DETAILED 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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on July 12, 2025, October 21, 2025, February 18, 2026, June 11, 2026 and August 24, 2026 are being considered by the examiner.
Specification
35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, requires the specification to be written in “full, clear, concise, and exact terms.” The specification is replete with terms which are not clear, concise and exact. The specification should be revised carefully in order to comply with 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112. Examples of some unclear, inexact or verbose terms used in the specification are: paragraph [0042] in page 10, blank after “a schedule” and blank before “is the number of epochs”.
The disclosure is objected to because of the following informalities: paragraph [0042] in page 10, “The input sequence of the poses is interleaved by ground-truth poses and self-generated poses [P1; P2; . . . ; Ps; Ps+1; . . . ; Ps+10; Ps+11; . . . ], where Pi is the self-generated poses (student forcing steps), and Pi is the ground-truth poses (teacher forcing steps)”. However, the specification uses one “Pi” representing both “self-generated poses ” and “ground-truth poses”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention.
Independent claims 1, 11 and 17 recites the limitation “generating a sequence of training poses by interleaving the first set of training poses with the second set of training poses”. Each claim clearly recites “generating a first set of training poses for an animated character using a first machine learning model” and “generating a second set of training poses using a second machine learning model”.
In view of the specification of the present application, only paragraph [0042] of the specification describes “The training gradually transitions from a teacher forcing training to an auto-regressive training. The input sequence of the poses is interleaved by ground-truth poses and self-generated poses [P1; P2; . . . ; Ps; Ps+1; . . . ; Ps+10; Ps+11; . . . ], where Pi is the self-generated poses (student forcing steps), and Pi is the ground-truth poses (teacher forcing steps).”. However, the specification does not support “ground-truth poses (teacher forcing steps)” and “self-generated poses (student forcing steps)” generated by different machine learning models. Thus, the specification does not enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make the invention commensurate in scope with these claims. Therefore the full scope of the claim does not have an appropriate description in the Application as originally filed. Accordingly, the claims are rejected under U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph.
Dependent claims 2-10 depend upon independent claim 1, dependent claims 12-16 depend upon independent claim 11, dependent claims 18-20 depend upon independent claim 17. They are rejected at least due to their respective dependencies from a rejected claim.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Independent claims 1, 11 and 17 recites the limitation “generating a sequence of training poses by interleaving the first set of training poses with the second set of training poses”.
However, each claim clearly recites “generating a first set of training poses for an animated character using a first machine learning model” and “generating a second set of training poses using a second machine learning model”.
In view of the specification of the present application, only paragraph [0042] of the specification describes “The training gradually transitions from a teacher forcing training to an auto-regressive training. The input sequence of the poses is interleaved by ground-truth poses and self-generated poses [P1; P2; . . . ; Ps; Ps+1; . . . ; Ps+10; Ps+11; . . . ], where Pi is the self-generated poses (student forcing steps), and Pi is the ground-truth poses (teacher forcing steps).”. However, the specification does not support “ground-truth poses (teacher forcing steps)” and “self-generated poses (student forcing steps)” generated by different machine learning models. The issue is persons of ordinary skill in the art reading the specification is not able to understand what method or system applicant is intending to encompass. Therefore, the examiner deems the claims indefinite as they fail to particularly point out and distinctly claim what Applicant regards as the invention. Accordingly, the claims are rejected under U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph.
Dependent claims 2-10 depend upon independent claim 1, dependent claims 12-16 depend upon independent claim 11, dependent claims 18-20 depend upon independent claim 17. They are rejected at least due to their respective dependencies from a rejected claim.
Examiner’s Comment
Claims 1-20 have not art rejection but rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph and U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph. A final determination of patentability, after further search, will be mode upon resolution of above 35 U.S.C. 112 rejection.
The information disclosure statement (IDS) submitted on July 12, 2025, October 21, 2025, February 18, 2026, June 11, 2026 and August 24, 2026 have been considered by the examiner.
The examiner has completed the prior art reference search and discovered the closest prior art references:
The prior art reference Bocquelet et al (U. S. Patent Application Publication 2022/0076472 A1) discloses a method of generating or modifying poses in an animation of a character. Bocquelet discloses a machine learning (ML) prediction system (As shown in FIG. 1) takes a variable number and type of input effectors and determines full body joint orientations. The system is trained for posing per type of character. During training of an ML pose prediction system, the system obtains an input training set “the plurality of input poses” and performs randomly translating and randomly rotating character poses in the plurality of input poses to increase the possible applications of the ML pose prediction system 100 along with increasing the output quality of the ML pose prediction system when posing a character.
The prior art reference Wang et al (U. S. Patent Application Publication 2020/0342646 A1) discloses system and method for creating videos including realistic and smooth human body movement in synchronization with music. The system includes a music-to-pose neural network (NN) and a pose-to-dance NN. During the training of the neural network, a first step of downloading a video of a human being dancing from the Internet, extracting music from the downloaded video, extracting pose key points (body part landmarks) of the human dancing in the video, and labeling samples of the extracted music with the extracted pose key points to create music-pose key points (ground truth) pairs; a second step of inputting music to the neural network to predict pose key points, comparing the predicted pose key points with the ground truth pairs (extracted from the videos) to determine information indicating whether the network has learned correct information or not, and using the information to adjust the neural network (As shown in FIG. 2).
The prior art reference Cappello et al (U. S. Patent Application Publication 2020/0167984 A1) discloses a method for determining identifiers for tagging frames of an animation with by performing a pre-determined motion using a machine learning mode. The method obtains data indicating a pose of an animated object in a plurality of frames, uses frames of the input pose data to train the machine learning for determining identifiers for changes in pose of characters having this form.
The prior art reference FEDYUKOV et al (U. S. Patent Application Publication 2021/0049811 A1) discloses a system for building a parametric model of a person’s body using a neural network and machine learning algorithm. The neural network is trained using images of different people from different angles with a known texture map, and the error in restoring such a texture map is penalized.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Xilin Guo whose telephone number is (571)272-5786. The examiner can normally be reached Monday - Friday 9:00 AM-5:30 PM EST.
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, Daniel Hajnik can be reached at 571-272-7642. 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.
/XILIN GUO/Primary Examiner, Art Unit 2616
Prosecution Insights