Office Action Predictor
Last updated: April 15, 2026
Application No. 18/874,513

VIDEO GENERATION BASED ON 3D WINDOW ATTENTION

Non-Final OA §103
Filed
Dec 12, 2024
Examiner
DUBASKY, GIGI L
Art Unit
2421
Tech Center
2400 — Computer Networks
Assignee
Beijing Zitiao Network Technology Co., LTD.
OA Round
1 (Non-Final)
74%
Grant Probability
Favorable
1-2
OA Rounds
2y 10m
To Grant
99%
With Interview

Examiner Intelligence

Grants 74% — above average
74%
Career Allow Rate
451 granted / 610 resolved
+15.9% vs TC avg
Strong +36% interview lift
Without
With
+35.6%
Interview Lift
resolved cases with interview
Typical timeline
2y 10m
Avg Prosecution
21 currently pending
Career history
631
Total Applications
across all art units

Statute-Specific Performance

§101
6.4%
-33.6% vs TC avg
§103
50.1%
+10.1% vs TC avg
§102
18.7%
-21.3% vs TC avg
§112
10.3%
-29.7% vs TC avg
Black line = Tech Center average estimate • Based on career data from 610 resolved cases

Office Action

§103
1178DETAILED ACTION Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. Information Disclosure Statement The information disclosure statement (IDS) submitted on 12/02/2025 was filed on or after the effective filing date of the instant application on 12/12/2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Claim Objections Claims 1-20 are objected to because of the following informalities: Claims 1, 10 and 19 recite “3D” which is an acronym without describing its definition earlier in the claim. Claims 4 and 13 recite “2D” which is an acronym without describing its definition earlier in the claim. Other dependent claims are objected the same. Appropriate corrections are required. Claim Rejections - 35 USC § 103 The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over He et al (US 2023/0130006) in view of Yao et al (CN 117830099 B – an English translation is provided herein with cited paragraphs corresponding to original document). Regarding claim 1, He discloses a method for video generation, comprising: dividing a video feature of an input video into a plurality of 3D video windows based on a predetermined window size, the plurality of 3D video windows comprising a first video window and a second video window (¶ [0041]-[0042] and ¶ [0053]-[0055] for dividing a video feature of an input data into three-dimensional video sliding windows with a predetermined size to extract local and global video features); updating the video feature by determining video attention within each video window of the plurality of 3D video windows, wherein the video attention associated with the first video window is independent from the second video window (¶ [0055]-[0070] for merging the extracted local feature and global feature to obtain target video feature (as “updating the video feature”) by using self-attention and cross-attention algorithms performed within each of non-overlapped video feature sliding windows). He discloses determining a target querying video based on the improved target video feature (¶ [0081]-[0084]), but is silent about generating a target video based on the updated video feature. Yao discloses dividing video characteristic of an input video into three-dimensional sliding windows spanning multiple frames, using a self-attention mechanism in each of sliding windows and using a cross-attention operation to correct or update the generated video characteristic and generating a super-resolution video based on the updated video characteristic (¶ [0077]-[0088]). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify He system with the teaching of Yao about generating a target super-resolution video based on updated video feature, so to provide an alternative implementation of using the pre-processed target video feature not only to determine querying video but also to generate a higher resolution video in the benefits of enhancing system. Regarding claim 2, He in view of Yao discloses the method as discussed in the rejection of claim 1. The combined system further discloses wherein the predetermined window size is independent from a size of the input video (taught by He; ¶ [0053]-[0055]). Regarding claim 3, He in view of Yao discloses the method as discussed in the rejection of claim 2. The combined system further discloses wherein the plurality of 3D video windows comprise at least one window whose size is smaller than the predetermined window size (taught by He; ¶ [0053]-[0055]). Regarding claim 4, He in view of Yao discloses the method as discussed in the rejection of claim 1. The combined system further discloses determining a window feature of a target 3D video window; converting the window feature into a 2D tensor; and determining the video attention of the target 3D video window based on the 2D tensor (taught by Yao; Figure2 and ¶ [0068]-[0088]). Regarding claim 5, He in view of Yao discloses the method as discussed in the rejection of claim 4. The combined system further discloses wherein determining the video attention of the target 3D video window based on the 2D tensor comprises: determining a set of query vectors, a first set of key vectors and a first set of value vectors based on the 2D tensor; concatenating the first set of key vectors with a second set of key vectors to obtain an updated set of key vectors, and concatenating the first set of value vectors with a second set of value vectors to obtain an updated set of value vectors, wherein the second set of key vectors and the second set of value vectors are determined based on a text associated with the input video; and determining the video attention based on the set of query vectors, the updated set of key vectors and the updated set of value vectors (taught by Yao; ¶ [0022]-[0028] and ¶ [0080]-[0082]). Regarding claim 6, He in view of Yao discloses the method as discussed in the rejection of claim 5. The combined system further discloses wherein the text comprises an input text or a text generated based on the input video (taught by Yao; ¶ [0022]-[0028] and ¶ [0080]-[0082]). Regarding claim 7, He in view of Yao discloses the method as discussed in the rejection of claim 1. The combined system further discloses wherein the video attention comprises a first round of video attention, the plurality of 3D video windows comprise a first plurality of 3D video windows, and before generating a target video based on the updated video feature, the method further comprises: dividing the updated video feature a second plurality of 3D video windows based on the predetermined window size, wherein a first starting position of the second plurality of 3D video windows is determined based on a second starting position of the first plurality of 3D video windows and an offset; and updating the video feature by determining video attention within each video window of the second plurality of 3D video windows (taught by He; Figures 3-4; ¶ [0052]-[0067]; and taught by Yao; Figures 3-4). Regarding claim 8, He in view of Yao discloses the method as discussed in the rejection of claim 7. The combined system further discloses wherein the offset is relevant to the predetermined window size (taught by He; Figures 3-4; ¶ [0052]-[0067]). Regarding claim 9, He in view of Yao discloses the method as discussed in the rejection of claim 1. The combined system further discloses wherein a first image quality of the target video is better than a second image quality of the input video (taught by Yao; ¶ [0077]-[0088]). Regarding claims 10-18, all limitations of claims 10-18 are analyzed and rejected corresponding to claims 1-9 respectively. Regarding claims 19-20, all limitations of claims 19-20 are analyzed and rejected corresponding to claims 1-2 respectively. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to GIGI L DUBASKY whose telephone number is (571)270-5686. The examiner can normally be reached M-F 9:00-5:00. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Nathan Flynn can be reached at 571-272-1915. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /GIGI L DUBASKY/Primary Examiner, Art Unit 2421
Read full office action

Prosecution Timeline

Dec 12, 2024
Application Filed
Dec 22, 2025
Non-Final Rejection — §103
Mar 30, 2026
Response Filed

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12593078
Live Video Playback
2y 5m to grant Granted Mar 31, 2026
Patent 12587695
PER-SEGMENT PARAMETERS FOR CONTENT
2y 5m to grant Granted Mar 24, 2026
Patent 12587706
REBUFFERING REDUCTION IN ADAPTIVE BIT-RATE VIDEO STREAMING
2y 5m to grant Granted Mar 24, 2026
Patent 12581161
METHODS AND APPARATUS TO CREATE CANDIDATE REFERENCE SIGNATURES FROM SIGNATURE FRAGMENTS
2y 5m to grant Granted Mar 17, 2026
Patent 12568272
VIDEO STUTTER PREDICTION METHOD AND APPARATUS, DEVICE AND MEDIUM
2y 5m to grant Granted Mar 03, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
74%
Grant Probability
99%
With Interview (+35.6%)
2y 10m
Median Time to Grant
Low
PTA Risk
Based on 610 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in for Full Analysis

Enter your email to receive a magic link. No password needed.

Free tier: 3 strategy analyses per month