Search Results for author:
Found 46 papers, 22 papers with code
Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability
When new knowledge emerges, AnoT maps it onto a node in the rule graph and traverses the rule graph recursively to derive the anomaly score of the knowledge.
Test-time adaptation for geospatial point cloud semantic segmentation with distinct domain shifts
For photogrammetric (SensatUrban) to airborne (Hessigheim 3D) adaptation at the inference stage, our method achieves 59. 46\% mIoU and 85. 97\% OA without retraining or fine-turning.
A Pairwise DomMix Attentive Adversarial Network for Unsupervised Domain Adaptive Object Detection
Then a pairwise attentive adversarial network is applied with attentive encoding on both image-level and instance-level features at different scales and optimizes domain alignment by adversarial learning.
Style Alignment based Dynamic Observation Method for UAV-View Geo-localization
In this paper, a style alignment based dynamic observation method for UAV-view geo-localization is proposed to meet the above challenges from two perspectives: visual style transformation and surrounding noise control.
DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs
Moreover, we conduct extensive benchmark experiments on DTGB, evaluating 7 popular dynamic graph learning algorithms and their variants of adapting to text attributes with LLM embeddings, along with 6 powerful large language models (LLMs).
EWMoE: An effective model for global weather forecasting with mixture-of-experts
Weather forecasting is a crucial task for meteorologic research, with direct social and economic impacts.
Graphic Design with Large Multimodal Model
One existing practice is Graphic Layout Generation (GLG), which aims to layout sequential design elements.
A sustainable development perspective on urban-scale roof greening priorities and benefits
Greenspaces are tightly linked to human well-being.
DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition
This paper proposes a new pipeline for long-tail (LT) recognition.
UB-FineNet: Urban Building Fine-grained Classification Network for Open-access Satellite Images
Then, a new fine-grained classification network with Category Information Balancing Module (CIBM) and Contrastive Supervision (CS) technique is proposed to mitigate the problem of class imbalance and improve the classification robustness and accuracy.
Rectify the Regression Bias in Long-Tailed Object Detection
While existing methods fail to handle the regression bias, the class-specific regression head for rare classes is hypothesized to be the main cause of it in this paper.
Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills
We propose a framework called decoupled meta-reinforcement learning (DCMRL), which (1) contrastively restricts the learning of task contexts through pulling in similar task contexts within the same task and pushing away different task contexts of different tasks, and (2) utilizes a Gaussian quantization variational autoencoder (GQ-VAE) for clustering the Gaussian distributions of the task contexts and skills respectively, and decoupling the exploration and learning processes of their spaces.
Online Anomaly Detection over Live Social Video Streaming
After that, we propose a novel model update scheme that incrementally maintains CLSTM and decoder.
AdaDiff: Adaptive Step Selection for Fast Diffusion
Diffusion models, as a type of generative models, have achieved impressive results in generating images and videos conditioned on textual conditions.
Examining User-Friendly and Open-Sourced Large GPT Models: A Survey on Language, Multimodal, and Scientific GPT Models
Generative pre-trained transformer (GPT) models have revolutionized the field of natural language processing (NLP) with remarkable performance in various tasks and also extend their power to multimodal domains.
Generalized Unbiased Scene Graph Generation
To the end, we propose the Multi-Concept Learning (MCL) framework, which ensures a balanced learning process across rare/ uncommon/ common concepts.
StreamE: Learning to Update Representations for Temporal Knowledge Graphs in Streaming Scenarios
To reduce the parameter size, entity representations in StreamE are decoupled from the model training to serve as the memory module to store the historical information of entities.
ESTISR: Adapting Efficient Scene Text Image Super-resolution for Real-Scenes
While scene text image super-resolution (STISR) has yielded remarkable improvements in accurately recognizing scene text, prior methodologies have placed excessive emphasis on optimizing performance, rather than paying due attention to efficiency - a crucial factor in ensuring deployment of the STISR-STR pipeline.
Urban GeoBIM construction by integrating semantic LiDAR point clouds with as-designed BIM models
In this paper, we propose a complementary strategy that integrates LiDAR point clouds with as-designed BIM models for reconstructing urban scenes.
W-MAE: Pre-trained weather model with masked autoencoder for multi-variable weather forecasting
On the temporal scale, we fine-tune the pre-trained W-MAE to predict the future states of meteorological variables, thereby modeling the temporal dependencies present in weather data.
Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation
Yet, previous works tend to encode multimodal and contextual relationships in a loosely-coupled manner, which may harm relationship modelling.
Generalizing Math Word Problem Solvers via Solution Diversification
In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator.
One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learning
It considerably outperforms genuine scene-level weakly supervised methods by up to 25\% in terms of average F1 score and achieves competitive results against full supervision schemes.
Temporal knowledge graph representation learning with local and global evolutions
Temporal knowledge graph (TKG) representation learning aims to project entities and relations in TKG to low-dimensional vector space while preserving the evolutionary nature of TKG.
Step by step: a hierarchical framework for multi-hop knowledge graph reasoning with reinforcement learning
Due to this one-to-many dilemma, enlarged action space and ignoring logical relationship between entity and relation increase the difficulty of learning.
SMDT: Cross-View Geo-Localization with Image Alignment and Transformer
Next, we simultaneously train dual conditional generative adversarial nets by taking the semantic segmentation images and converted images as input to synthesize the aerial image with ground view style.
Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations
Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues.
Efficient divide-and-conquer registration of UAV and ground LiDAR point clouds through canopy shape context
Finally, we implement coarse alignment of ULS and ground LiDAR datasets by combining the results of ground alignment and image matching and finish fine registration.
Mining Contextual Information Beyond Image for Semantic Segmentation
To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations.
MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving
Math word problem (MWP) solving faces a dilemma in number representation learning.
Ranked #5 on
Math Word Problem Solving
on MathQA
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
It enables learning high-quality Laplacian representations that faithfully approximate the ground truth.
Contrast and Order Representations for Video Self-Supervised Learning
To address this, we present a contrast-and-order representation (CORP) framework for learning self-supervised video representations that can automatically capture both the appearance information within each frame and temporal information across different frames.
Ranked #3 on
Self-Supervised Action Recognition Linear
on UCF101
Action Recognition
Self-Supervised Action Recognition Linear
+1
COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-Training for Vision-Language Representation
There are two key designs in it, one is the weight-sharing transformer on top of the visual and textual encoders to align text and image semantically, the other is three kinds of contrastive learning designed for sharing knowledge between different modalities.
Is normalization indispensable for training deep neural network?
In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation.
Improving Generalization in Reinforcement Learning with Mixture Regularization
Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments.
E-FCNN for tiny facial expression recognition
To effectively leverage the texture information of faces, we design a novel three-stream super-resolution network, which is embedded with an edge-enhancement block as one branch.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Temporal Context Aggregation for Video Retrieval with Contrastive Learning
The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc.
Ranked #6 on
Video Retrieval
on FIVR-200K
Graph-to-Tree Learning for Solving Math Word Problems
While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well.
Ranked #10 on
Math Word Problem Solving
on Math23K
TFNet: Multi-Semantic Feature Interaction for CTR Prediction
The CTR (Click-Through Rate) prediction plays a central role in the domain of computational advertising and recommender systems.
Ranked #33 on
Click-Through Rate Prediction
on Criteo
Towards Good Practices for Video Object Segmentation
Semi-supervised video object segmentation is an interesting yet challenging task in machine learning.
Qiniu Submission to ActivityNet Challenge 2018
We also propose new non-local-based models for further improvement on the recognition accuracy.
Learning in High-Dimensional Multimedia Data: The State of the Art
Given the high dimensionality and the high complexity of multimedia data, it is important to investigate new machine learning algorithms to facilitate multimedia data analysis.
Zero-Shot Hashing via Transferring Supervised Knowledge
Supervised knowledge e. g. semantic labels or pair-wise relationship) associated to data is capable of significantly improving the quality of hash codes and hash functions.
Learning to Point and Count
This paper proposes the problem of point-and-count as a test case to break the what-and-where deadlock.
Multiple Granularity Descriptors for Fine-Grained Categorization
Fine-grained categorization, which aims to distinguish subordinate-level categories such as bird species or dog breeds, is an extremely challenging task.
Modeling Based on Elman Wavelet Neural Network for Class-D Power Amplifiers
In Class-D Power Amplifiers (CDPAs), the power supply noise can intermodulate with the input signal, manifesting into power-supply induced intermodulation distortion (PS-IMD) and due to the memory effects of the system, there exist asymmetries in the PS-IMDs.
