Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks196 from public data
- Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks863
A novel bi-directional graph model is proposed, named Bi-Directional Graph Convolutional Networks (Bi-GCN), to explore both characteristics of rumors by operating on both top-down and bottom-up propagation of rumors.
- Graph Representation Learning via Graphical Mutual Information Maximization706
An unsupervised learning model trained by maximizing GMI between the input and output of a graph neural encoder is developed, which outperforms state-of-the-art unsuper supervised counterparts, and even sometimes exceeds the performance of supervised ones.
- 607
- Graph Convolutional Networks for Temporal Action Localization549
This paper builds an action proposal graph, where each proposal is represented as a node and their relations between two proposals as an edge and applies the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization.
- Progressive Feature Alignment for Unsupervised Domain Adaptation490
The Progressive Feature Alignment Network (PFAN) is proposed to align the discriminative features across domains progressively and effectively, via exploiting the intra-class variation in the target domain.
- A Fast and Accurate One-Stage Approach to Visual Grounding462
A simple, fast, and accurate one-stage approach to visual grounding that enables end-to-end joint optimization and shows great potential in terms of both accuracy and speed for both phrase localization and referring expression comprehension.
- Dense Regression Network for Video Grounding346
A novel dense regression network (DRN) is designed to regress the distances between the frame within the ground truth and the starting (ending) frame of the video segment described by the query to improve the video grounding accuracy.
- Multimodal Token Fusion for Vision Transformers327
The design of TokenFusion allows the transformer to learn correlations among multimodal features, while the single-modal transformer architecture remains largely intact, and surpasses state-of-the-art methods in three typical vision tasks: multimodals image-to-image translation, RGB-depth semantic segmentation, and 3D object detection with point cloud and images.
- Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering304
This work proposes a new architecture, Positional Self-Attention with Coattention (PSAC), which does not require RNNs for video question answering and significantly outperforms the state-of-the-art on three tasks and attains comparable result on the Count task.
- Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation243
A decoupled training strategy by which the encoder is only trained when maximizing the adversary loss while keeping frozen otherwise is developed, which demonstrates the superior performance of NICE-GAN over state-of-the-art methods in terms of FID, KID, and also human preference.
- End-to-End Learning of Motion Representation for Video Understanding229
This work proposes TVNet, a novel end-to-end trainable neural network, to learn optical-flow-like features from data, which achieves better accuracies than all compared methods, while being competitive with the fastest counterpart in terms of features extraction time.
- Deep Feature Pyramid Reconfiguration for Object Detection224
A novel reconfiguration architecture is proposed to combine low-level representations with high-level semantic features in a highly-nonlinear yet efficient way to gather task-oriented features across different spatial locations and scales, globally and locally.
- 198
- A Restricted Black-Box Adversarial Framework Towards Attacking Graph Embedding Models180
This paper investigates the theoretical connections between graph signal processing and graph embedding models in a principled way and forms a generalized adversarial attacker, GF-Attack, which is constructed by the graph filter and feature matrix and validated on several benchmark datasets.
- Semi-Supervised Graph Classification: A Hierarchical Graph Perspective172
This work proposes a novel supervised, self-attentive graph embedding method called SAGE, which embeds graph instances of arbitrary size into fixed-length vectors and demonstrates that SEAL-C/AI not only outperform competing methods by a significant margin in terms of accuracy/Macro-F1, but also generate meaningful interpretations of the learned representations.
- Multimode Grasping Soft Gripper Achieved by Layer Jamming Structure and Tendon-Driven Mechanism129
A soft gripper with multiple grasping modes integrated with layer jamming structure and tendon-driven mechanism with superior performance and the multimode grasping ability that satisfies various grasping tasks is proposed.
- 110
- Macro Graph Neural Networks for Online Billion-Scale Recommender Systems108
This work names the conventional user-item recommendation graph as "micro recommendation grap" and introduces a revolutionizing MAcro Recommendation Graph (MAG) for billion-scale recommendations to reduce the neighbor count from billions to hundreds in the graph structure infrastructure.
- 104
- A survey of geometric graph neural networks: data structures, models and applications97
This paper formalizes geometric graph as the data structure, on top of which it provides a unified view of existing models from the geometric message passing perspective, and summarizes the applications as well as the related datasets to facilitate later research for methodology development and experimental evaluation.
- 97
- Graph Convolutional Module for Temporal Action Localization in Videos93
It is claimed that the relations between action units play an important role in action localization, and a more powerful action detector should not only capture the local content of each action unit but also allow a wider field of view on the context related to it to enhance action localization.
- 82
- Cross-dependent graph neural networks for molecular property prediction81
This work explores the multi-view modeling with graph neural network to form a novel paralleled framework which considers both atoms and bonds equally important when learning molecular representations, and proposes a cross-dependent message passing scheme to enhance information communication of different views.
- 81
- 79
- Label-Aware Graph Convolutional Networks74
This paper considers the problem of node classification and proposes the Label-Aware Graph Convolutional Network (LAGCN) framework which can directly identify valuable neighbors to enhance the performance of existing GCN models and introduces the concept of positive ratio to evaluate the density of valuable neighbors in the LA graph.
- Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance73
This paper defines an imperfect expert setting for RLfD in a formal way, and points out that previous methods suffer from two issues in terms of optimality and convergence, respectively, and tackles these two issues by regarding the expert guidance as a soft constraint on regulating the policy exploration of the agent, which eventually leads to a constrained optimization problem.
- 71
- Scalable Gaussian process regression using deep neural networks71
A scalable Gaussian process model for regression by applying a deep neural network as the feature-mapping function, which can learn much more meaningful representation of the data by the finite-dimensional but deep-layered feature- mapping function.
- 69
- 67
- 64
- 63
- 61
- Building feature space of extreme learning machine with sparse denoising stacked-autoencoder59
An approach is proposed that effectively integrates the advantages in SAE, sparse AE, denoising AE, and the RR implementation in ELM algorithm and tends to achieve a better generalization ability on relatively large datasets that were not pre-processed for feature abstraction.
- Bridged Transformer for Vision and Point Cloud 3D Object Detection58
Bridged Transformer is proposed, an end-to-end architecture for 3D object detection which learns to identify 3D and 2D object bounding boxes from both points and image patches and surpasses state-of-the-art methods on SUN RGB-D and ScanNetV2 datasets.
- Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction53
Channel-Exchanging-Network (CEN) is proposed which is self-adaptive, parameter-free, and more importantly, applicable for multimodal and multitask dense image prediction and adaptively exchanges channels between subnetworks of different modalities.
- 49
- 48
- 47
- Deep Graph Learning46
This tutorial aims to provide a comprehensive introduction to deep graph learning and introduces the applications of DGL towards various domains, including but not limited to drug discovery, computer vision, medical image analysis, social network analysis, natural language processing and recommendation.
- 45
- Graph Cross-Correlated Network for Recommendation44
The Graph Cross-correlated Network for Recommendation (GCR) is proposed, which serves as a general recommendation paradigm that explicitly considers correlations between user/item subgraphs and comprehensively incorporates the cross-correlated terms for recommendations.
- 43
- 39
- Controllable Image-to-Video Translation: A Case Study on Facial Expression Generation38
A novel neural network architecture is designed that can incorporate the user input into its skip connections and several improvements to the adversarial training method for the neural network are proposed.
- 37
- SE(3)-equivariant ternary complex prediction towards target protein degradation33
This work introduces DeepTernary, a deep learning method for rapid and accurate prediction of PROTAC and molecular glue-induced ternary complex structures, achieving state-of-the-art results by learning from a curated dataset, TernaryDB.
- 33
- 33
- 32
- 31
- 29
- 29
- 29
- 28
- 27
- 27
- 27
- 27
- 24
- 24
- 24
- 23
- 23
- 23
- 22
- 22
- 22
- 21
- 20
- 19
- Facial Image-to-Video Translation by a Hidden Affine Transformation19
This work derives an inverse formulation to the affine transformation, enabling automatic inference of the facial expression intensities from videos, and could improve users' communication experience by enabling them to conveniently and creatively produce expression GIFs, which are popular art forms in online messaging and social networks.
- 19
- 17
- 17
- 17
- 16
- 15
- Hygroscopic photothermal sorbents for atmospheric water harvesting: From preparation to applications15
- 14
- 14
- 14
- 13
- 13
- 12
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- Watch, Reason and Code6
A Watch-Reason-Code (WRC) model to synthesise programs that describe the process carried out in a set of video sequences and can achieve the state-of-the-art under a variety of settings is proposed.
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- Towards Purely Unsupervised Disentanglement of Appearance and Shape for Person Images Generation4
An encoder-decoder-like network to extract both the shape and appearance features from input images at the same time, and train the parameters by three losses: feature adversarial loss, color consistency loss and reconstruction loss, which achieves clean disentanglement.
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- One Path to Model Them All: Learnable-Time Flow Matching for Crystal Structure and Energy Prediction–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.