To address such a problem, this paper proposes a novel efficient entities and relations extraction model called TDEER, which stands for Translating Decoding Schema for Joint Extraction of Entities and Relations.
Ranked #1 on Joint Entity and Relation Extraction on NYT
Human action recognition is a quite hugely investigated area where most remarkable action recognition networks usually use large-scale coarse-grained action datasets of daily human actions as inputs to state the superiority of their networks.
For a platform with billions of products, it is extremely time-costly and labor-expensive to manually pick and organize qualified images.
In this paper, we proposed an automatic Scenario-based Multi-product Advertising Copywriting Generation system (SMPACG) for E-Commerce, which has been deployed on a leading Chinese e-commerce platform.
At its core is a new lighting model (dubbed DSGLight) based on depth-augmented Spherical Gaussians (SG) and a Graph Convolutional Network (GCN) that infers the new lighting representation from a single LDR image of limited field-of-view.
In addition, this kind of product description should be eye-catching to the readers.
It consists of two main components: 1) natural language generation, which is built from a transformer-pointer network and a pre-trained sequence-to-sequence model based on millions of training data from our in-house platform; and 2) copywriting quality control, which is based on both automatic evaluation and human screening.
The task of visual question generation (VQG) aims to generate human-like neural questions from an image and potentially other side information (e. g., answer type or the answer itself).
Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease-positive individuals in the wider population.
We introduce a novel deep learning based group activity recognition approach called the Pose Only Group Activity Recognition System (POGARS), designed to use only tracked poses of people to predict the performed group activity.
In this paper, we propose a model, SSI, to improve sequential recommendation consistency with Self-Supervised Imitation.
In this paper, a novel adaptive smooth disturbance observer-based fast finite-time adaptive backstepping control scheme is presented for the attitude tracking of the 3-DOF helicopter system subject to compound disturbances.
In this paper we present the results of our experiments in training and deploying a self-supervised retrieval-based chatbot trained with contrastive learning for assisting customer support agents.
Sophisticated trajectory prediction models that effectively mimic team dynamics have many potential uses for sports coaches, broadcasters and spectators.
This paper presents a novel adaptive fast smooth second-order sliding mode control for the attitude tracking of the three degree-of-freedom (3-DOF) helicopter system with lumped disturbances.
Systems and Control Systems and Control
Distributed deep learning systems (DDLS) train deep neural network models by utilizing the distributed resources of a cluster.
To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames.
Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem.
Ranked #21 on 3D Human Pose Estimation on MPI-INF-3DHP
We study deep learning approaches to inferring numerical coordinates for points of interest in an input image.
Ranked #27 on Pose Estimation on MPII Human Pose
Most research has been focused on action recognition and using it to classify many clips in continuous video for action localisation.
Due to recent advances in technology, the recording and analysis of video data has become an increasingly common component of athlete training programmes.