Search Results for author:
Found 99 papers, 34 papers with code
Supervised Edge Attention Network for Accurate Image Instance Segmentation
In this task, many works segment instance based on a bounding box from the box head, which means the quality of the detection also affects the completeness of the mask.
GroverGPT-2: Simulating Grover's Algorithm via Chain-of-Thought Reasoning and Quantum-Native Tokenization
Our results show that GroverGPT-2 can learn and internalize quantum circuit logic through efficient processing of quantum-native tokens, providing direct evidence that classical models like LLMs can capture the structure of quantum algorithms.
Visual enhancement and 3D representation for underwater scenes: a review
Underwater visual enhancement (UVE) and underwater 3D reconstruction pose significant challenges in computer vision and AI-based tasks due to complex imaging conditions in aquatic environments.
LLGS: Unsupervised Gaussian Splatting for Image Enhancement and Reconstruction in Pure Dark Environment
Simply using enhanced images as inputs would lead to issues with multi-view consistency, and current single-view enhancement systems rely on pre-trained data, lacking scene generalization.
Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
Large language models (LLMs) like GPT-4 and LLaMA-3 utilize the powerful in-context learning (ICL) capability of Transformer architecture to learn on the fly from limited examples.
Understanding Driver Cognition and Decision-Making Behaviors in High-Risk Scenarios: A Drift Diffusion Perspective
First, a risk sensitivity model based on a multivariate Gaussian distribution is developed to characterize individual differences in risk cognition.
WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining
Currently, several recent works have utilized the segmenting anything model (SAM) to boost the segmentation performance in medical images, where most of them focus on training an adaptor for fine-tuning a large amount of pixel-wise annotated medical images following a fully supervised manner.
Can Multimodal LLMs Perform Time Series Anomaly Detection?
Starting with the univariate case (point- and range-wise anomalies), we extend our evaluation to more practical scenarios, including multivariate and irregular time series scenarios, and variate-wise anomalies.
Benchmarking LLMs for Political Science: A United Nations Perspective
Large Language Models (LLMs) have achieved significant advances in natural language processing, yet their potential for high-stake political decision-making remains largely unexplored.
Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection
Experiments on the MVTecLOCO dataset confirm the efficacy of ComGEN, achieving the best AUROC score of 91. 2%.
PersonaHOI: Effortlessly Improving Personalized Face with Human-Object Interaction Generation
We introduce PersonaHOI, a training- and tuning-free framework that fuses a general StableDiffusion model with a personalized face diffusion (PFD) model to generate identity-consistent human-object interaction (HOI) images.
Human-Object Interaction Detection
Human-Object Interaction Generation
GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching
In this work, we explore the potential of leveraging Large Language Models (LLMs) to simulate the output of a quantum Turing machine using Grover's quantum circuits, known to provide quadratic speedups over classical counterparts.
Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective
Although text-based large language models exhibit human-level writing ability and remarkable intelligence, speech language models (SLMs) still struggle to generate semantically coherent outputs.
Automated Driving with Evolution Capability: A Reinforcement Learning Method with Monotonic Performance Enhancement
Hence, the proposed HCPI-RL planner has the following features: i) Evolutionary automated driving with monotonic performance enhancement; ii) With the capability of handling scenarios with emergency; iii) With enhanced decision-making optimality.
Anti-bullying Adaptive Cruise Control: A proactive right-of-way protection approach
The current Adaptive Cruise Control (ACC) systems are vulnerable to "road bully" such as cut-ins.
MV-Adapter: Multi-view Consistent Image Generation Made Easy
To efficiently model the 3D geometric knowledge within the adapter, we introduce innovative designs that include duplicated self-attention layers and parallel attention architecture, enabling the adapter to inherit the powerful priors of the pre-trained models to model the novel 3D knowledge.
Gated Parametric Neuron for Spike-based Audio Recognition
Compared with the LIF neuron, the GPN has two distinguishing advantages: 1) it copes well with the vanishing gradients by improving the flow of gradient propagation; and, 2) it learns spatio-temporal heterogeneous neuronal parameters automatically.
Boosting 3D Object Generation through PBR Materials
By analyzing the components of PBR materials, we choose to consider albedo, roughness, metalness, and bump maps.
UNSCT-HRNet: Modeling Anatomical Uncertainty for Landmark Detection in Total Hip Arthroplasty
Total hip arthroplasty (THA) relies on accurate landmark detection from radiographic images, but unstructured data caused by irregular patient postures or occluded anatomical markers pose significant challenges for existing methods.
HG2P: Hippocampus-inspired High-reward Graph and Model-Free Q-Gradient Penalty for Path Planning and Motion Control
Goal-conditioned hierarchical reinforcement learning (HRL) decomposes complex reaching tasks into a sequence of simple subgoal-conditioned tasks, showing significant promise for addressing long-horizon planning in large-scale environments.
UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction
3D Gaussian splatting (3DGS) offers the capability to achieve real-time high quality 3D scene rendering.
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
Approximate MU is a practical method for large-scale models.
Hi-EF: Benchmarking Emotion Forecasting in Human-interaction
We propose a novel Emotion Forecasting (EF) task grounded in the theory that an individuals emotions are easily influenced by the emotions or other information conveyed during interactions with another person.
All rivers run into the sea: Unified Modality Brain-like Emotional Central Mechanism
In the field of affective computing, fully leveraging information from a variety of sensory modalities is essential for the comprehensive understanding and processing of human emotions.
Non-Robust Features are Not Always Useful in One-Class Classification
The robustness of machine learning models has been questioned by the existence of adversarial examples.
EMPL: A novel Efficient Meta Prompt Learning Framework for Few-shot Unsupervised Domain Adaptation
However, current FS-UDA methods are still suffer from two issues: 1) the data from different domains can not be effectively aligned by few-shot labeled data due to the large domain gaps, 2) it is unstable and time-consuming to generalize to new FS-UDA tasks. To address this issue, we put forward a novel Efficient Meta Prompt Learning Framework for FS-UDA.
The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention
In this work, we propose DemOgraphic FActualIty Representation (DoFaiR), a benchmark to systematically quantify the trade-off between using diversity interventions and preserving demographic factuality in T2I models.
Suppressing Uncertainties in Degradation Estimation for Blind Super-Resolution
To extract Uncertainty-based Degradation Representation from LR images, the AUDE utilizes the Self-supervised Uncertainty Contrast module with Uncertainty Suppression Loss to suppress the inherent model uncertainty of the Degradation Extractor.
D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition
The contemporary state-of-the-art of Dynamic Facial Expression Recognition (DFER) technology facilitates remarkable progress by deriving emotional mappings of facial expressions from video content, underpinned by training on voluminous datasets.
Dynamic Facial Expression Recognition
Facial Expression Recognition
FaceGPT: Self-supervised Learning to Chat about 3D Human Faces
We introduce FaceGPT, a self-supervised learning framework for Large Vision-Language Models (VLMs) to reason about 3D human faces from images and text.
VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model
In this paper, we focus on resolving the problem of image outpainting, which aims to extrapolate the surrounding parts given the center contents of an image.
OUS: Scene-Guided Dynamic Facial Expression Recognition
By analyzing the Rigid Cognitive Problem, OUS successfully understands the complex relationship between scene context and emotional expression, closely aligning with human emotional understanding in real-world scenarios.
Ranked #5 on
Dynamic Facial Expression Recognition
on FERV39k
Dynamic Facial Expression Recognition
Facial Expression Recognition
Accelerating the Evolution of Personalized Automated Lane Change through Lesson Learning
Guided by the objective of optimizing rewards within the constraints of the driving zone, this approach employs model predictive control for trajectory planning.
From Friendship Networks to Classroom Dynamics: Leveraging Neural Networks, Instrumental Variable and Genetic Algorithms for Optimal Educational Outcomes
Though the result is much more efficient (i. e. more positive average peer effect) than random classroom assignment (i. e. the current practice in most Chinese middle schools), GA policy is highly inequitable: a small number of students are predicted to experience severely negative peer effects.
MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise
Recently, large language models (LLMs) have evolved into interactive agents, proficient in planning, tool use, and task execution across a wide variety of tasks.
SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior
To tackle this problem, we propose a novel approach that enhances the capacity of 3DGS by leveraging prior from a Diffusion Model along with complementary multi-modal data.
CACA Agent: Capability Collaboration based AI Agent
As AI Agents based on Large Language Models (LLMs) have shown potential in practical applications across various fields, how to quickly deploy an AI agent and how to conveniently expand the application scenario of AI agents has become a challenge.
Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations
This is particularly true for medical image segmentation (MIS) datasets, where the processes of collection and fine-grained annotation are time-intensive and laborious.
A$^{3}$lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP
Specifically, our A$^{3}$lign-DFER method is designed with multiple modules that work together to obtain the most suitable expanded-dimensional embeddings for classification and to achieve alignment in three key aspects: affective, dynamic, and bidirectional.
Dynamic Facial Expression Recognition
Facial Expression Recognition
Neural Field Classifiers via Target Encoding and Classification Loss
We successfully propose a novel Neural Field Classifier (NFC) framework which formulates existing neural field methods as classification tasks rather than regression tasks.
HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models
In the specific, our model is constructed based on Latent Diffusion Model (LDM) and elaborately designed to absorb content and style instance as conditions of LDM.
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
Parallel Ranking of Ads and Creatives in Real-Time Advertising Systems
In this paper, we propose for the first time a novel architecture for online parallel estimation of ads and creatives ranking, as well as the corresponding offline joint optimization model.
RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment
Deep learning-based video quality assessment (deep VQA) has demonstrated significant potential in surpassing conventional metrics, with promising improvements in terms of correlation with human perception.
Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
To ensure AI safety, instruction-tuned Large Language Models (LLMs) are specifically trained to ensure alignment, which refers to making models behave in accordance with human intentions.
A comprehensive survey on deep active learning in medical image analysis
Deep learning has achieved widespread success in medical image analysis, leading to an increasing demand for large-scale expert-annotated medical image datasets.
Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models
While existing works on claim verification have shown promising results, a crucial piece of the puzzle that remains unsolved is to understand how to verify claims without relying on human-annotated data, which is expensive to create at a large scale.
Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement
Compared to image duplication and synthesis, image splicing detection is more challenging due to the lack of reference images and the typically small tampered areas.
Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout
Here, we propose a goal-conditioned HRL framework named Guided Cooperation via Model-based Rollout (GCMR), aiming to bridge inter-layer information synchronization and cooperation by exploiting forward dynamics.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
CMRxRecon: An open cardiac MRI dataset for the competition of accelerated image reconstruction
However, a limitation of CMR is its slow imaging speed, which causes patient discomfort and introduces artifacts in the images.
Fin-Fact: A Benchmark Dataset for Multimodal Financial Fact Checking and Explanation Generation
Fact-checking in financial domain is under explored, and there is a shortage of quality dataset in this domain.
Investigating Online Financial Misinformation and Its Consequences: A Computational Perspective
In conclusion, this research paper sheds light on the pervasive issue of online financial misinformation and its wide-ranging consequences.
Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning
In this work, we propose an efficient computation framework for multimodal alignment by introducing a novel visual semantic module to further improve the performance of the VL tasks.
S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields
Recently, Neural Radiance Field (NeRF) has shown great success in rendering novel-view images of a given scene by learning an implicit representation with only posed RGB images.
LOIS: Looking Out of Instance Semantics for Visual Question Answering
Visual question answering (VQA) has been intensively studied as a multimodal task that requires effort in bridging vision and language to infer answers correctly.
Free-Form Composition Networks for Egocentric Action Recognition
We evaluated our method on three popular egocentric action recognition datasets, Something-Something V2, H2O, and EPIC-KITCHENS-100, and the experimental results demonstrate the effectiveness of the proposed method for handling data scarcity problems, including long-tailed and few-shot egocentric action recognition.
Hierarchical Matching and Reasoning for Multi-Query Image Retrieval
Afterwards, the VR module is developed to excavate the potential semantic correlations among multiple region-query pairs, which further explores the high-level reasoning similarity.
Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation
Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student.
ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about
Large language models have gained considerable interest for their impressive performance on various tasks.
Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment planning.
EndoBoost: a plug-and-play module for false positive suppression during computer-aided polyp detection in real-world colonoscopy (with dataset)
In addition, the released dataset can be used to perform 'stress' tests on established detection systems and encourages further research toward robust and reliable computer-aided endoscopic image analysis.
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
MIC significantly improves the state-of-the-art performance across the different recognition tasks for synthetic-to-real, day-to-nighttime, and clear-to-adverse-weather UDA.
Combating Health Misinformation in Social Media: Characterization, Detection, Intervention, and Open Issues
Because of the uniqueness and importance of combating health misinformation in social media, we conduct this survey to further facilitate interdisciplinary research on this problem.
The Extreme Cardiac MRI Analysis Challenge under Respiratory Motion (CMRxMotion)
The quality of cardiac magnetic resonance (CMR) imaging is susceptible to respiratory motion artifacts.
CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval
We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting.
SoMoFormer: Social-Aware Motion Transformer for Multi-Person Motion Prediction
Most prior methods only involve learning local pose dynamics for individual motion (without global body trajectory) and also struggle to capture complex interaction dependencies for social interactions.
Positively transitioned sentiment dialogue corpus for developing emotion-affective open-domain chatbots
In this paper, we describe a data enhancement method for developing Emily, an emotion-affective open-domain chatbot.
Boosting Video-Text Retrieval with Explicit High-Level Semantics
Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video).
Temporal Saliency Query Network for Efficient Video Recognition
For each category, the common pattern of it is employed as a query and the most salient frames are responded to it.
Ranked #5 on
Action Recognition
on ActivityNet
NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition
On the video level, a temporal attention module is learned under dual video-level supervisions on both the salient and the non-salient representations.
Ranked #4 on
Action Recognition
on ActivityNet
Can multi-label classification networks know what they don't know?
Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.
Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
In this paper, we describe approaches for developing Emily, an emotion-affective open-domain chatbot.
Efficient and Systematic Partitioning of Large and Deep Neural Networks for Parallelization
We propose the Flex-Edge Recursive Graph and the Double Recursive Algorithm, successfully limiting our parallelization strategy generation to a linear complexity with a good quality of parallelization strategy.
Freeing Hybrid Distributed AI Training Configuration
Hybrid Parallelism (HP), which applies different parallel strategies on different parts of DNNs, is more efficient but requires advanced configurations.
CONet: Channel Optimization for Convolutional Neural Networks
To solve this, we introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimizes channel sizes across network layers for a given CNN.
Step-Wise Hierarchical Alignment Network for Image-Text Matching
Image-text matching plays a central role in bridging the semantic gap between vision and language.
Can multi-label classification networks know what they don’t know?
Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.
Robo-Advising: Enhancing Investment with Inverse Optimization and Deep Reinforcement Learning
Machine Learning (ML) has been embraced as a powerful tool by the financial industry, with notable applications spreading in various domains including investment management.
Hierarchical Cost Analysis for Distributed DL
In order to formalize the behaviors of the HP in distributed DL and quantitatively evaluate the cost caused by HP, we are studying Bridging DL composed by a double-level execution model associated with a symbolic cost model.
ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception
Level-5 driving automation requires a robust visual perception system that can parse input images under any condition.
Strictly Decentralized Adaptive Estimation of External Fields using Reproducing Kernels
Approximations of the evolution of the ideal local estimate $\hat{g}^i_t$ of agent $i$ is constructed solely using observations made by agent $i$ on a fine time scale.
Prediction of 3D Cardiovascular hemodynamics before and after coronary artery bypass surgery via deep learning
The clinical treatment planning of coronary heart disease requires hemodynamic parameters to provide proper guidance.
Energy-based Out-of-distribution Detection for Multi-label Classification
Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.
Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning
Query reformulation aims to alter noisy or ambiguous text sequences into coherent ones closer to natural language questions.
Context-Aware Graph Convolution Network for Target Re-identification
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks.
Frame Aggregation and Multi-Modal Fusion Framework for Video-Based Person Recognition
To tackle the challenges above, we propose a novel Frame Aggregation and Multi-Modal Fusion (FAMF) framework for video-based person recognition, which aggregates face features and incorporates them with multi-modal information to identify persons in videos.
Learning Risk Preferences from Investment Portfolios Using Inverse Optimization
Our approach allows the learner to continuously estimate real-time risk preferences using concurrent observed portfolios and market price data.
UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results
The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration.
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains.
Ranked #15 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
Consensus-Aware Visual-Semantic Embedding for Image-Text Matching
In this paper, we propose a Consensus-aware Visual-Semantic Embedding (CVSE) model to incorporate the consensus information, namely the commonsense knowledge shared between both modalities, into image-text matching.
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
Large scale continuous-time mean-variance portfolio allocation via reinforcement learning
We propose to solve large scale Markowitz mean-variance (MV) portfolio allocation problem using reinforcement learning (RL).
Continuous-Time Mean-Variance Portfolio Selection: A Reinforcement Learning Framework
We approach the continuous-time mean-variance (MV) portfolio selection with reinforcement learning (RL).
Saliency-Guided Attention Network for Image-Sentence Matching
Concretely, the saliency detector provides the visual saliency information as the guidance for the two attention modules.
Enhancing Topic Modeling for Short Texts with Auxiliary Word Embeddings
Recent studies show that the Dirichlet Multinomial Mixture (DMM) model is effective for topic inference over short texts by assuming that each piece of short text is generated by a single topic.
Exploration versus exploitation in reinforcement learning: a stochastic control approach
We carry out a complete analysis of the problem in the linear--quadratic (LQ) setting and deduce that the optimal feedback control distribution for balancing exploitation and exploration is Gaussian.
Parameter-Free Spatial Attention Network for Person Re-Identification
We propose a novel architecture for Person Re-Identification, based on a novel parameter-free spatial attention layer introducing spatial relations among the feature map activations back to the model.
Ranked #20 on
Person Re-Identification
on DukeMTMC-reID
Multi-task Sparse Learning with Beta Process Prior for Action Recognition
In this paper, we formulate human action recognition as a novel Multi-Task Sparse Learning(MTSL) framework which aims to construct a test sample with multiple features from as few bases as possible.
