CTNF 18/937,628 CTNF 86788 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-21-aia AIA Claim (s) 1-20 , is/are rejected under 35 U.S.C. 103 as being unpatentable over Li (US PGPUB 2023/0154188 A1) and further in view of Gavrilyuk (US PGPUB 2019/0147284 A1) . As per claim 1, Li discloses a computer-implemented method for action detection (Li, Figs. 1-8), comprising: encoding a text feature of an input textual description of an action using a visual language model (VLM) (Li, Fig. 2:204:222:225, shows text input 204 provided to text encoder of VLM 225); encoding a video feature of an input video using the VLM (Li, Fig. 2:220, video encoder); Li does not explicitly disclose recognizing the action in the video, based on the text feature and the video feature, to localize the action within the video; and locating a person performing the action within the video using the VLM. Gavrilyuk discloses recognizing the action in the video, based on the text feature and the video feature, to localize the action within the video (Gavrilyuk, Fig. 8:800, and paragraphs 7, 27, 29, 32, 65, 70, and 94, discloses The object tracking model is further configured for localizing the action and the actor in the sequence of frames based on the natural language query); and locating a person performing the action within the video using the VLM (Gavrilyuk, Fig. 8:800, and paragraphs 7, 29, 32, 65, and 70, discloses localizing the action and the actor). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Li teachings by implementing action and actor localization module to the system, as taught by Gavrilyuk. The motivation would be to improve object localization systems to localize objects in a video based on a natural language query by discriminating actions performed by the objects (paragraphs 6 and 29), as taught by Gavrilyuk. As per claim 2, Li in view of Gavrilyuk further discloses the method of claim 1, wherein recognizing the action includes applying a model that applies a mixer to each frame of the input video (Gavrilyuk, paragraphs 27, 32 and 62, discloses n this configuration, dynamic filters are generated based on the natural language query. The dynamic filters may be convolved with each frame of the sequence of frames to perform pixel-wise segmentation. The action and the actor may be localized based on the pixel-wise segmentation. An object that is performing an action, such as a jumping man, a flying bird, or a moving car, may be referred to as an actor). As per claim 3, Li in view of Gavrilyuk further discloses the method of claim 2, wherein the mixer recursively updates temporal queries, spatial queries, and person boxes from a previous video frame to predict person scores and action scores for a current video frame (Gavrilyuk, paragraphs 27, 32, 37, 43, 62-65, 104 and 109, discloses The output of the deep convolutional network 350 is a classification score 366 for the input data 352. The classification score 366 may be a set of probabilities, where each probability is the probability of the input data including a feature from a set of features). As per claim 4, Li in view of Gavrilyuk further discloses the method of claim 3, wherein the mixer uses query-query mixing and query-video mixing to update the spatial queries (Gavrilyuk, paragraphs 64 and 101-103). As per claim 5, Li in view of Gavrilyuk further discloses the method of claim 3, wherein the mixer uses query-query mixing, query-video mixing, and an adaptive semantic condition to update the temporal queries (Gavrilyuk, paragraphs 27, 32, 64 and 92-93). As per claim 6, Li in view of Gavrilyuk further discloses the method of claim 3, wherein the temporal queries are discriminative of action labels that were used during training as well as previously unseen terms (Gavrilyuk, paragraphs 34, 55, 70, and 104). As per claim 7, Li in view of Gavrilyuk further discloses the method of claim 3, wherein the mixer outputs a box locating the person, a person score to determine that the box is kept, and an action score that assigns an action category to the box (Li, paragraphs 58-59, and 67-68). As per claim 8, Li in view of Gavrilyuk further discloses the method of claim 1, wherein recognizing the action includes determining a similarity between the text feature and the video feature (Li, paragraph 67 and 79). As per claim 9, Li in view of Gavrilyuk further discloses the method of claim 1, further comprising performing a driving action responsive to the action (Gavrilyuk, paragraph 112). As per claim 10, Li in view of Gavrilyuk further discloses the method of claim 9, wherein the driving action is selected from the group consisting of a braking action, an acceleration action, and a steering action (Gavrilyuk, paragraph 112, discloses “an apparatus, such as an autonomous vehicle, may be controlled to avoid a collision or navigate to a destination. For example, the model may be defined in an autonomous vehicle, a semi-autonomous vehicle”). As per claim 11, Li discloses a system for action detection (Li, Fig. 6:600), comprising: a hardware processor (Li, Fig. 6:600:610); and a memory (Li, Fig. 6:620) that stores a computer program which, when executed by the hardware processor, causes the hardware processor (Li, paragraph 49) to: For rest of claim limitations please see the analysis of claim 1. As per claim 12, please see the analysis of claim 2. As per claim 13, please see the analysis of claim 3. As per claim 14, please see the analysis of claim 4. As per claim 15, please see the analysis of claim 5. As per claim 16, please see the analysis of claim 6. As per claim 17, please see the analysis of claim 7. As per claim 18, please see the analysis of claim 8. As per claim 19, please see the analysis of claim 9. As per claim 20, please see the analysis of claim 10. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to SYED Z HAIDER whose telephone number is (571)270-5169. The examiner can normally be reached MONDAY-FRIDAY 9-5:30 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, SAM K Ahn can be reached at 571-272-3044. 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. /SYED HAIDER/Primary Examiner, Art Unit 2633 Application/Control Number: 18/937,628 Page 2 Art Unit: 2633 Application/Control Number: 18/937,628 Page 3 Art Unit: 2633 Application/Control Number: 18/937,628 Page 7 Art Unit: 2633
Prosecution Insights