IP Library Granted Patent US 11,468,680
Granted Patent B2
US 11,468,680 · App. 16/998,404 · Granted Oct 11, 2022

Shuffle, attend, and adapt: video domain adaptation by clip order prediction and clip attention alignment

Inventors: Gaurav Sharma (Newark, CA); Samuel Schulter (New York, NY); Jinwoo Choi (Blacksburg, VA)
G06V20/48G06K9/6259G06N3/0481G06N3/08G06V20/41G06V20/46G06V40/20
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 11,468,680
App. No.
16/998,404
Granted
Oct 11, 2022
Kind
B2
Abstract

A method for performing video domain adaptation for human action recognition is presented. The method includes using annotated source data from a source video and unannotated target data from a target video in an unsupervised domain adaptation setting, identifying and aligning discriminative clips in the source and target videos via an attention mechanism, and learning spatial-background invariant human action representations by employing a self-supervised clip order prediction loss for both the annotated source data and the unannotated target data.

Claims (139)

1. A computer-implemented method executed on a processor for performing video domain adaptation for human action recognition, the method comprising:

using annotated source data from a source video and unannotated target data from a target video in an unsupervised domain adaptation setting;

identifying and aligning discriminative clips in the source and target videos via an attention mechanism; and

learning spatial-background invariant human action representations by employing a self-supervised clip order prediction loss for both the annotated source data and the unannotated target data.

2. The method of claim 1 , wherein the attention mechanism suppresses temporal background clips.

3. The method of claim 2 , wherein the attention mechanism is learned jointly for video-level adaptation and classification.

4. The method of claim 3 , wherein the discriminative clips are selected by employing an auxiliary network such that video features are derived as a weighted combination of the identified discriminative clips.

5. The method of claim 4 , wherein the attention mechanism is pre-trained with a binary cross-entropy loss to obtain a ground truth attention vector.

6. The method of claim 1 , wherein the clip order prediction (COP) loss is given as:

L

COP

=

-

𝔼

(

x

,

y

)

(

X

,

Y

)

k

=

1

M

!

[

y

k

log

f

O

(

ϕ

)

]

where f O is a linear classification function for COP, ϕ=Ω(Φ(x 1 ), . . . , Φ(x M )) is a ReLU activation of multi-layer perceptron (MLP), which takes M clip features as input, and (x,y) are data.

7. The method of claim 1 , wherein a domain adversarial loss helps a shuffle and attend video domain adaptation (SAVA) model to align video-level features between the source and target videos.

8. A non-transitory computer-readable storage medium comprising a computer-readable program for performing video domain adaptation for human action recognition, wherein the computer-readable program when executed on a computer causes the computer to perform the steps of:

using annotated source data from a source video and unannotated target data from a target video in an unsupervised domain adaptation setting;

identifying and aligning discriminative clips in the source and target videos via an attention mechanism; and

learning spatial-background invariant human action representations by employing a self-supervised clip order prediction loss for both the annotated source data and the unannotated target data.

9. The non-transitory computer-readable storage medium of claim 8 , wherein the attention mechanism suppresses temporal background clips.

10. The non-transitory computer-readable storage medium of claim 9 , wherein the attention mechanism is learned jointly for video-level adaptation and classification.

11. The non-transitory computer-readable storage medium of claim 10 , wherein the discriminative clips are selected by employing an auxiliary network such that video features are derived as a weighted combination of the identified discriminative clips.

12. The non-transitory computer-readable storage medium of claim 11 , wherein the attention mechanism is pre-trained with a binary cross-entropy loss to obtain a ground truth attention vector.

13. The non-transitory computer-readable storage medium of claim 8 , wherein the clip order prediction (COP) loss is given as:

L

COP

=

-

𝔼

(

x

,

y

)

(

X

,

Y

)

k

=

1

M

!

[

y

k

log

f

O

(

ϕ

)

]

where f O is a linear classification function for COP, ϕ=Φ(Ψ(x 1 ), . . . , Φ(x M )) is a ReLU activation of multi-layer perceptron (MLP), which takes M clip features as input, and (x,y) are data.

14. The non-transitory computer-readable storage medium of claim 8 , wherein a domain adversarial loss helps a shuffle and attend video domain adaptation (SAVA) model to align video-level features between the source and target videos.

15. A system for performing video domain adaptation for human action recognition, the system comprising:

a memory; and

one or more processors in communication with the memory configured to:

use annotated source data from a source video and unannotated target data from a target video in an unsupervised domain adaptation setting;

identify and align discriminative clips in the source and target videos via an attention mechanism; and

learn spatial-background invariant human action representations by employing a self-supervised clip order prediction loss for both the annotated source data and the unannotated target data.

16. The system of claim 15 , wherein the attention mechanism suppresses temporal background clips.

17. The system of claim 16 , wherein the attention mechanism is learned jointly for video-level adaptation and classification.

18. The system of claim 17 , wherein the discriminative clips are selected by employing an auxiliary network such that video features are derived as a weighted combination of the identified discriminative clips.

19. The system of claim 18 , wherein the attention mechanism is pre-trained with a binary cross-entropy loss to obtain a ground truth attention vector.

20. The system of claim 15 , wherein the clip order prediction (COP) loss is given as:

L

COP

=

-

𝔼

(

x

,

y

)

(

X

,

Y

)

k

=

1

M

!

[

y

k

log

f

O

(

ϕ

)

]

where f O is a linear classification function for COP, ϕ=χ(Φ(x 1 ), . . . , Φ(x M )) is a ReLU activation of multi-layer perceptron (MLP), which takes M clip features as input, and (x,y) are data.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 22, 2022
From: NEC LABORATORIES AMERICA, INC.
To: NEC CORPORATION
Reel/Frame 060855/0623 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 20, 2020
From: SHARMA, GAURAV; SCHULTER, SAMUEL; CHOI, JINWOO
To: NEC LABORATORIES AMERICA, INC.
Reel/Frame 053552/0876 →
Continuity (3)
Provisional Application 62935674 · Nov 15, 2019
Provisional Application 62892047 · Aug 27, 2019
Related Publication 20210064883A1 · Mar 4, 2021