Search Results for author:
Found 46 papers, 13 papers with code
EasySplat: View-Adaptive Learning makes 3D Gaussian Splatting Easy
In this way, the proposed method tackles the limitation on initialization and optimization, leading to an efficient and accurate 3DGS modeling.
Auto-bidding in real-time auctions via Oracle Imitation Learning (OIL)
Deciding the best bid for an impression opportunity is challenging, due to the stochastic nature of user behavior and the variability of advertisement traffic over time.
Point Cloud-Assisted Neural Image Compression
High-efficient image compression is a critical requirement.
MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing
We identify inter-task and intra-task sensitivity issues in current ICL methods for PCP, which we attribute to inflexible sampling strategies lacking context adaptation at the point and prompt levels.
OKG: On-the-Fly Keyword Generation in Sponsored Search Advertising
Current keyword decision-making in sponsored search advertising relies on large, static datasets, limiting the ability to automatically set up keywords and adapt to real-time KPI metrics and product updates that are essential for effective advertising.
ViMo: Generating Motions from Casual Videos
Although humans have the innate ability to imagine multiple possible actions from videos, it remains an extraordinary challenge for computers due to the intricate camera movements and montages.
Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space
In this paper, we introduce a novel path to $\textit{general}$ human motion generation by focusing on 2D space.
Integrating Domain Knowledge for handling Limited Data in Offline RL
With the ability to learn from static datasets, Offline Reinforcement Learning (RL) emerges as a compelling avenue for real-world applications.
Augmenting Offline RL with Unlabeled Data
This framework enables the student policy to gain insights not only from the offline RL dataset but also from the knowledge transferred by a teacher policy.
$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
Continuous diffusion models have demonstrated their effectiveness in addressing the inherent uncertainty and indeterminacy in monocular 3D human pose estimation (HPE).
Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos
To generate coherent motions, we first leverage the Kalman filter to construct smooth crops in the focus tunnel and inject the position embedding of the tunnel into attention layers to improve the continuity of the generated videos.
Grounded Knowledge-Enhanced Medical VLP for Chest X-Ray
Medical vision-language pre-training has emerged as a promising approach for learning domain-general representations of medical image and text.
Existence Is Chaos: Enhancing 3D Human Motion Prediction with Uncertainty Consideration
We believe our work could provide a novel perspective to consider the uncertainty quality for the general motion prediction task and encourage the studies in this field.
An AI-Driven Approach to Wind Turbine Bearing Fault Diagnosis from Acoustic Signals
This study aimed to develop a deep learning model for the classification of bearing faults in wind turbine generators from acoustic signals.
Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization
Without using knowledge distillation, ensemble model or extra training data during detector training, our proposed MIC outperforms previous SOTA methods trained with these complex techniques on LVIS.
Efficient Transferability Assessment for Selection of Pre-trained Detectors
Given this zoo, we adopt 7 target datasets from 5 diverse domains as the downstream target tasks for evaluation.
EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian Splatting
Specifically, our approach incorporates deformation fields to handle dynamic scenes, depth-guided supervision with spatial-temporal weight masks to optimize 3D targets with tool occlusion from a single viewpoint, and surface-aligned regularization terms to capture the much better geometry.
CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects
Customized text-to-video generation aims to generate high-quality videos guided by text prompts and subject references.
A graph-based multimodal framework to predict gentrification
Gentrification--the transformation of a low-income urban area caused by the influx of affluent residents--has many revitalizing benefits.
Semantic Face Compression for Metaverse: A Compact 3D Descriptor Based Approach
In this letter, we envision a new metaverse communication paradigm for virtual avatar faces, and develop the semantic face compression with compact 3D facial descriptors.
Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train
Foundation models have exhibited remarkable success in various applications, such as disease diagnosis and text report generation.
3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation
Notably, the original SAM architecture is designed for 2D natural images, therefore would not be able to extract the 3D spatial information from volumetric medical data effectively.
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
On the other hand, JPMA is proposed to assemble multiple hypotheses generated by D3DP into a single 3D pose for practical use.
Interactive Face Video Coding: A Generative Compression Framework
In this paper, we propose a novel framework for Interactive Face Video Coding (IFVC), which allows humans to interact with the intrinsic visual representations instead of the signals.
Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling
Each score is derived from machine perceptual differences between original and compressed images.
Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition
Our module can work seamlessly with the existing action classification model.
$C^*$-algebra Net: A New Approach Generalizing Neural Network Parameters to $C^*$-algebra
We apply our framework to practical problems such as density estimation and few-shot learning and show that our framework enables us to learn features of data even with a limited number of samples.
A DOMAIN TRANSFER BASED DATA AUGMENTATION METHOD FOR AUTOMATED RESPIRATORY CLASSIFICATION
The performance of deep neural network (DNN) based methods is highly data-dependent.
Ranked #16 on
Audio Classification
on ICBHI Respiratory Sound Database
(using extra training data)
Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives
From the view of feature, we break down the video into trajectories and first leverage trajectory feature in VideoQA to enhance the alignment between two modalities.
Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
We propose federation of unsupervised learning (FedUL), where the unlabeled data are transformed into surrogate labeled data for each of the clients, a modified model is trained by supervised FL, and the wanted model is recovered from the modified model.
Distributed On-Sensor Compute System for AR/VR Devices: A Semi-Analytical Simulation Framework for Power Estimation
Augmented Reality/Virtual Reality (AR/VR) glasses are widely foreseen as the next generation computing platform.
Self-attention based anchor proposal for skeleton-based action recognition
Skeleton sequences are widely used for action recognition task due to its lightweight and compact characteristics.
Enhancing Model Robustness and Fairness with Causality: A Regularization Approach
In this paper, we propose a simple and intuitive regularization approach to integrate causal knowledge during model training and build a robust and fair model by emphasizing causal features and de-emphasizing spurious features.
Unsupervised Federated Learning is Possible
We propose federation of unsupervised learning (FedUL), where the unlabeled data are transformed into surrogate labeled data for each of the clients, a modified model is trained by supervised FL, and the wanted model is recovered from the modified model.
End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization
In this paper, we show that the design and optimization of network architecture could be further improved for compression towards machine vision.
AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibaba
Conceptual graphs, which is a particular type of Knowledge Graphs, play an essential role in semantic search.
Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent
A novel ring FL topology as well as a map-reduce based synchronizing method are designed in the proposed RDFL to improve decentralized FL performance and bandwidth utilization.
Multi-Density Attention Network for Loop Filtering in Video Compression
In this paper, we propose a on-line scaling based multi-density attention network for loop filtering in video compression.
A Cross Channel Context Model for Latents in Deep Image Compression
The proposed cross channel context model is combined with the joint autoregressive and hierarchical prior entropy model.
Minimization of ion micromotion with artificial neural network
Minimizing the micromotion of the single trapped ion in a linear Paul trap is a tedious and time-consuming work, but is of great importance in cooling the ion into the motional ground state as well as maintaining long coherence time, which is crucial for quantum information processing and quantum computation.
Atomic Physics Quantum Physics
Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals
However, the classifier trained on the combined data is more robust and performs well on both the original test data and the counterfactual test data (e. g., 12%-25% increase in accuracy compared with the traditional classifier).
Identifying Spurious Correlations for Robust Text Classification
The predictions of text classifiers are often driven by spurious correlations -- e. g., the term `Spielberg' correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment.
Are Words Commensurate with Actions? Quantifying Commitment to a Cause from Online Public Messaging
Often, this public messaging is aimed at aligning the entity with a particular cause or issue, such as the environment or public health.
Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification
The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries.
Neural Architecture Search on Acoustic Scene Classification
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden.
When do Words Matter? Understanding the Impact of Lexical Choice on Audience Perception using Individual Treatment Effect Estimation
However, we lack general methods for estimating the causal effect of lexical choice on the perception of a specific sentence.
