Search Results for author:
Found 289 papers, 90 papers with code
Domain-specific knowledge distillation yields smaller and better models for conversational commerce
We demonstrate that knowledge distillation can be used not only to reduce model size, but to simultaneously adapt a contextual language model to a specific domain.
多特征融合的越英端到端语音翻译方法(A Vietnamese-English end-to-end speech translation method based on multi-feature fusion)
“语音翻译的编码器需要同时编码语音中的声学和语义信息, 单一的Fbank或Wav2vec2语音特征表征能力存在不足。本文通过分析人工的Fbank特征与自监督的Wav2vec2特征间的差异性, 提出基于交叉注意力机制的声学特征融合方法, 并探究了不同的自监督特征和融合方式, 加强模型对语音中声学和语义信息的学习。结合越南语语音特点, 以Fbank特征为主、Pitch特征为辅混合编码Fbank表征, 构建多特征融合的越-英语音翻译模型。实验表明, 使用多特征的语音翻译模型相比单特征翻译效果更优, 与简单的特征拼接方法相比更有效, 所提的多特征融合方法在越-英语音翻译任务上提升了1. 97个BLEU值。”
RealMedDial: A Real Telemedical Dialogue Dataset Collected from Online Chinese Short-Video Clips
We collected and annotated a wide range of meta-data with respect to medical dialogue including doctor profiles, hospital departments, diseases and symptoms for fine-grained analysis on language usage pattern and clinical diagnosis.
Two Languages Are Better than One: Bilingual Enhancement for Chinese Named Entity Recognition
Chinese Named Entity Recognition (NER) has continued to attract research attention.
Automated Quality Evaluation of Cervical Cytopathology Whole Slide Images Based on Content Analysis
The ThinPrep Cytologic Test (TCT) is the most widely used method for cervical cancer screening, and the sample quality directly impacts the accuracy of the diagnosis.
FauForensics: Boosting Audio-Visual Deepfake Detection with Facial Action Units
The rapid evolution of generative AI has increased the threat of realistic audio-visual deepfakes, demanding robust detection methods.
Agent-as-a-Service based on Agent Network
AaaS-AN unifies the entire agent lifecycle, including construction, integration, interoperability, and networked collaboration, through two core components: (1) a dynamic Agent Network, which models agents and agent groups as vertexes that self-organize within the network based on task and role dependencies; (2) service-oriented agents, incorporating service discovery, registration, and interoperability protocols.
Seed1.5-VL Technical Report
We present Seed1. 5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning.
DiffVQA: Video Quality Assessment Using Diffusion Feature Extractor
To address this limitation, we introduce a novel VQA framework, DiffVQA, which harnesses the robust generalization capabilities of diffusion models pre-trained on extensive datasets.
Explainable Machine Learning for Cyberattack Identification from Traffic Flows
The increasing automation of traffic management systems has made them prime targets for cyberattacks, disrupting urban mobility and public safety.
Machine Learning for Cyber-Attack Identification from Traffic Flows
This paper presents our simulation of cyber-attacks and detection strategies on the traffic control system in Daytona Beach, FL.
GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution
In this paper, we propose GuideSR, a novel single-step diffusion-based image super-resolution (SR) model specifically designed to enhance image fidelity.
POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications
Large language models (LLMs) have become a disruptive force in the industry, introducing unprecedented capabilities in natural language processing, logical reasoning and so on.
SEGA: Drivable 3D Gaussian Head Avatar from a Single Image
Creating photorealistic 3D head avatars from limited input has become increasingly important for applications in virtual reality, telepresence, and digital entertainment.
Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input
First, the IMU sensor inputs, the optional egocentric image, and text description of human motion are encoded into the latent space of a motion VQ-VAE.
Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue Generation
Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not included in their training data.
An LLM-Driven Multi-Agent Debate System for Mendelian Diseases
Accurate diagnosis of Mendelian diseases is crucial for precision therapy and assistance in preimplantation genetic diagnosis.
ZFusion: An Effective Fuser of Camera and 4D Radar for 3D Object Perception in Autonomous Driving
In typical traffic scenarios like the VoD (View-of-Delft) dataset, experiments show that with reasonable inference speed, ZFusion achieved the state-of-the-art mAP (mean average precision) in the region of interest, while having competitive mAP in the entire area compared to the baseline methods, which demonstrates performance close to LiDAR and greatly outperforms those camera-only methods.
SelfMedHPM: Self Pre-training With Hard Patches Mining Masked Autoencoders For Medical Image Segmentation
In recent years, deep learning methods such as convolutional neural network (CNN) and transformers have made significant progress in CT multi-organ segmentation.
GeoRAG: A Question-Answering Approach from a Geographical Perspective
Geographic Question Answering (GeoQA) addresses natural language queries in geographic domains to fulfill complex user demands and improve information retrieval efficiency.
Training-Free Text-Guided Image Editing with Visual Autoregressive Model
Text-guided image editing is an essential task that enables users to modify images through natural language descriptions.
Style Quantization for Data-Efficient GAN Training
Instead of direct quantization, we first map the input latent variables into a less entangled ``style'' space and apply quantization using a learnable codebook.
FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video
Egocentric motion capture with a head-mounted body-facing stereo camera is crucial for VR and AR applications but presents significant challenges such as heavy occlusions and limited annotated real-world data.
SceneMI: Motion In-betweening for Modeling Human-Scene Interactions
Modeling human-scene interactions (HSI) is essential for understanding and simulating everyday human behaviors.
Towards Harmless Multimodal Assistants with Blind Preference Optimization
Additionally, applying BPO to the MMSafe-PO dataset greatly reduces the base MLLM's unsafe rate on other safety benchmarks (14. 5% on MM-SafetyBench and 82. 9% on HarmEval, demonstrating the effectiveness and robustness of both the dataset and the approach.
A Survey on Human Interaction Motion Generation
Humans inhabit a world defined by interactions -- with other humans, objects, and environments.
Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars
Our system is capable of producing 3D Gaussian avatars that support dynamic animation, including accurate facial expression transfer.
Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation
Our experiments show that the new camera configurations with back views provide superior support for 3D pose tracking compared to only frontal placements.
KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception
Inspired by the Human Visual System (HVS) that links global quality to the local texture of different regions and their visual saliency, we propose a Kaleidoscope Video Quality Assessment (KVQ) framework, which aims to effectively assess both saliency and local texture, thereby facilitating the assessment of global quality.
Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning
Chain-of-Thought (CoT) reasoning has proven effective in natural language tasks but remains underexplored in multimodal alignment.
STeCa: Step-level Trajectory Calibration for LLM Agent Learning
To address this, we highlight the importance of timely calibration and the need to automatically construct calibration trajectories for training agents.
Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks.
Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors
Intelligent tutoring agents powered by large language models (LLMs) have been increasingly explored to deliver personalized guidance in areas such as language learning and science education.
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination inefficiencies.
EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Camera
To address these limitations, we introduce EventEgo3D++, the first approach that leverages a monocular event camera with a fisheye lens for 3D human motion capture.
Molecular Odor Prediction Based on Multi-Feature Graph Attention Networks
Olfactory perception plays a critical role in both human and organismal interactions, yet understanding of its underlying mechanisms and influencing factors remain insufficient.
Auto-Prompting SAM for Weakly Supervised Landslide Extraction
These informative prompts are able to identify the extent of landslide areas (box prompts) and denote the centers of landslide objects (point prompts), guiding SAM in landslide segmentation.
Discrete Curvature Graph Information Bottleneck
CurvGIB advances the Variational Information Bottleneck (VIB) principle for Ricci curvature optimization to learn the optimal information transport pattern for specific downstream tasks.
InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
Face image restoration aims to enhance degraded facial images while addressing challenges such as diverse degradation types, real-time processing demands, and, most crucially, the preservation of identity-specific features.
RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation
Standard clothing asset generation involves creating forward-facing flat-lay garment images displayed on a clear background by extracting clothing information from diverse real-world contexts, which presents significant challenges due to highly standardized sampling distributions and precise structural requirements in the generated images.
TextMaster: Universal Controllable Text Edit
In image editing tasks, high-quality text editing capabilities can significantly reduce human and material resource costs.
Delving Deep into Engagement Prediction of Short Videos
Understanding and modeling the popularity of User Generated Content (UGC) short videos on social media platforms presents a critical challenge with broad implications for content creators and recommendation systems.
Multimodal Trajectory Prediction for Autonomous Driving on Unstructured Roads using Deep Convolutional Network
Recently, the application of autonomous driving in open-pit mining has garnered increasing attention for achieving safe and efficient mineral transportation.
EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Avatars
Immersive VR telepresence ideally means being able to interact and communicate with digital avatars that are indistinguishable from and precisely reflect the behaviour of their real counterparts.
UniMo: Universal Motion Correction For Medical Images without Network Retraining
In this paper, we introduce a Universal Motion Correction (UniMo) framework, leveraging deep neural networks to tackle the challenges of motion correction across diverse imaging modalities.
E2CL: Exploration-based Error Correction Learning for Embodied Agents
Language models are exhibiting increasing capability in knowledge utilization and reasoning.
RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment
Large Language Models (LLMs) like GPT-4, MedPaLM-2, and Med-Gemini achieve performance competitively with human experts across various medical benchmarks.
MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data
Generative adversarial networks (GANs) have made impressive advances in image generation, but they often require large-scale training data to avoid degradation caused by discriminator overfitting.
Multi-periodicity dependency Transformer based on spectrum offset for radio frequency fingerprint identification
These challenges diminish the capability of RFFI methods in feature representation, complicating the effective identification of device identities.
ControlNeXt: Powerful and Efficient Control for Image and Video Generation
In this paper, we propose ControlNeXt: a powerful and efficient method for controllable image and video generation.
Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation
During reinforcement learning training, the proximal policy optimization algorithm is used to fine-tune the policy, enabling the generation of empathetic responses.
POA: Pre-training Once for Models of All Sizes
Once pre-trained, POA allows the extraction of pre-trained models of diverse sizes for downstream tasks.
Mitral Regurgitation Recognition based on Unsupervised Out-of-Distribution Detection with Residual Diffusion Amplification
Since MR data is limited and has large intra-class variability, we propose an unsupervised out-of-distribution (OOD) detection method to identify MR rather than building a deep classifier.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Matting by Generation
This paper introduces an innovative approach for image matting that redefines the traditional regression-based task as a generative modeling challenge.
SpaER: Learning Spatio-temporal Equivariant Representations for Fetal Brain Motion Tracking
In this paper, we introduce SpaER, a pioneering method for fetal motion tracking that leverages equivariant filters and self-attention mechanisms to effectively learn spatio-temporal representations.
UMono: Physical Model Informed Hybrid CNN-Transformer Framework for Underwater Monocular Depth Estimation
Underwater monocular depth estimation serves as the foundation for tasks such as 3D reconstruction of underwater scenes.
Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight
This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs).
Soli-enabled Noncontact Heart Rate Detection for Sleep and Meditation Tracking
This study represents the first application of the noncontact HR detection technology to sleep and meditation tracking, offering a promising alternative to wearable devices for HR monitoring during sleep and meditation.
SpectralKAN: Kolmogorov-Arnold Network for Hyperspectral Images Change Detection
In this paper, we propose an spectral Kolmogorov-Arnold Network for HSIs-CD (SpectralKAN).
Root Cause Localization for Microservice Systems in Cloud-edge Collaborative Environments
Experiments conducted on the dataset collected from the benchmark show that MicroCERCL can accurately localize the root cause of microservice systems in such environments, significantly outperforming state-of-the-art approaches with an increase of at least 24. 1% in top-1 accuracy.
Explainable AI for Comparative Analysis of Intrusion Detection Models
We trained all models to the accuracy of 90\% on the UNSW-NB15 Dataset.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+4
SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding
Remote Sensing Large Multi-Modal Models (RSLMMs) are developing rapidly and showcase significant capabilities in remote sensing imagery (RSI) comprehension.
RobustSAM: Segment Anything Robustly on Degraded Images
Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system.
DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer
Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quality face images for downstream tasks.
Ranked #1 on
Face Image Quality Assessment
on CGFIQA-40k
Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior
Capturing High Dynamic Range (HDR) scenery using 8-bit cameras often suffers from over-/underexposure, loss of fine details due to low bit-depth compression, skewed color distributions, and strong noise in dark areas.
A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions
With the advent of Large Language Models (LLMs), medical artificial intelligence (AI) has experienced substantial technological progress and paradigm shifts, highlighting the potential of LLMs to streamline healthcare delivery and improve patient outcomes.
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection.
No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks
In particular, we analyze the two most representative types of attack approaches: Explicit Harmful Attack (EHA) and Identity-Shifting Attack (ISA).
Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation
Integrating multimodal knowledge into large language models (LLMs) represents a significant advancement in dialogue generation capabilities.
Enhancing DETRs Variants through Improved Content Query and Similar Query Aggregation
The design of the query is crucial for the performance of DETR and its variants.
MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems.
Hi-Gen: Generative Retrieval For Large-Scale Personalized E-commerce Search
To overcome these problems, we introduce an efficient Hierarchical encoding-decoding Generative retrieval method (Hi-Gen) for large-scale personalized E-commerce search systems.
EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams
In response to the existing limitations, this paper 1) introduces a new problem, i. e., 3D human motion capture from an egocentric monocular event camera with a fisheye lens, and 2) proposes the first approach to it called EventEgo3D (EE3D).
DiffBody: Human Body Restoration by Imagining with Generative Diffusion Prior
Human body restoration plays a vital role in various applications related to the human body.
Application of Quantum Tensor Networks for Protein Classification
We show that protein sequences can be thought of as sentences in natural language processing and can be parsed using the existing Quantum Natural Language framework into parameterized quantum circuits of reasonable qubits, which can be trained to solve various protein-related machine-learning problems.
Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue
Inspired by decision-making theories in cognitive science, we propose a novel target-constrained bidirectional planning (TRIP) approach, which plans an appropriate dialogue path by looking ahead and looking back.
Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training
In this study, we proposed a multi-view contrastive self-supervised method to improve thyroid nodule classification and segmentation performance with limited manual labels.
Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents.
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining
Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence.
Ranked #1 on
Zero-Shot Transfer Image Classification
on ImageNet
(using extra training data)
Zero-Shot Cross-Modal Retrieval
Zero-shot Image Retrieval
+3
OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy
We advance the field of Parameter-Efficient Fine-Tuning (PEFT) with our novel multi-adapter method, OrchMoE, which capitalizes on modular skill architecture for enhanced forward transfer in neural networks.
Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis
Clinicians typically employ both intuitive and analytic reasoning to formulate a differential diagnosis.
Enhancing Automatic Modulation Recognition through Robust Global Feature Extraction
Modulated signals exhibit long temporal dependencies, and extracting global features is crucial in identifying modulation schemes.
Towards Better Vision-Inspired Vision-Language Models
In this paper we present a vision-inspired vision-language connection module dubbed as VIVL which efficiently exploits the vision cue for VL models.
3D Human Pose Perception from Egocentric Stereo Videos
Hence, existing methods often fail to accurately estimate complex 3D poses from egocentric views.
Ranked #3 on
Egocentric Pose Estimation
on UnrealEgo
Personalized Restoration via Dual-Pivot Tuning
This approach ensures that personalization does not interfere with the restoration process, resulting in a natural appearance with high fidelity to the person's identity and the attributes of the degraded image.
COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal
In recent years, there has been a growing interest in exploring dialogues with more complex goals, such as negotiation, persuasion, and emotional support, which go beyond traditional service-focused dialogue systems.
Robust Communicative Multi-Agent Reinforcement Learning with Active Defense
We propose an active defense strategy, where agents automatically reduce the impact of potentially harmful messages on the final decision.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
Prior studies on Remote Sensing Foundation Model (RSFM) reveal immense potential towards a generic model for Earth Observation.
Ranked #1 on
Zero-shot Classification (unified classes)
on AID
Towards 4D Human Video Stylization
To overcome these limitations, we leverage Neural Radiance Fields (NeRFs) to represent videos, conducting stylization in the rendered feature space.
Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement
In this work, we explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion.
Ranked #1 on
Egocentric Pose Estimation
on GlobalEgoMocap Test Dataset
(using extra training data)
Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks
The case study involving additional biomedical NLP tasks further shows Taiyi's considerable potential for bilingual biomedical multi-tasking.
Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation
Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep t ("time indexing"), which struggles to predict precise object movements.
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image.
A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations
Emotion recognition in conversations (ERC), the task of recognizing the emotion of each utterance in a conversation, is crucial for building empathetic machines.
Ranked #1 on
Emotion Recognition in Conversation
on IEMOCAP
Emotion Recognition in Conversation
Multimodal Emotion Recognition
Self-Detoxifying Language Models via Toxification Reversal
Drawing on this idea, we devise a method to identify the toxification direction from the normal generation process to the one prompted with the negative prefix, and then steer the generation to the reversed direction by manipulating the information movement within the attention layers.
Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation
Target-oriented dialogue systems, designed to proactively steer conversations toward predefined targets or accomplish specific system-side goals, are an exciting area in conversational AI.
PatchProto Networks for Few-shot Visual Anomaly Classification
The visual anomaly diagnosis can automatically analyze the defective products, which has been widely applied in industrial quality inspection.
Segmented Harmonic Loss: Handling Class-Imbalanced Multi-Label Clinical Data for Medical Coding with Large Language Models
In this paper, we gauge the extent of the impact by evaluating the performance of LLMs for the task of medical coding on real-life noisy data.
Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification
In this way, the pre-training task and the T2I-ReID task are made consistent with each other on both data and training levels.
FFPN: Fourier Feature Pyramid Network for Ultrasound Image Segmentation
In this paper, we introduce a novel Fourier-anchor-based DTS framework called Fourier Feature Pyramid Network (FFPN) to address the aforementioned issues.
Model predictive control strategy in waked wind farms for optimal fatigue loads
In this paper, a closed-loop model predictive controller is developed that minimizes the wind farm tracking errors, the dynamical fatigue load, and and the load equalization.
Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation
State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e. g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR.
Learning Implicit Entity-object Relations by Bidirectional Generative Alignment for Multimodal NER
Our BGA-MNER consists of \texttt{image2text} and \texttt{text2image} generation with respect to entity-salient content in two modalities.
ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation
To overcome this challenge, we propose an innovative multimodal framework, called ZRIGF, which assimilates image-grounded information for dialogue generation in zero-resource situations.
Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration
In this paper, we propose a deep learning-based character stroke extraction method that takes semantic features and prior information of strokes into consideration.
Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network.
Image Harmonization with Diffusion Model
In this paper, we present a novel approach for image harmonization by leveraging diffusion models.
Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers with Partially Annotated Ultrasound Images
To address this issue, a novel Two-Stage Detection and Diagnosis Network (TSDDNet) is proposed based on weakly supervised learning to enhance diagnostic accuracy of the ultrasound-based CAD for breast cancers.
Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification
Second, we introduce a regularization technique that utilizes style interpolation consistency in the frequency space to encourage self-consistency in the logit space of the model output.
Medical Dialogue Generation via Dual Flow Modeling
It extracts the medical entities and dialogue acts used in the dialogue history and models their transitions with an entity-centric graph flow and a sequential act flow, respectively.
Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue
The key to achieving this task lies in planning dialogue paths that smoothly and coherently direct conversations towards the target.
Exploring Effective Factors for Improving Visual In-Context Learning
By doing this, the model can leverage the diverse knowledge stored in different parts of the model to improve its performance on new tasks.
Robust Calibrate Proxy Loss for Deep Metric Learning
The mainstream researche in deep metric learning can be divided into two genres: proxy-based and pair-based methods.
Learning to Recover Spectral Reflectance from RGB Images
Instead of relying on naive end-to-end training, we also propose a novel architecture that integrates the physical relationship between the spectral reflectance and the corresponding RGB images into the network based on our mathematical analysis.
PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
To handle the variances of objects as time proceeds, a novel scheme of progressive decoding is used to update pose and shape queries at each frame.
Ranked #32 on
3D Human Pose Estimation
on 3DPW
NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attacks
Our work could provide a useful tool to defend against certain adversarial attacks on deep neural networks.
Exploring Adversarial Attacks on Neural Networks: An Explainable Approach
Finally, we demonstrate that the layers $Block4\_conv1$ and $Block5\_cov1$ of the VGG-16 model are more susceptible to adversarial attacks.
MetaMorph: Learning Metamorphic Image Transformation With Appearance Changes
This paper presents a novel predictive model, MetaMorph, for metamorphic registration of images with appearance changes (i. e., caused by brain tumors).
Temporal Segment Transformer for Action Segmentation
To deal with these issues, we propose an attention based approach which we call \textit{temporal segment transformer}, for joint segment relation modeling and denoising.
DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs
Close-up facial images captured at short distances often suffer from perspective distortion, resulting in exaggerated facial features and unnatural/unattractive appearances.
Differentiable Rotamer Sampling with Molecular Force Fields
Molecular dynamics is the primary computational method by which modern structural biology explores macromolecule structure and function.
Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help
Multi-agent reinforcement learning (MARL) has achieved great progress in cooperative tasks in recent years.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Low Entropy Communication in Multi-Agent Reinforcement Learning
Communication in multi-agent reinforcement learning has been drawing attention recently for its significant role in cooperation.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
CSDR-BERT: a pre-trained scientific dataset match model for Chinese Scientific Dataset Retrieval
As the number of open and shared scientific datasets on the Internet increases under the open science movement, efficiently retrieving these datasets is a crucial task in information retrieval (IR) research.
Graph Contrastive Learning for Skeleton-based Action Recognition
In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences.
Ranked #17 on
Skeleton Based Action Recognition
on NTU RGB+D
FE-TCM: Filter-Enhanced Transformer Click Model for Web Search
In this paper, We use Transformer as the backbone network of feature extraction, add filter layer innovatively, and propose a new Filter-Enhanced Transformer Click Model (FE-TCM) for web search.
Energy-Efficient Adaptive 3D Sensing
Active depth sensing achieves robust depth estimation but is usually limited by the sensing range.
Uncertainty-guided Learning for Improving Image Manipulation Detection
Image manipulation detection (IMD) is of vital importance as faking images and spreading misinformation can be malicious and harm our daily life.
Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation
In this work, we propose a novel feature enhancement network to simultaneously model short- and long-term temporal correlation.
s-Adaptive Decoupled Prototype for Few-Shot Object Detection
To provide precise information for the query image, the prototype is decoupled into task-specific ones, which provide tailored guidance for 'where to look' and 'what to look for', respectively.
Scene-aware Egocentric 3D Human Pose Estimation
To this end, we propose an egocentric depth estimation network to predict the scene depth map from a wide-view egocentric fisheye camera while mitigating the occlusion of the human body with a depth-inpainting network.
Ranked #3 on
Egocentric Pose Estimation
on GlobalEgoMocap Test Dataset
(using extra training data)
COLA: Improving Conversational Recommender Systems by Collaborative Augmentation
Inspired by collaborative filtering, we propose a collaborative augmentation (COLA) method to simultaneously improve both item representation learning and user preference modeling to address these issues.
WAIR-D: Wireless AI Research Dataset
The statistical data hinder the trained AI models from further fine-tuning for a specific scenario, and ray-tracing data with limited environments lower down the generalization capability of the trained AI models.
Privacy-Preserving Visual Localization with Event Cameras
We present a robust, privacy-preserving visual localization algorithm using event cameras.
Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation
An intuitive solution is ``coupling'' the CAM with the long-range attention matrix of visual transformers (ViT) We find that the direct ``coupling'', e. g., pixel-wise multiplication of attention and activation, achieves a more global coverage (on the foreground), but unfortunately goes with a great increase of false positives, i. e., background pixels are mistakenly included.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
CAE v2: Context Autoencoder with CLIP Target
That is to say, the smaller the model, the lower the mask ratio needs to be.
Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining
The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO.
Ranked #7 on
Object Detection
on COCO test-dev
A survey on the development status and application prospects of knowledge graph in smart grids
With the advent of the electric power big data era, semantic interoperability and interconnection of power data have received extensive attention.
Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers
We introduce a newly designed framework that (i) simultaneously derives features from both image and latent shape spaces with large intra-class variations; and (ii) gains increased model interpretability by allowing direct access to the underlying geometric features of image data.
Self-Supervised 2D/3D Registration for X-Ray to CT Image Fusion
Deep Learning-based 2D/3D registration enables fast, robust, and accurate X-ray to CT image fusion when large annotated paired datasets are available for training.
RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
Recently, transformer-based networks have shown impressive results in semantic segmentation.
Ranked #2 on
Real-Time Semantic Segmentation
on CamVid
U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction
Therefore, we designed a U-shaped High-Resolution Network (U-HRNet), which adds more stages after the feature map with strongest semantic representation and relaxes the constraint in HRNet that all resolutions need to be calculated parallel for a newly added stage.
Beam Management in Ultra-dense mmWave Network via Federated Reinforcement Learning: An Intelligent and Secure Approach
Deploying ultra-dense networks that operate on millimeter wave (mmWave) band is a promising way to address the tremendous growth on mobile data traffic.
Design of the PID temperature controller for an alkaline electrolysis system with time delays
This paper focuses on the design of the PID temperature controller for an alkaline electrolysis system to achieve fast and stable temperature control.
Sample-Efficient Multi-Agent Reinforcement Learning with Demonstrations for Flocking Control
By pretraining with non-expert demonstrations, PwD-MARL improves sample efficiency in the process of online MARL with a warm start.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control
Flocking control is a challenging problem, where multiple agents, such as drones or vehicles, need to reach a target position while maintaining the flock and avoiding collisions with obstacles and collisions among agents in the environment.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition
In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions.
Multilayer Fisher extreme learning machine for classification
To address this problem, a novel Fisher extreme learning machine autoencoder (FELM-AE) is proposed and is used as the component for the multilayer Fisher extreme leaning machine (ML-FELM).
Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems
Recommendation dialogue systems aim to build social bonds with users and provide high-quality recommendations.
IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation
In particular, we firstly formulate video frames as a series of instance-guided tokens and each token is in charge of predicting the 3D pose of a human instance.
Ranked #11 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture
We present UnrealEgo, i. e., a new large-scale naturalistic dataset for egocentric 3D human pose estimation.
Ranked #5 on
Egocentric Pose Estimation
on UnrealEgo
Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing.
Seeing Far in the Dark with Patterned Flash
Flash illumination is widely used in imaging under low-light environments.
Dynamic Graph Reasoning for Multi-person 3D Pose Estimation
Finally, the 3D poses are decoded according to dynamic decoding graphs for each detected person.
3D Multi-Person Pose Estimation (absolute)
3D Multi-Person Pose Estimation (root-relative)
+1
UFO: Unified Feature Optimization
UFO aims to benefit each single task with a large-scale pretraining on all tasks.
Action Quality Assessment with Temporal Parsing Transformer
Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences.
Learning Granularity-Unified Representations for Text-to-Image Person Re-identification
In PGU, we adopt a set of shared and learnable prototypes as the queries to extract diverse and semantically aligned features for both modalities in the granularity-unified feature space, which further promotes the ReID performance.
Privacy-preserving household load forecasting based on non-intrusive load monitoring: A federated deep learning approach
In this method, the integrated power is decomposed into individual device power by non-intrusive load monitoring, and the power of individual appliances is predicted separately using a federated deep learning model.
MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue
Firstly, we build an evaluation metric composed of 5 groups of parallel sub-metrics called Multi-Metric Evaluation (MME) to evaluate the quality of dialogue comprehensively.
Structured Light with Redundancy Codes
We propose three applications using our redundancy codes: (1) Self error-correction for SL imaging under strong ambient light, (2) Error detection for adaptive reconstruction under global illumination, and (3) Interference filtering with device-specific projection sequence encoding, especially for event camera-based SL and light curtain devices.
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
In this paper, we rethink the paradigm and explore a new regime: {\em fine-tuning a small part of parameters in the backbone}.
Ranked #15 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map
The integration of a SLAM algorithm with place recognition technology empowers it with the ability to mitigate accumulated errors and to relocalize itself.
One-to-N & N-to-One: Two Advanced Backdoor Attacks Against Deep Learning Models
In this article, for the first time, we propose two advanced backdoor attacks, the multi-target backdoor attacks and multi-trigger backdoor attacks: 1) One-to-N attack, where the attacker can trigger multiple backdoor targets by controlling the different intensities of the same backdoor; 2) N-to-One attack, where such attack is triggered only when all the N backdoors are satisfied.
Human-Object Interaction Detection via Disentangled Transformer
To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder.
PP-Matting: High-Accuracy Natural Image Matting
Also, we propose a semantic context branch (SCB) that adopts a semantic segmentation subtask.
Ranked #4 on
Image Matting
on Distinctions-646
Implicit Sample Extension for Unsupervised Person Re-Identification
Specifically, we generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy.
Glass Segmentation with RGB-Thermal Image Pairs
Due to the large difference between the transmission property of visible light and that of the thermal energy through the glass where most glass is transparent to the visible light but opaque to thermal energy, glass regions of a scene are made more distinguishable with a pair of RGB and thermal images than solely with an RGB image.
NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks
Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs.
Exploiting Pairwise Mutual Information for Knowledge-Grounded Dialogue
Correlation integration is designed to fully exploit the pairwise mutual information among dialogue context, knowledge, and responses, while overall integration adopts an integration gate to capture global information.
Hierarchical Memory Learning for Fine-Grained Scene Graph Generation
After the autonomous partition of coarse and fine predicates, the model is first trained on the coarse predicates and then learns the fine predicates.
Image Steganography based on Style Transfer
Image steganography is the art and science of using images as cover for covert communications.
Thermal Modelling and Controller Design of an Alkaline Electrolysis System under Dynamic Operating Conditions
A control-oriented thermal model is established in the form of a third-order time-delay process, which is used for simulation and controller design.
Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks
Recent researches demonstrate that Deep Neural Networks (DNN) models are vulnerable to backdoor attacks.
Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision
Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision.
Ranked #4 on
Egocentric Pose Estimation
on GlobalEgoMocap Test Dataset
(using extra training data)
An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems
The effectiveness of the FSRE-AdaTSK is demonstrated on 19 datasets of which five are in more than 2000 dimension including two with dimension greater than 7000.
Compression-Resistant Backdoor Attack against Deep Neural Networks
After training, the backdoor attack against DNN is robust to image compression.
Training Object Detectors From Scratch: An Empirical Study in the Era of Vision Transformer
Instead of proposing a specific vision transformer based detector, in this work, our goal is to reveal the insights of training vision transformer based detectors from scratch.
Hybrid Atlas Building with Deep Registration Priors
Registration-based atlas building often poses computational challenges in high-dimensional image spaces.
MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection
The multiple accurate cues from multiple DFs are then simultaneously propagated to the saliency network with a multi-guidance loss.
3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image
Our key intuition is that style transfer and view synthesis have to be jointly modeled for this task.
Relative Distributed Formation and Obstacle Avoidance with Multi-agent Reinforcement Learning
In this paper, we propose a distributed formation and obstacle avoidance method based on multi-agent reinforcement learning (MARL).
Model Predictive Control
Multi-agent Reinforcement Learning
+3
Image-Guided Navigation of a Robotic Ultrasound Probe for Autonomous Spinal Sonography Using a Shadow-aware Dual-Agent Framework
Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers.
URIR: Recommendation algorithm of user RNN encoder and item encoder based on knowledge graph
This implies that URIR can effectively use knowledge graph to obtain better user codes and item codes, thereby obtaining better recommendation results.
Zero-bias Deep Neural Network for Quickest RF Signal Surveillance
In this paper, we provide a deep learning framework for RF signal surveillance.
One-Bit Matrix Completion with Differential Privacy
In this paper, we propose a unified framework for ensuring a strong privacy guarantee of one-bit matrix completion with DP.
SAM: A Self-adaptive Attention Module for Context-Aware Recommendation System
In this work, we propose a novel and general self-adaptive module, the Self-adaptive Attention Module (SAM), which adjusts the selection bias by capturing contextual information based on its representation.
Applying Differential Privacy to Tensor Completion
Tensor completion aims at filling the missing or unobserved entries based on partially observed tensors.
A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks
Biphasic facial age translation aims at predicting the appearance of the input face at any age.
To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection
Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate matches between image-level annotations and salient objects are still inadequate.
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.
Learning to Detect: A Data-driven Approach for Network Intrusion Detection
With massive data being generated daily and the ever-increasing interconnectivity of the world's Internet infrastructures, a machine learning based intrusion detection system (IDS) has become a vital component to protect our economic and national security.
Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound
In this study, we build a novel multi-label learning (MLL) scheme to identify multiple standard planes and corresponding anatomical structures of fetus simultaneously.
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion.
Flip Learning: Erase to Segment
Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation.
Distributed Learning for Time-varying Networks: A Scalable Design
The wireless network is undergoing a trend from "onnection of things" to "connection of intelligence".
A Novel Interactive Two-stage Joint Retail Electricity Market for Multiple Microgrids
To accommodate the advent of microgrids (MG) managing distributed energy resources (DER) in distribution systems, an interactive two-stage joint retail electricity market mechanism is proposed to provide an effective platform for these prosumers to proactively join in retail transactions.
Deep Iterative 2D/3D Registration
A refinement step using the classical optimization-based 2D/3D registration method applied in combination with Deep Learning-based techniques can provide the required accuracy.
Bayesian Atlas Building with Hierarchical Priors for Subject-specific Regularization
This paper presents a novel hierarchical Bayesian model for unbiased atlas building with subject-specific regularizations of image registration.
Seeing in Extra Darkness Using a Deep-Red Flash
We propose a new flash technique for low-light imaging, using deep-red light as an illuminating source.
