Modern writing assistance applications are always equipped with a Grammatical Error Correction (GEC) model to correct errors in user-entered sentences.
This paper aims to assess the impact of COVID-19 on the public finance of Chinese local governments, with a particular focus on the effect of lockdown measures on startups during the pandemic.
This approach achieves feature integration in a unified backbone, removing the need for carefully-designed fusion modules and resulting in a more effective and efficient VL tracking framework.
Intrathoracic airway segmentation in computed tomography (CT) is a prerequisite for various respiratory disease analyses such as chronic obstructive pulmonary disease (COPD), asthma and lung cancer.
The responses generated by chatbots based on LLMs are recorded for blind evaluations by five licensed medical experts.
In recommendation systems, a large portion of the ratings are missing due to the selection biases, which is known as Missing Not At Random.
To compensate for the lack of geometry in 2D Image compositing, recent deep learning-based approaches introduced a pixel height representation to generate soft shadows and reflections.
Placing and orienting a camera to compose aesthetically meaningful shots of a scene is not only a key objective in real-world photography and cinematography but also for virtual content creation.
The unmanned aerial vehicle (UAV) enabled mobile edge computing (MEC) has been deemed a promising paradigm to provide ubiquitous communication and computing services for the Internet of Things (IoT).
Driven by the visions of Internet of Things (IoT), there is an ever-increasing demand for computation resources of IoT users to support diverse applications.
Despite recent success, deep learning-based methods for predicting 3D garment deformation under body motion suffer from interpenetration problems between the garment and the body.
Moment retrieval in videos is a challenging task that aims to retrieve the most relevant video moment in an untrimmed video given a sentence description.
We study lossless acceleration for seq2seq generation with a novel decoding algorithm -- Aggressive Decoding.
We test the effectiveness of our representation on the human image harmonization task by predicting shading that is coherent with a given background image.
Extracting relational triples from unstructured text is an essential task in natural language processing and knowledge graph construction.
Hierarchical text classification is a challenging subtask of multi-label classification due to its complex label hierarchy.
Synthetic data construction of Grammatical Error Correction (GEC) for non-English languages relies heavily on human-designed and language-specific rules, which produce limited error-corrected patterns.
Temporal language grounding in videos aims to localize the temporal span relevant to the given query sentence.
Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance.
no code implementations • • Xiao-Feng Huang, Li-Ming Cao, Xu-Dong Tian, * Qiao Zhu, Eri Saikawa, Li-Liang Lin, Yong Cheng, Ling-Yan He, * Min Hu, Yuan-Hang Zhang, Ke-Ding Lu, Yu-Han Liu, Kaspar Daellenbach, Jay G. Slowik, Qian Tang, Qiao-Li Zou, Xin Sun, Bing-Ye Xu, Lan Jiang, Ye-Min Shen, Nga Lee Ng, and André S. H. Prévôt*
The lockdown due to COVID-19 created a rare opportunity to examine the nonlinear responses of secondary aerosols, which are formed through atmospheric oxidation of gaseous precursors, to intensive precursor emission reductions.
We present a single-image data-driven method to automatically relight images with full-body humans in them.
Simulation results illustrate that a distributed planning model is more sensitive to individual load differences, which is precisely the defect of the joint planning model.
Recently, distillation approaches are suggested to extract general knowledge from a teacher network to guide a student network.
In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC).
This paper proposes a network embedding framework to capture the transfer behaviors on structured networks via deep prediction models.
Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation.
Then the generated samples are used to train the compact student network under the supervision of the teacher.
The proposed approach promotes the performance of student model as the virtual sample created by multiple images produces a similar probability distribution in the teacher and student networks.
In this paper, we exploit syntactic awareness to the model by the graph attention network on the dependency tree structure and external pre-training knowledge by BERT language model, which helps to model the interaction between the context and aspect words better.
A typical challenge that hinders their real-world applications is that unknown samples may be fed into the system during the testing phase, but traditional deep neural networks will wrongly recognize these unknown samples as one of the known classes.
Then, we borrow the idea of Coulomb's Law from physics and introduce the concept of attractive force and repulsive force to this graph to learn correlation and mutual exclusion between relations.
A typical challenge is that unknown samples may be fed into the system during the testing phase and traditional deep neural networks will wrongly recognize the unknown sample as one of the known classes.
The network first introduces a High-Order Representation module to extract the contextual high-order information from all stages of the backbone.
Low-shot learning indicates the ability to recognize unseen objects based on very limited labeled training samples, which simulates human visual intelligence.
An even larger dataset comprising 547 hours of German speech aligned to German text is available for speech recognition.
Learning to recognize novel visual categories from a few examples is a challenging task for machines in real-world industrial applications.
Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher model.
Part-based trackers are effective in exploiting local details of the target object for robust tracking.
Finally, given a set of semantic descriptions, the diverse properties of the samples in the semantic space can lead the framework to find an appropriate generation model that uses appropriate parameters to produce a desired texture.