task, wherein the task comprises action recognition or object detection.

21 . A computer-implemented method, the method comprising:

for each of a plurality of sequential inputs included in a sequence:

processing a current sequential input with at least a portion of a current instantiation of a machine-learned convolutional neural network to generate a current set of intermediate feature data;

storing the current set of intermediate feature data for provision to a plurality of subsequent instantiations of the machine-learned convolutional neural network applied to process a plurality of subsequent sequential inputs that are subsequent to the current sequential input in the sequence, wherein the current instantiation of the machine-learned convolutional neural network is connected to the plurality of subsequent instantiations of the machine-learned convolutional neural network via one or more temporal residual connections;

accessing a plurality of sets of preceding intermediate feature data generated by a plurality of preceding instantiations of the machine-learned convolutional neural network applied to process a plurality of preceding sequential inputs that precede the current sequential input in the sequence, wherein the current instantiation of the machine-learned convolutional neural network is connected to the a plurality of preceding instantiations of the machine-learned convolutional neural network via the one or more temporal residual connections, wherein the plurality of sets of preceding intermediate feature data comprise feature maps from a plurality of different previous timestamps; and

generating a model output from the current instantiation of the machine-learned convolutional neural network based at least in part on the current set of intermediate feature data and the plurality of sets of preceding intermediate feature data.

22 . One or more non-transitory computer-readable media that collectively store:

a machine-learned convolutional neural network that comprises one or more temporal residual connections that respectively supply one or more sets of intermediate feature data generated from a current sequential input to a plurality of other instantiations of the machine-learned convolutional neural network applied to process a plurality of other sequential inputs; and

computer-readable instructions for executing the machine-learned convolutional neural network

instructions that, when executed by one or more processors, cause a computing system to perform operations, the operations comprising:

for each of a plurality of sequential inputs included in a sequence:

processing the current sequential input with at least a portion of a current instantiation of the machine-learned convolutional neural network to generate a current set of intermediate feature data;

storing the current set of intermediate feature data for provision to a plurality of subsequent instantiations of the machine-learned convolutional neural network applied to process a plurality of subsequent sequential inputs that are subsequent to the current sequential input in the sequence;

accessing a plurality of sets of preceding intermediate feature data generated by a plurality of preceding instantiations of the machine-learned convolutional neural network applied to process a plurality of preceding sequential inputs that precede the current sequential input in the sequence, wherein the plurality of sets of preceding intermediate feature data comprise feature maps from a plurality of different previous timestamps; and

generating a model output from the current instantiation of the machine-learned convolutional neural network based at least in part on the current set of intermediate feature data and the plurality of sets of preceding intermediate feature data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 18, 2023
From: YUAN, LIANGZHE; WANG, YONGZHE
To: GOOGLE LLC
Reel/Frame 063681/0672 →
Continuity (2)
Provisional Application 63136772 · Jan 13, 2021
Related Publication 20230419082A1 · Dec 28, 2023
References Cited (23)
US 20200098139A1 · Kaplanyan et al. · 2020 [cited by applicant]
US 20200103483A1 · Hardy et al. · 2020 [cited by applicant]
US 20200225376A1 · Liu et al. · 2020 [cited by applicant]
US 20220157059A1 · Meng et al. · 2022 [cited by applicant]
US 20240153044A1 · Mihal · 2024 [cited by examiner]
CN 111930992 · 2020 [cited by applicant]
WO WO2019143025 · 2019 [cited by applicant]
Jang, B. et al., “Bi-Istm model to increase accuracy in text classification: combining word2vec cnn and attention mechanism,” Applied Sciences, vol. 10 (Aug. 24, 2020) 14 pp. (Year: 2020). [cited by examiner]
Kopuklu, O. et al., “Dissected 3d cnns: temporal skip connections for efficient online video processing,” downloaed from <arxiv.org/pdf/2009.14639v1> (Sep. 30, 2020) 10 pp. (Year: 2020). [cited by examiner]
Salur, M.U. et al., “A novel hybrid deep learning model for sentiment classification,” IEEE Access (Apr. 6, 2020) pp. 58080-58093. (Year: 2020). [cited by examiner]
Sun, X. et al., “A novel coding architecture for multi-line lidar point clouds based on clustering and convolutional Istm network,” IEEE Trans. on Intelligent Transportation Systems (vol. 23, Issue 3) (0 Nov. 2020) pp. … [cited by examiner]
Qui, T. et al., “Long short-term memory with dynamic skip connections,” The 33rd AAAI Conf. on Artificial Intelligence (2019) pp. 6481-6488. (Year: 2019). [cited by examiner]
Feichtenhofer, C. et al., “Temporal residual networks for dynamic scene recognition,” Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (2017) pp. 4728-4737. (Year: 2017). [cited by examiner]
International Preliminary Report on Patentability for Application No. PCT/US2021/064363, mailed Jul. 27, 2023, 10 pages. [cited by applicant]
Liu et al., “Looking Fast and Slow: Memory-Guided Mobile Video Object Detection”, arXiv:1903.10172v1, Mar. 25, 2019, 10 pages. [cited by applicant]
Liu et al., “Mobile Video Object Detection with Temporally-Aware Feature Maps”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 18-23, 2018, Salt Lake City, UT, pp. 5686-5695. [cited by applicant]
Carreira et al., “Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset.”, arXiv:1705.07750v3, Feb. 12, 2018, 10 pages. [cited by applicant]
He et al., “Deep Residual Learning for Image Recognition.”, arXiv:1512.03385v1, Dec. 10, 2015, 12 pages. [cited by applicant]
International Search Report for Application No. PCT/US2021/064363, mailed on Apr. 20, 2022, 2 pages. [cited by applicant]
Köpüklü et al., “Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing”, arxiv.org, Sep. 30, 2020, XP081774595, 10 pages. [cited by applicant]
Poggio, “Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex Theory of Deep Learning: View Project the MIT Vision Machine Project View Project”, Apr. 12, 2016, https://arxiv.org/pdf/… [cited by applicant]
Chinese Search Report Corresponding to Application No. 2021800830689 on May 14, 2025. [cited by applicant]
Chinese Search Report Corresponding to Application No. 2021800830689 on Oct. 9, 2025. [cited by applicant]