Search Results for author:
Found 118 papers, 56 papers with code
Dynamic Base model Shift for Delta Compression
To this end, we propose Dynamic Base Model Shift (DBMS), which dynamically adapts the base model to the target task before performing delta compression.
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
OmniCaptioner: One Captioner to Rule Them All
We propose OmniCaptioner, a versatile visual captioning framework for generating fine-grained textual descriptions across a wide variety of visual domains.
Towards Physically Plausible Video Generation via VLM Planning
In the second stage, we use the predicted motion trajectories/changes to guide the video generation of a VDM.
UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines
Traditional spatiotemporal models generally rely on task-specific architectures, which limit their generalizability and scalability across diverse tasks due to domain-specific design requirements.
RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints
Furthermore, we explore the architectures and training strategies for multi-agent imitation learning, aiming to build safe and efficient embodied multi-agent systems.
Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs
Multi-Modal Large Language Models (MLLMs) stand out in various tasks but still struggle with hallucinations.
Transforming Weather Data from Pixel to Latent Space
The downstream task further demonstrates that task models can apply to multiple PVS with low data costs in latent space and achieve superior performance compared to models in pixel space.
Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform
With transformer-based models and the pretrain-finetune paradigm becoming mainstream, the high storage and deployment costs of individual finetuned models on multiple tasks pose critical challenges.
SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing
Survey paper plays a crucial role in scientific research, especially given the rapid growth of research publications.
Nature-Inspired Population-Based Evolution of Large Language Models
Evolution, the engine behind the survival and growth of life on Earth, operates through the population-based process of reproduction.
SeisMoLLM: Advancing Seismic Monitoring via Cross-modal Transfer with Pre-trained Large Language Model
Recent advances in deep learning have revolutionized seismic monitoring, yet developing a foundation model that performs well across multiple complex tasks remains challenging, particularly when dealing with degraded signals or data scarcity.
EvoFlow: Evolving Diverse Agentic Workflows On The Fly
The past two years have witnessed the evolution of large language model (LLM)-based multi-agent systems from labor-intensive manual design to partial automation (\textit{e. g.}, prompt engineering, communication topology) and eventually to fully automated design.
TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
CFD blocks adopt a bottom-up cascading approach to obtain series representations for each frequency band.
Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution
In the sampling, we employed optimizable convolutional kernels to simulate the upscale process, thereby generating high-resolution ERA5 maps using low-resolution ERA5 maps as well as observations from weather stations as guidance.
Multi-agent Architecture Search via Agentic Supernet
Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs.
VQLTI: Long-Term Tropical Cyclone Intensity Forecasting with Physical Constraints
(2) Incorporating physical knowledge and physical constraints can help mitigate the accumulation of forecasting errors.
Kolmogorov Arnold Neural Interpolator for Downscaling and Correcting Meteorological Fields from In-Situ Observations
Obtaining accurate weather forecasts at station locations is a critical challenge due to systematic biases arising from the mismatch between multi-scale, continuous atmospheric characteristic and their discrete, gridded representations.
DispFormer: Pretrained Transformer for Flexible Dispersion Curve Inversion from Global Synthesis to Regional Applications
Surface wave dispersion curve inversion is essential for estimating subsurface Shear-wave velocity ($v_s$), yet traditional methods often struggle to balance computational efficiency with inversion accuracy.
Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback
The scientific research paradigm is undergoing a profound transformation owing to the development of Artificial Intelligence (AI).
LWFNet: Coherent Doppler Wind Lidar-Based Network for Wind Field Retrieval
LWFNet demonstrates remarkable performance in lidar-based wind field retrieval, setting a benchmark for future research and advancing the development of deep learning models in this domain.
Chimera: Improving Generalist Model with Domain-Specific Experts
This results in a versatile model that excels across the chart, table, math, and document domains, achieving state-of-the-art performance on multi-modal reasoning and visual content extraction tasks, both of which are challenging tasks for assessing existing LMMs.
CA-MoE: Channel-Adapted MoE for Incremental Weather Forecasting
Atmospheric science is intricately connected with other fields, e. g., geography and aerospace.
DuoCast: Duo-Probabilistic Meteorology-Aware Model for Extended Precipitation Nowcasting
Recently, extended short-term precipitation nowcasting struggles with decreasing precision because of insufficient consideration of meteorological knowledge, such as weather fronts which significantly influence precipitation intensity, duration, and spatial distribution.
FengWu-W2S: A deep learning model for seamless weather-to-subseasonal forecast of global atmosphere
Seamless forecasting that produces warning information at continuum timescales based on only one system is a long-standing pursuit for weather-climate service.
DiffSR: Learning Radar Reflectivity Synthesis via Diffusion Model from Satellite Observations
Weather radar data synthesis can fill in data for areas where ground observations are missing.
WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning
Finally, we adopt a visual prompting question-answering paradigm for the training of unified weather understanding tasks.
On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
Large numbers of synthesized videos from diffusion models pose threats to information security and authenticity, leading to an increasing demand for generated content detection.
WorldSimBench: Towards Video Generation Models as World Simulators
WorldSimBench includes Explicit Perceptual Evaluation and Implicit Manipulative Evaluation, encompassing human preference assessments from the visual perspective and action-level evaluations in embodied tasks, covering three representative embodied scenarios: Open-Ended Embodied Environment, Autonomous, Driving, and Robot Manipulation.
SIFM: A Foundation Model for Multi-granularity Arctic Sea Ice Forecasting
Arctic sea ice performs a vital role in global climate and has paramount impacts on both polar ecosystems and coastal communities.
Diffusion Models Need Visual Priors for Image Generation
Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details.
Ranked #36 on
Image Generation
on ImageNet 256x256
IceDiff: High Resolution and High-Quality Sea Ice Forecasting with Generative Diffusion Prior
Variation of Arctic sea ice has significant impacts on polar ecosystems, transporting routes, coastal communities, and global climate.
PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling
By rethinking the blurriness in precipitation nowcasting as a blur kernel acting on predictions, we propose an unsupervised postprocessing method to eliminate the blurriness without the requirement of training with the pairs of blurry predictions and corresponding ground truth.
WeatherFormer: Empowering Global Numerical Weather Forecasting with Space-Time Transformer
Numerical Weather Prediction (NWP) system is an infrastructure that exerts considerable impacts on modern society. Traditional NWP system, however, resolves it by solving complex partial differential equations with a huge computing cluster, resulting in tons of carbon emission.
ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
Based on ComfyBench, we further develop ComfyAgent, a novel framework that empowers LLM-based agents to autonomously design collaborative AI systems by generating workflows.
A Benchmark for AI-based Weather Data Assimilation
Recent advancements in Artificial Intelligence (AI) have led to the development of several Large Weather Models (LWMs) that rival State-Of-The-Art (SOTA) Numerical Weather Prediction (NWP) systems.
MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling
In an era of frequent extreme weather and global warming, obtaining precise, fine-grained near-surface weather forecasts is increasingly essential for human activities.
Fast Information Streaming Handler (FisH): A Unified Seismic Neural Network for Single Station Real-Time Earthquake Early Warning
FisH is designed to process real-time streaming seismic data and generate simultaneous results for phase picking, location estimation, and magnitude estimation in an end-to-end fashion.
VegeDiff: Latent Diffusion Model for Geospatial Vegetation Forecasting
By capturing the uncertainties in vegetation changes and modeling the complex influence of relevant variables, VegeDiff outperforms existing deterministic methods, providing clear and accurate forecasting results of future vegetation states.
PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines
In this paper, we introduce PredBench, a benchmark tailored for the holistic evaluation of spatio-temporal prediction networks.
How far are today's time-series models from real-world weather forecasting applications?
As a result, it enables a better training of models and a more accurate assessment of the real-world forecasting capabilities of TSF models, pushing them closer to in-situ applications.
FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation
Data assimilation is a vital component in modern global medium-range weather forecasting systems to obtain the best estimation of the atmospheric state by combining the short-term forecast and observations.
Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification
In the task-specific evaluation setting, gallery sets are categorized according to specific ReID tasks.
Data-driven Global Ocean Modeling for Seasonal to Decadal Prediction
Accurate ocean dynamics modeling is crucial for enhancing understanding of ocean circulation, predicting climate variability, and tackling challenges posed by climate change.
Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling
This paper proposes a physics-AI hybrid model (i. e., WeatherGFT) which generalizes weather forecasts to finer-grained temporal scales beyond training dataset.
VAE-Var: Variational-Autoencoder-Enhanced Variational Assimilation
Data assimilation refers to a set of algorithms designed to compute the optimal estimate of a system's state by refining the prior prediction (known as background states) using observed data.
CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer
To mitigate this issue, we introduce an efficient neural codec, the Variational Autoencoder Transformer (VAEformer), for extreme compression of climate data to significantly reduce data storage cost, making AI-based meteorological research portable to researchers.
G-Refine: A General Quality Refiner for Text-to-Image Generation
Based on the mechanisms of the Human Visual System (HVS) and syntax trees, the first two indicators can respectively identify the perception and alignment deficiencies, and the last module can apply targeted quality enhancement accordingly.
RS-Mamba for Large Remote Sensing Image Dense Prediction
RSM is specifically designed to capture the global context of remote sensing images with linear complexity, facilitating the effective processing of large VHR images.
Ranked #1 on
Road Segmentation
on Massachusetts Roads Dataset
Building change detection for remote sensing images
Change Detection
+3
A Survey on Long Video Generation: Challenges, Methods, and Prospects
Video generation is a rapidly advancing research area, garnering significant attention due to its broad range of applications.
HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation
We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in an unsupervised man- ner.
Global Tropical Cyclone Intensity Forecasting with Multi-modal Multi-scale Causal Autoregressive Model
Accurate forecasting of Tropical cyclone (TC) intensity is crucial for formulating disaster risk reduction strategies.
CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling
Precipitation nowcasting based on radar data plays a crucial role in extreme weather prediction and has broad implications for disaster management.
Diffusion Model-based Probabilistic Downscaling for 180-year East Asian Climate Reconstruction
As our planet is entering into the "global boiling" era, understanding regional climate change becomes imperative.
ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast
Data-driven weather forecast based on machine learning (ML) has experienced rapid development and demonstrated superior performance in the global medium-range forecast compared to traditional physics-based dynamical models.
Improving Global Weather and Ocean Wave Forecast with Large Artificial Intelligence Models
The rapid advancement of artificial intelligence technologies, particularly in recent years, has led to the emergence of several large parameter artificial intelligence weather forecast models.
FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting
Therefore, building a kilometer-scale global forecast model is a persistent pursuit in the meteorology domain.
Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning
As a pre-trained paradigm, we conduct the Kriging task from a new perspective of representation: we aim to first learn robust and general representations and then recover attributes from representations.
Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Method
In this paper, we extend meteorological downscaling to arbitrary scattered station scales, establish a brand new benchmark and dataset, and retrieve meteorological states at any given station location from a coarse-resolution meteorological field.
Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting
To make the model trained on historical data better adapt to future data in a fully online manner, this paper conducts the first study of the online test-time adaptation techniques for spatial-temporal traffic flow forecasting problems.
Ranked #5 on
Traffic Prediction
on NYCTaxi
Q-Refine: A Perceptual Quality Refiner for AI-Generated Image
With the rapid evolution of the Text-to-Image (T2I) model in recent years, their unsatisfactory generation result has become a challenge.
Towards an end-to-end artificial intelligence driven global weather forecasting system
Initial states are typically generated by traditional data assimilation components, which are computational expensive and time-consuming.
FengWu-4DVar: Coupling the Data-driven Weather Forecasting Model with 4D Variational Assimilation
Weather forecasting is a crucial yet highly challenging task.
ResoNet: Robust and Explainable ENSO Forecasts with Hybrid Convolution and Transformer Networks
Recent studies have shown that deep learning (DL) models can skillfully predict the El Ni\~no-Southern Oscillation (ENSO) forecasts over 1. 5 years ahead.
VisionTraj: A Noise-Robust Trajectory Recovery Framework based on Large-scale Camera Network
Trajectory recovery based on the snapshots from the city-wide multi-camera network facilitates urban mobility sensing and driveway optimization.
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Human-centric perception tasks, e. g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis.
Ranked #1 on
Pedestrian Image Caption
on CUHK-PEDES
A Critical Perceptual Pre-trained Model for Complex Trajectory Recovery
Then, we propose a Multi-view Graph and Complexity Aware Transformer (MGCAT) model to encode these semantics in trajectory pre-training from two aspects: 1) adaptively aggregate the multi-view graph features considering trajectory pattern, and 2) higher attention to critical nodes in a complex trajectory.
Understanding Masked Autoencoders From a Local Contrastive Perspective
Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies.
Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation
A 360-degree (omni-directional) image provides an all-encompassing spherical view of a scene.
Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training
Our approach enables collaboration among multiple clinical sites without compromising data privacy under a federated learning paradigm that incorporates a noise-robust training strategy based on label correction.
STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning
Scale variation is a deep-rooted problem in object counting, which has not been effectively addressed by existing scale-aware algorithms.
Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities
The distribution representation of a clue is a vector consisting of the relation between this clue and all other clues from all modalities, thus being modality agnostic and good for person clustering.
Enhancing Mapless Trajectory Prediction through Knowledge Distillation
Scene information plays a crucial role in trajectory forecasting systems for autonomous driving by providing semantic clues and constraints on potential future paths of traffic agents.
MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators
Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans.
LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
To mitigate these limitations, we introduce the LargeST benchmark dataset.
Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions.
Correlated Time Series Self-Supervised Representation Learning via Spatiotemporal Bootstrapping
We evaluated the effectiveness and flexibility of our representation learning framework on correlated time series forecasting and cold-start transferring the forecasting model to new instances with limited data.
Correlated Time Series Forecasting
Representation Learning
+1
Dynamic Causal Graph Convolutional Network for Traffic Prediction
In this work, we propose a novel approach for traffic prediction that embeds time-varying dynamic Bayesian network to capture the fine spatiotemporal topology of traffic data.
Ranked #15 on
Traffic Prediction
on METR-LA
LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
To the best of our knowledge, we present one of the very first open-source endeavors in the field, LAMM, encompassing a Language-Assisted Multi-Modal instruction tuning dataset, framework, and benchmark.
MM-DAG: Multi-task DAG Learning for Multi-modal Data -- with Application for Traffic Congestion Analysis
This encourages the multi-task design: with each DAG as a task, the MM-DAG tries to learn the multiple DAGs jointly so that their consensus and consistency are maximized.
Stimulative Training++: Go Beyond The Performance Limits of Residual Networks
In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of loafing, and further propose a new training scheme as well as three improved strategies for boosting residual networks beyond their performance limits.
Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation
To mitigate those limitations, we propose Hierarchical Diffusion Autoencoders (HDAE) that exploit the fine-grained-to-abstract and lowlevel-to-high-level feature hierarchy for the latent space of diffusion models.
FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI).
FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Prediction
In this paper, we focus on dealing with the long-tail phenomenon in trajectory prediction.
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.
Ranked #1 on
Pedestrian Attribute Recognition
on PA-100K
(using extra training data)
UniHCP: A Unified Model for Human-Centric Perceptions
When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e. g., 69. 8 mIoU on CIHP for human parsing, 86. 18 mA on PA-100K for attribute prediction, 90. 3 mAP on Market1501 for ReID, and 85. 8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.
Ranked #1 on
Pose Estimation
on MS-COCO
Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phase
As past poses often contain useful auxiliary hints, in this paper, we propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T), with an attention based encoder-decoder architecture to discover the auxiliary information implicitly for synthesizing controllable motion without explicitly requiring auxiliary information such as phase.
Saliency Guided Contrastive Learning on Scene Images
Despite being feasible, recent works largely overlooked discovering the most discriminative regions for contrastive learning to object representations in scene images.
Learning from pseudo-labels: deep networks improve consistency in longitudinal brain volume estimation
An accurate and robust quantitative measurement of brain volume change is paramount for translational research and clinical applications.
Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective
In this paper, with extensive and deep-going experiments, we comprehensively analyze existing spatiotemporal graph learning models and reveal that extracting adjacency matrices with carefully design strategies, which are viewed as the key of enhancing performance on graph learning, are largely ineffective.
$β$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search
To address the robustness problem, we first benchmark different NAS methods under a wide range of proxy data, proxy channels, proxy layers and proxy epochs, since the robustness of NAS under different kinds of proxies has not been explored before.
A Bibliometric Analysis and Review on Reinforcement Learning for Transportation Applications
Transportation is the backbone of the economy and urban development.
Towards Frame Rate Agnostic Multi-Object Tracking
In this paper, we propose a Frame Rate Agnostic MOT framework with a Periodic training Scheme (FAPS) to tackle the FraMOT problem for the first time.
Jointly Contrastive Representation Learning on Road Network and Trajectory
Unlike the existing cross-scale contrastive learning methods on graphs that only contrast a graph and its belonging nodes, the contrast between road segment and trajectory is elaborately tailored via novel positive sampling and adaptive weighting strategies.
An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection
We hope this work can provide insights for the image-based 3D detection community under a semi-supervised setting.
Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches
Contrastive-based self-supervised learning methods achieved great success in recent years.
Action Recognition With Motion Diversification and Dynamic Selection
To address this issue, we introduce a Motion Diversification and Selection (MoDS) module to generate diversified spatio-temporal motion features and then select the suitable motion representation dynamically for categorizing the input video.
Ranked #19 on
Action Recognition
on Something-Something V1
Unsupervised Knowledge Adaptation for Passenger Demand Forecasting
These multimodal forecasting models can improve accuracy but be less practical when different parts of multimodal datasets are owned by different institutions who cannot directly share data among them.
Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains
While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain.
MS Lesion Segmentation: Revisiting Weighting Mechanisms for Federated Learning
In addition, the segmentation loss function in each client is also re-weighted according to the lesion volume for the data during training.
DR.VIC: Decomposition and Reasoning for Video Individual Counting
Instead of relying on the Multiple Object Tracking (MOT) techniques, we propose to solve the problem by decomposing all pedestrians into the initial pedestrians who existed in the first frame and the new pedestrians with separate identities in each following frame.
Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest.
Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encoding
Trajectories obtained from object detection and tracking are inevitably noisy, which could cause serious forecasting errors to predictors built on ground truth trajectories.
Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
The pretrain-finetune paradigm is a classical pipeline in visual learning.
Improving the Transferability of Supervised Pretraining with an MLP Projector
The pretrain-finetune paradigm is a classical pipeline in visual learning.
Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images
Following the top-down paradigm, we decompose the task into two stages, i. e. person localization and pose estimation.
Ranked #2 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Then, a compact set of the possible combinations for different token pooling and attention sharing mechanisms are constructed.
GLiT: Neural Architecture Search for Global and Local Image Transformer
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition.
Ranked #130 on
Image Classification
on ImageNet
(GFLOPs metric)
Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
In this work, we proposed a novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM), which fully exploits heterogeneous information of historical data (e. g., incomplete OD matrices, unfinished order vectors, and DO matrices) to jointly learn the evolutionary patterns of OD and DO ridership.
Mutual CRF-GNN for Few-Shot Learning
In this MCGN, the labels and features of support data are used by the CRF for inferring GNN affinities in a principled and probabilistic way.
Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
As a special design of this transformer, the information encoded in the encoder is different from that in the decoder, i. e. the encoder encodes temporal-channel information of multiple frames while the decoder decodes the spatial-channel information for the current frame in a voxel-wise manner.
Knowledge Adaption for Demand Prediction based on Multi-task Memory Neural Network
Accurate demand forecasting of different public transport modes(e. g., buses and light rails) is essential for public service operation. However, the development level of various modes often varies sig-nificantly, which makes it hard to predict the demand of the modeswith insufficient knowledge and sparse station distribution (i. e., station-sparse mode).
Spectrum-Guided Adversarial Disparity Learning
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.
Face to Purchase: Predicting Consumer Choices with Structured Facial and Behavioral Traits Embedding
We design a semi-supervised model based on a hierarchical embedding network to extract high-level features of consumers and to predict the top-$N$ purchase destinations of a consumer.
Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
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 #2 on
Weather Forecasting
on SD
Are You A Risk Taker? Adversarial Learning of Asymmetric Cross-Domain Alignment for Risk Tolerance Prediction
Most current studies on survey analysis and risk tolerance modelling lack professional knowledge and domain-specific models.
STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting
Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services.
