Knowledge distillation is a generalized logits matching technique for model compression.
The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner.
To address this, we present a novel deep learning framework for portrait lighting enhancement based on 3D facial guidance.
In light of this, we propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution.
Face image manipulation via three-dimensional guidance has been widely applied in various interactive scenarios due to its semantically-meaningful understanding and user-friendly controllability.
Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model.
However, the social network information may not be available in many recommender systems, which hinders application of SamWalker.
To deal with these problems, we propose an efficient and effective collaborative sampling method CoSam, which consists of: (1) a collaborative sampler model that explicitly leverages user-item interaction information in sampling probability and exhibits good properties of normalization, adaption, interaction information awareness, and sampling efficiency; and (2) an integrated sampler-recommender framework, leveraging the sampler model in prediction to offset the bias caused by uneven sampling.
Our study demonstrates the importance of item trend information in recommendation system designs, and our method also possesses great efficiency which enables it to be practical in real-world scenarios.
The HMOR encodes interaction information as the ordinal relations of depths and angles hierarchically, which captures the body-part and joint level semantic and maintains global consistency at the same time.
This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet.
Ranked #2 on 2D Human Pose Estimation on COCO-WholeBody
It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class.
The first aims to learn pose- and expression-related feature representations in the source domain and adapt both feature distributions to that of the target domain by imposing adversarial learning.
We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks.
Ranked #3 on Traffic Prediction on PeMS04
A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence.
The second-level distillation is performed to transfer the knowledge in the ensemble of auxiliary peers further to the group leader, i. e., the model used for inference.
HGP-SL incorporates graph pooling and structure learning into a unified module to generate hierarchical representations of graphs.
Ranked #1 on Graph Classification on Mutagenicity
Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid.
Second, given a meta path, nodes in HIN are connected by path instances while existing works fail to fully explore the differences between path instances that reflect nodes' preferences in the semantic space.
In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms.
Ranked #4 on Multi-Person Pose Estimation on CrowdPose
Multimodal wearable sensor data classification plays an important role in ubiquitous computing and has a wide range of applications in scenarios from healthcare to entertainment.
In order to answer these kinds of questions, we attempt to model human sense of style compatibility in this paper.
Dynamic and personalized elements such as top stories, recommended list in a webpage are vital to the understanding of the dynamic nature of web 2. 0 sites.
To overcome the limitations of existing methods, we propose a novel approach in this paper to learn effective features automatically from the structured data using the Convolutional Neural Network (CNN).
Experimental results on three public datasets and two proposed datasets demonstrate the superiority of the proposed approach, indicating the effectiveness of body structure and orientation information for improving re-identification performance.