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 .
Status of Claims
2. This is a final action on the merits in response to the reply received 4/7/2026.
Response to Arguments
Applicant’s arguments have been considered but are moot in view of new grounds of rejections.
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.
Claim(s) 1, 3-8, 10-16, 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over US 20220116633 A1-Jiang et al (Hereinafter referred to as “Jiang”), in view of US 20210390410 A1-Vaswani et al (Hereinafter referred to as “Vaswani”), in further view of US 20230010160 A1-Chen et al (Hereinafter referred to as “Chen”), in view of US 20220261960 A1-Wang et al (Hereinafter referred to as “Wang”).
Regarding claim 1, Jiang discloses a method of decoding encoded video data ([0002]), the method comprising:
determining, from the encoded video data, a block of a picture ([0032], wherein plurality of original image frames are partitioned into spatial blocks, each spatial block can be further partitioned into smaller blocks iteratively);
applying a neural network (NN)-based filter to the block to generate a filtered block ([0007], wherein using neural network with loop filters), wherein the NN-based filter comprises a plurality of backbone blocks and at least one of the backbone blocks comprises an attention block configured to process non- normalized data (According to instant applicant’s specification, [0167], discloses that Backbone is nothing more than some feature extraction. To be consistent with applicant’s specification, Jiang discloses feature extraction in fig. 4-5).
determining a decoded version of the block based on the filtered block ([0032], wherein On the decoder side, the quantized residual ŷ.sub.t is first de-quantized (e.g., through inverse transformation such as Inverse Discrete Cosine Transform (IDCT)) to obtain a recovered residual {circumflex over (r)}.sub.1, and then the recovered residual {circumflex over (r)}.sub.t is added back to the predicted frame {tilde over (x)}.sub.t to obtain a reconstructed frame by {circumflex over (x)}.sub.t={tilde over (x)}.sub.t+{circumflex over (r)}.sub.t); and outputting a decoded version of the picture comprising the decoded version of the block ([0033-0034]).
Jiang fails to disclose NN-based filter comprises a plurality of backbone blocks and at least one of the backbone blocks comprises an attention block configured to process non- normalized data
However, in the same field of endeavor, Vaswani discloses NN-based filter comprises a backbone block and at least one of the backbone blocks comprises an attention block configured to process non- normalized data (fig. 1 shows a backbone that comprise a self attention layer; [0062], wherein while the backbone neural network can be a ResNet-based backbone with one or more of the convolutional layers replaced with local self-attention layers. For example, the backbone can be a ResNet-50 or a ResNet-101 backbone with the last two, three, or four, convolutional layers replaced with local self-attention layers)
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to modify the method disclosed by Jiang to disclose NN-based filter comprises a backbone block and at least one of the backbone blocks comprises an attention block configured to process non- normalized data as taught by Vaswani, to improve the speed, the effectiveness, or both of the training process ([0071], Vaswani).
Jiang and Vaswani fail to disclose NN-based filter comprise a plurality of backbone blocks.
However, in the same field of endeavor, Chen discloses a NN-based filter comprise a plurality of backbone blocks ([0095], wherein a plurality of feature extraction subnetworks are available).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to modify the method disclosed by Jiang and Vaswani to disclose NN-based filter comprises a plurality of backbone blocks and at least one of the backbone blocks comprises an attention block configured to process non- normalized data as taught by Chen, thereby improving processing accuracy of the neural network for the multimodal data ([0100], Chen).
Jiang, Vaswani and Chen fail to disclose a plurality of cascaded backbone blocks
However, in the same field of endeavor, Wang discloses NN-based filter comprise a plurality of cascaded backbone blocks ([0091], Wang discloses using a convolution layer, which is a NN filter, to obtain filter results. The Filter comprises sequentially performing extractions using residual blocks that are cascaded).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to modify the method disclosed by Jiang, Vaswani, and Chen to disclose NN-based filter comprise a plurality of cascaded backbone blocks as taught by Wang, thereby to improve the picture quality, which is conducive to improving the video viewing experience of users ([0023], Wang)
Regarding claim 3, Vaswani discloses the method of claim 1, wherein the attention block processes the non-normalized data without a normalization layer (Fig 1, shows no normalization layer).
Regarding claim 4, Jiang discloses the method of claim 1, wherein the NN-based filter comprises a plurality of convolution layers (jiang, [0055], plurality convolution layers, and the attention block is configured to receive inputs from the one or more convolution layers ([0061], Jiang).
Regarding claim 5, jiang discloses the method of claim 1, wherein the attention block comprises a plurality of convolutions layers configured to generate query, key, and value inputs ([0045]).
Regarding claim 6, Vaswani discloses the method of claim 1, wherein the plurality of backbone blocks consists of 24 blocks ([0062], resnet 50 has 50 blocks), and the 24 backbone blocks consist of 2 backbone blocks that include attention blocks ([0062], wherein 2-4 are replaced with attention layers).
Regarding claim 7, Jiang discloses the method of claim 1, wherein the method of decoding is performed as part of a video encoding process ([0032]).
Regarding claim 8, analyses are analogous to those presented for claim 1 and are applicable for claim 8, Device with memory and processors (Jiang, fig 2).
Regarding claim 10, analyses are analogous to those presented for claim 3 and are applicable for claim 10.
Regarding claim 11, analyses are analogous to those presented for claim 4 and are applicable for claim 11.
Regarding claim 12, analyses are analogous to those presented for claim 5 and are applicable for claim 12.
Regarding claim 13, analyses are analogous to those presented for claim 6 and are applicable for claim 13.
Regarding claim 14, Jiang discloses the device of claim 8, further comprising a display configured to display decoded video data ([0025]).
Regarding claim 15, Jiang discloses the device of claim 8, wherein the device comprises one or more of a camera, a computer, a mobile device, a broadcast receiver device, or a set-top box ([0019]).
Regarding claim 16, analyses are analogous to those presented for claim 1 and are applicable for claim 16.
Regarding claim 18, analyses are analogous to those presented for claim 3 and are applicable for claim 18.
Regarding claim 19, analyses are analogous to those presented for claim 4 and are applicable for claim 19.
Regarding claim 20, analyses are analogous to those presented for claim 6 and are applicable for claim 20.
Claim(s) 2, 9, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over US 20220116633 A1-Jiang et al (Hereinafter referred to as “Jiang”), in view of US 20210390410 A1-Vaswani et al (Hereinafter referred to as “Vaswani”), in further view of US 20230010160 A1-Chen et al (Hereinafter referred to as “Chen”), in view of US 20220261960 A1-Wang et al (Hereinafter referred to as “Wang”), in further view of US 20220160433 A1-Rafii-Tari et al (hereinafter referred to as “Rafi”).
Regarding claim 2, Jiang discloses the method of claim 1 (see claim 1),
Jiang, Vaswani, and Chen fail to discloses wherein the attention block performs only multiplication and addition operations.
However, in the same field of endeavor, Rafi discloses determining, from the encoded video data, a block of a picture ([0055]); applying a neural network (NN)-based filter to the block to generate a filtered block([0040]), wherein the NN-based filter comprises a backbone block ([0040]) and attention block ([0052]) determining a decoded version of the block based on the filtered block [0055] and outputting a decoded version of the picture comprising the decoded version of the block ([0055]); wherein the attention block performs only multiplication and addition operations ([0053], wherein common attention techniques are dot-product attention, which uses the dot product between vectors to determine attention. Dot product uses multiplication and addition)
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to modify the method disclosed by Jiang, Vaswani, and Chen to disclose wherein the attention block performs only multiplication and addition operations as taught by Rafi, thereby improving real time communication ([0061], Rafi).
Regarding claim 9, analyses are analogous to those presented for claim 2 and are applicable for claim 9.
Regarding claim 17, analyses are analogous to those presented for claim 2 and are applicable for claim 17.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LERON BECK whose telephone number is (571)270-1175. The examiner can normally be reached M-F 8 am-5pm.
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, David Czekaj can be reached at (571) 272-7327. 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.
LERON . BECK
Examiner
Art Unit 2487
/LERON BECK/Primary Examiner, Art Unit 2487
Prosecution Insights