公开(公告)号：US20220366317A1

公开(公告)日：2022-11-17

申请号：US17484623

申请日：2021-09-24

Applicant: salesforce.com, inc.

Inventor： Mingfei Gao ,  Zeyuan Chen ,  Ran Xu

IPC: G06N20/20 ,  G06N5/00 ,  G06N5/04

Abstract: Embodiments described a field extraction system that does not require field-level annotations for training. Specifically, the training process is bootstrapped by mining pseudo-labels from unlabeled forms using simple rules. Then, a transformer-based structure is used to model interactions between text tokens in the input form and predict a field tag for each token accordingly. The pseudo-labels are used to supervise the transformer training. As the pseudo-labels are noisy, a refinement module that contains a sequence of branches is used to refine the pseudo-labels. Each of the refinement branches conducts field tagging and generates refined labels. At each stage, a branch is optimized by the labels ensembled from all previous branches to reduce label noise.

公开(公告)号：US11232308B2

公开(公告)日：2022-01-25

申请号：US16394964

申请日：2019-04-25

Applicant: salesforce.com, inc.

Inventor： Mingfei Gao ,  Richard Socher ,  Caiming Xiong

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06N3/00

Abstract: Embodiments described herein provide a two-stage online detection of action start system including a classification module and a localization module. The classification module generates a set of action scores corresponding to a first video frame from the video, based on the first video frame and video frames before the first video frames in the video. Each action score indicating a respective probability that the first video frame contains a respective action class. The localization module is coupled to the classification module for receiving the set of action scores from the classification module and generating an action-agnostic start probability that the first video frame contains an action start. A fusion component is coupled to the localization module and the localization module for generating, based on the set of action scores and the action-agnostic start probability, a set of action-specific start probabilities, each action-specific start probability corresponding to a start of an action belonging to the respective action class.

公开(公告)号：US20210357687A1

公开(公告)日：2021-11-18

申请号：US16931228

申请日：2020-07-16

Applicant: salesforce.com, inc.

Inventor： Mingfei Gao ,  Yingbo Zhou ,  Ran Xu ,  Caiming Xiong

IPC: G06K9/62 ,  G06K9/00 ,  G06F17/18 ,  G06N3/08

Abstract: Embodiments described herein provide systems and methods for a partially supervised training model for online action detection. Specifically, the online action detection framework may include two modules that are trained jointly—a Temporal Proposal Generator (TPG) and an Online Action Recognizer (OAR). In the training phase, OAR performs both online per-frame action recognition and start point detection. At the same time, TPG generates class-wise temporal action proposals serving as noisy supervisions for OAR. TPG is then optimized with the video-level annotations. In this way, the online action detection framework can be trained with video-category labels only without pre-annotated segment-level boundary labels.