Search Results for author:
Found 70 papers, 22 papers with code
Mind the Discriminability: Asymmetric Adversarial Domain Adaptation
Adversarial domain adaptation has made tremendous success by learning domain-invariant feature representations.
REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?
To this end, we propose the first robot task planning benchmark with vague REs (REI-Bench), where we discover that the vagueness of REs can severely degrade robot planning performance, leading to success rate drops of up to 77. 9%.
Generative Dataset Distillation using Min-Max Diffusion Model
In this work, we leverage the popular diffusion model as the generator to compute a surrogate dataset, boosted by a min-max loss to control the dataset's diversity and representativeness during training.
RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark
Despite this, most existing visual perception methods that utilize RAW data directly integrate image signal processing (ISP) stages with subsequent network modules, often overlooking potential synergies at the model level.
Emergence of Painting Ability via Recognition-Driven Evolution
The palette branch learns a limited colour palette, while the stroke branch parameterises each stroke using B\'ezier curves to render an image, subsequently evaluated by a high-level recognition module.
Unsupervised UAV 3D Trajectories Estimation with Sparse Point Clouds
Compact UAV systems, while advancing delivery and surveillance, pose significant security challenges due to their small size, which hinders detection by traditional methods.
NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries
Additionally, we also propose a 'Self-Correction' prompting mechanism and a new evaluation metric to enhance and measure both noise detection capability and answer quality.
Look a Group at Once: Multi-Slide Modeling for Survival Prediction
In this paper, we introduce GroupMIL, a novel framework inspired by the clinical practice of collective analysis, which models multiple slides as a single sample and organizes groups of patches and slides sequentially to capture cross-slide prognostic features.
UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration
In this work, we aim to deal with this challenging few-shot non-rigid point cloud registration problem.
Enhancing Dataset Distillation via Label Inconsistency Elimination and Learning Pattern Refinement
In the final evaluation, our M-DATM achieved accuracies of 0. 4061 and 0. 1831 on the CIFAR-100 and Tiny ImageNet datasets, ranking 1st in the Fixed Images Per Class (IPC) Track.
X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing
Human sensing, which employs various sensors and advanced deep learning technologies to accurately capture and interpret human body information, has significantly impacted fields like public security and robotics.
Feedback Favors the Generalization of Neural ODEs
Inspired by the feedback philosophy, we present feedback neural networks, showing that a feedback loop can flexibly correct the learned latent dynamics of neural ordinary differential equations (neural ODEs), leading to a prominent generalization improvement.
RecurFormer: Not All Transformer Heads Need Self-Attention
Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead.
IoT-LLM: Enhancing Real-World IoT Task Reasoning with Large Language Models
Large Language Models (LLMs) have demonstrated remarkable capabilities across textual and visual domains but often generate outputs that violate physical laws, revealing a gap in their understanding of the physical world.
GERA: Geometric Embedding for Efficient Point Registration Analysis
Point cloud registration aims to provide estimated transformations to align point clouds, which plays a crucial role in pose estimation of various navigation systems, such as surgical guidance systems and autonomous vehicles.
Editable Fairness: Fine-Grained Bias Mitigation in Language Models
Then, we propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.
More Than Positive and Negative: Communicating Fine Granularity in Medical Diagnosis
Specifically, we devise a division rule based on medical knowledge to divide positive cases into two subcategories, namely atypical positive and typical positive.
A Trustworthy AIoT-enabled Localization System via Federated Learning and Blockchain
There is a significant demand for indoor localization technology in smart buildings, and the most promising solution in this field is using RF sensors and fingerprinting-based methods that employ machine learning models trained on crowd-sourced user data gathered from IoT devices.
Salient Sparse Visual Odometry With Pose-Only Supervision
Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs.
Diffusion Model is a Good Pose Estimator from 3D RF-Vision
However, the mmWave radar has a limited resolution with severe noise, leading to inaccurate and inconsistent human pose estimation.
Compact 3D Gaussian Splatting For Dense Visual SLAM
Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes.
Reliable Spatial-Temporal Voxels For Multi-Modal Test-Time Adaptation
Motivated by the fact that reliable predictions should be consistent with their spatial-temporal correspondences, Latte aggregates consecutive frames in a slide window manner and constructs Spatial-Temopral (ST) voxels to capture temporally local prediction consistency for each modality.
PowerSkel: A Device-Free Framework Using CSI Signal for Human Skeleton Estimation in Power Station
WiFi-based human pose estimation is a suitable method for monitoring power operations due to its low cost, device-free, and robustness to various illumination conditions. In this paper, a novel Channel State Information (CSI)-based pose estimation framework, namely PowerSkel, is developed to address these challenges.
MaskFi: Unsupervised Learning of WiFi and Vision Representations for Multimodal Human Activity Recognition
Benefiting from our unsupervised learning procedure, the network requires only a small amount of annotated data for finetuning and can adapt to the new environment with better performance.
T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition
We find that the tiny model after network augmentation is much easier for a teacher to distill.
MMAUD: A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats
In response to the evolving challenges posed by small unmanned aerial vehicles (UAVs), which possess the potential to transport harmful payloads or independently cause damage, we introduce MMAUD: a comprehensive Multi-Modal Anti-UAV Dataset.
SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
In this paper, we propose SEnsor Alignment (SEA) for MTS-UDA, aiming to reduce domain discrepancy at both the local and global sensor levels.
TENT: Connect Language Models with IoT Sensors for Zero-Shot Activity Recognition
Through the IoT-language contrastive learning, we derive a unified semantic feature space that aligns multi-modal features with language embeddings, so that the IoT data corresponds to specific words that describe the IoT data.
AdaPose: Towards Cross-Site Device-Free Human Pose Estimation with Commodity WiFi
The results demonstrate the effectiveness and robustness of AdaPose in eliminating domain shift, thereby facilitating the widespread application of WiFi-based pose estimation in smart cities.
MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation
In this work, we propose Multi-modal Prior Aided (MoPA) domain adaptation to improve the performance of rare objects.
Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data
For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT.
Graph-Aware Contrasting for Multivariate Time-Series Classification
As MTS data typically originate from multiple sensors, ensuring spatial consistency becomes essential for the overall performance of contrastive learning on MTS data.
Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
Unsupervised domain adaptation (UDA) involves adapting a model trained on a label-rich source domain to an unlabeled target domain.
MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing
Extensive experiments have been conducted to compare the sensing capacity of each or several modalities in terms of multiple tasks.
Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation
We thus consider a more realistic \textit{Few-Shot Video-based Domain Adaptation} (FSVDA) scenario where we adapt video models with only a few target video samples.
Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation
In this paper, we explore Multi-Modal Continual Test-Time Adaptation (MM-CTTA) as a new extension of CTTA for 3D semantic segmentation.
Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation
The second module compares the outputs of augmented data from the current model to the outputs of weakly augmented data from the source model, forming a novel consistency regularization on the model to alleviate the accumulation of prediction errors.
Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey
Video analysis tasks such as action recognition have received increasing research interest with growing applications in fields such as smart healthcare, thanks to the introduction of large-scale datasets and deep learning-based representations.
AirFi: Empowering WiFi-based Passive Human Gesture Recognition to Unseen Environment via Domain Generalization
The AirFi is a novel domain generalization framework that learns the critical part of CSI regardless of different environments and generalizes the model to unseen scenarios, which does not require collecting any data for adaptation to the new environment.
GaitFi: Robust Device-Free Human Identification via WiFi and Vision Multimodal Learning
As an important biomarker for human identification, human gait can be collected at a distance by passive sensors without subject cooperation, which plays an essential role in crime prevention, security detection and other human identification applications.
MetaFi: Device-Free Pose Estimation via Commodity WiFi for Metaverse Avatar Simulation
Avatar refers to a representative of a physical user in the virtual world that can engage in different activities and interact with other objects in metaverse.
Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation
To enable video models to be applied seamlessly across video tasks in different environments, various Video Unsupervised Domain Adaptation (VUDA) methods have been proposed to improve the robustness and transferability of video models.
SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing
WiFi sensing has been evolving rapidly in recent years.
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain.
Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels
This paradigm, however, is prone to significant degeneration under heavy label noise, as the number of clean samples is too small for conventional methods to behave well.
Calibrating Class Weights with Multi-Modal Information for Partial Video Domain Adaptation
It utilizes a novel class weight calibration method to alleviate the negative transfer caused by incorrect class weights.
AutoFi: Towards Automatic WiFi Human Sensing via Geometric Self-Supervised Learning
The AutoFi transfers knowledge from randomly collected CSI samples into human gait recognition and achieves state-of-the-art performance.
EfficientFi: Towards Large-Scale Lightweight WiFi Sensing via CSI Compression
WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access.
SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition
The results validate that our method works well on wireless human activity recognition and person identification systems.
AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications
Here, we present a Deep Dental Multimodal Analysis (DDMA) framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model (the most accurate digital dental model), and a fusion model to generate 3D fused crown-root-bone structures with high fidelity and accurate occlusal and dentition information.
Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
Video-based Unsupervised Domain Adaptation (VUDA) methods improve the robustness of video models, enabling them to be applied to action recognition tasks across different environments.
Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study
While action recognition (AR) has gained large improvements with the introduction of large-scale video datasets and the development of deep neural networks, AR models robust to challenging environments in real-world scenarios are still under-explored.
Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA), a branch of transfer learning where labels for target samples are unavailable, has been widely researched and developed in recent years with the help of adversarially trained models.
Towards Realistic Visual Dubbing with Heterogeneous Sources
The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video.
Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation
We show that with the help of a content-rich discrete visual codebook from VQ-VAE, the discrete diffusion model can also generate high fidelity images with global context, which compensates for the deficiency of the classical autoregressive model along pixel space.
Self-Supervised Video Representation Learning by Video Incoherence Detection
This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning.
Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment
Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios.
Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network
For videos, such negative transfer could be triggered by both spatial and temporal features, which leads to a more challenging Partial Video Domain Adaptation (PVDA) problem.
Aligning Correlation Information for Domain Adaptation in Action Recognition
Yet correlation features of the same action would differ across domains due to domain shift.
Suppressing Mislabeled Data via Grouping and Self-Attention
Specifically, this plug-and-play AFM first leverages a \textit{group-to-attend} module to construct groups and assign attention weights for group-wise samples, and then uses a \textit{mixup} module with the attention weights to interpolate massive noisy-suppressed samples.
Effective Action Recognition with Embedded Key Point Shifts
Temporal feature extraction is an essential technique in video-based action recognition.
PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition
Empirical results prove the effectiveness and efficiency of our PNL module, which achieves state-of-the-art performance of 83. 09% on the Mini-Kinetics dataset, with decreased computation cost compared to the non-local block.
ARID: A New Dataset for Recognizing Action in the Dark
We bridge the gap of the lack of data for this task by collecting a new dataset: the Action Recognition in the Dark (ARID) dataset.
Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition
Temporal feature extraction is an important issue in video-based action recognition.
Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training
The proposed MDAT stabilizes the gradient reversing in ARN by replacing the domain classifier with a reconstruction network, and in this manner ARN conducts both feature-level and pixel-level domain alignment without involving extra network structures.
Suppressing Uncertainties for Large-Scale Facial Expression Recognition
Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators.
Facial Expression Recognition
Facial Expression Recognition (FER)
Bootstrap Model Ensemble and Rank Loss for Engagement Intensity Regression
Based on our winner solution last year, we mainly explore head features and body features with a bootstrap strategy and two novel loss functions in this paper.
Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition
Extensive experiments show that our RAN and region biased loss largely improve the performance of FER with occlusion and variant pose.
Ranked #2 on
Facial Expression Recognition (FER)
on SFEW
Facial Expression Recognition
Facial Expression Recognition (FER)
Kervolutional Neural Networks
Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks.
