Search Results for author:
Found 323 papers, 125 papers with code
Enabling Deep Residual Networks for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) has attracted extensive research attention due to its great flexibility of exploiting large-scale image-level annotation for detector training.
zydhjh4593@SMM4H’22: A Generic Pre-trained BERT-based Framework for Social Media Health Text Classification
This paper describes our proposed framework for the 10 text classification tasks of Task 1a, 2a, 2b, 3a, 4, 5, 6, 7, 8, and 9, in the Social Media Mining for Health (SMM4H) 2022.
AccidentBlip2: Accident Detection With Multi-View MotionBlip2
We also extend our approach to a multi-vehicle cooperative system by deploying Motion Qformer on each vehicle and simultaneously inputting the inference-generated query into the MLP for autoregressive inference.
Causal Deconfounding via Confounder Disentanglement for Dual-Target Cross-Domain Recommendation
As a result, dual-target CDR has to meet two challenges: (1) how to effectively decouple observed confounders, including single-domain confounders and cross-domain confounders, and (2) how to preserve the positive effects of observed confounders on predicted interactions, while eliminating their negative effects on capturing comprehensive user preferences.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
RoT: Enhancing Large Language Models with Reflection on Search Trees
It uses a strong LLM to summarize guidelines from previous tree search experiences to enhance the ability of a weak LLM.
Task-Aware Encoder Control for Deep Video Compression
Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task, mandating a dedicated decoder per task.
Two-Phase Multi-Dose-Level PET Image Reconstruction with Dose Level Awareness
In this paper, to reconstruct high-quality SPET images from multi-dose-level LPET images, we design a novel two-phase multi-dose-level PET reconstruction algorithm with dose level awareness, containing a pre-training phase and a SPET prediction phase.
Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding
This paper introduces H-SAM: a prompt-free adaptation of SAM tailored for efficient fine-tuning of medical images via a two-stage hierarchical decoding procedure.
EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting
Precise camera tracking, high-fidelity 3D tissue reconstruction, and real-time online visualization are critical for intrabody medical imaging devices such as endoscopes and capsule robots.
Protein Conformation Generation via Force-Guided SE(3) Diffusion Models
The conformational landscape of proteins is crucial to understanding their functionality in complex biological processes.
Super-High-Fidelity Image Compression via Hierarchical-ROI and Adaptive Quantization
MSE-based models aim to improve objective metrics while generative models are leveraged to improve visual quality measured by subjective metrics.
Noise Dimension of GAN: An Image Compression Perspective
This trade-off depicts the best divergence we can achieve when noise is limited.
Content-aware Masked Image Modeling Transformer for Stereo Image Compression
Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations.
GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
In response, we propose a groundbreaking paradigm of image representation and compression by 2D Gaussian Splatting, named GaussianImage.
Few-shot Learning on Heterogeneous Graphs: Challenges, Progress, and Prospects
In this paper, we provide a comprehensive review of existing FLHG methods, covering challenges, research progress, and future prospects.
Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution
Harnessing the potential of leveraging this a priori knowledge in the context of image super-resolution presents a compelling avenue.
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
Dcl-Net: Dual Contrastive Learning Network for Semi-Supervised Multi-Organ Segmentation
Semi-supervised learning is a sound measure to relieve the strict demand of abundant annotated datasets, especially for challenging multi-organ segmentation .
Dose Prediction Driven Radiotherapy Paramters Regression via Intra- and Inter-Relation Modeling
Deep learning has facilitated the automation of radiotherapy by predicting accurate dose distribution maps.
CAMixerSR: Only Details Need More "Attention"
To satisfy the rapidly increasing demands on the large image (2K-8K) super-resolution (SR), prevailing methods follow two independent tracks: 1) accelerate existing networks by content-aware routing, and 2) design better super-resolution networks via token mixer refining.
Boosting Neural Representations for Videos with a Conditional Decoder
Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks.
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.
A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis
To bridge the distribution gap between user input behavior and model training datasets, we first construct a novel Coarse-Fine Granularity Prompts dataset (CFP) and propose a novel User-Friendly Fine-Grained Text Generation framework (UF-FGTG) for automated prompt optimization.
Consistency Models Improve Diffusion Inverse Solvers
In addition, we propose a new family of DIS using pure CM.
Adaptive Hypergraph Network for Trust Prediction
In this paper, we propose an Adaptive Hypergraph Network for Trust Prediction (AHNTP), a novel approach that improves trust prediction accuracy by using higher-order correlations.
A Lightweight Inception Boosted U-Net Neural Network for Routability Prediction
As the modern CPU, GPU, and NPU chip design complexity and transistor counts keep increasing, and with the relentless shrinking of semiconductor technology nodes to nearly 1 nanometer, the placement and routing have gradually become the two most pivotal processes in modern very-large-scale-integrated (VLSI) circuit back-end design.
Triplet-constraint Transformer with Multi-scale Refinement for Dose Prediction in Radiotherapy
Radiotherapy is a primary treatment for cancers with the aim of applying sufficient radiation dose to the planning target volume (PTV) while minimizing dose hazards to the organs at risk (OARs).
Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies
The advent of large language models (LLMs) such as ChatGPT, PaLM, and GPT-4 has catalyzed remarkable advances in natural language processing, demonstrating human-like language fluency and reasoning capacities.
DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models
In this paper, for the first time, we systematically explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works.
Image2Points:A 3D Point-based Context Clusters GAN for High-Quality PET Image Reconstruction
To obtain high-quality Positron emission tomography (PET) images while minimizing radiation exposure, numerous methods have been proposed to reconstruct standard-dose PET (SPET) images from the corresponding low-dose PET (LPET) images.
Deep Learning with Information Fusion and Model Interpretation for Health Monitoring of Fetus based on Long-term Prenatal Electronic Fetal Heart Rate Monitoring Data
This kind of continuous monitoring, in contrast to the short-term one, collects an extended period of fetal heart data.
GMC-IQA: Exploiting Global-correlation and Mean-opinion Consistency for No-reference Image Quality Assessment
Due to the subjective nature of image quality assessment (IQA), assessing which image has better quality among a sequence of images is more reliable than assigning an absolute mean opinion score for an image.
SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) the inherent complexity of 3D scenes due to the diverse object configurations, their rich attributes, and intricate relationships; (ii) the scarcity of paired 3D vision-language data to support grounded learning; and (iii) the absence of a unified learning framework to distill knowledge from grounded 3D data.
Idempotence and Perceptual Image Compression
However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec.
LLM-Guided Multi-View Hypergraph Learning for Human-Centric Explainable Recommendation
As personalized recommendation systems become vital in the age of information overload, traditional methods relying solely on historical user interactions often fail to fully capture the multifaceted nature of human interests.
A Deep Learning Representation of Spatial Interaction Model for Resilient Spatial Planning of Community Business Clusters
To address the limitation, we propose a SIM-GAT model to predict spatiotemporal visitation flows between community business clusters and their trade areas.
TeleChat Technical Report
Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe.
Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphs
To address this challenging problem, we propose a novel Causal OOD Heterogeneous graph Few-shot learning model, namely COHF.
Energy based diffusion generator for efficient sampling of Boltzmann distributions
We introduce a novel sampler called the energy based diffusion generator for generating samples from arbitrary target distributions.
Set Prediction Guided by Semantic Concepts for Diverse Video Captioning
Each caption in the set is attached to a concept combination indicating the primary semantic content of the caption and facilitating element alignment in set prediction.
DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution
Specifically, we propose a plug-in reparameterized dynamic unit (RDU) to promote the performance and inference cost trade-off.
Object Attribute Matters in Visual Question Answering
In this paper, we propose a novel VQA approach from the perspective of utilizing object attribute, aiming to achieve better object-level visual-language alignment and multimodal scene understanding.
Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning
In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth.
CogAgent: A Visual Language Model for GUI Agents
People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e. g., computer or smartphone screens.
Ranked #14 on
Visual Question Answering
on MM-Vet
Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models
We propose Causal Context Generation, Causal-CoG, which is a prompting strategy that engages contextual information to enhance precise VQA during inference.
Large Language Models for Intent-Driven Session Recommendations
Intent-aware session recommendation (ISR) is pivotal in discerning user intents within sessions for precise predictions.
Unified learning-based lossy and lossless JPEG recompression
Most image compression algorithms only consider uncompressed original image, while ignoring a large number of already existing JPEG images.
An Embodied Generalist Agent in 3D World
Leveraging massive knowledge and learning schemes from large language models (LLMs), recent machine learning models show notable successes in building generalist agents that exhibit the capability of general-purpose task solving in diverse domains, including natural language processing, computer vision, and robotics.
ML-Bench: Evaluating Large Language Models for Code Generation in Repository-Level Machine Learning Tasks
While Large Language Models (LLMs) have demonstrated proficiency in code generation benchmarks, translating these results into practical development scenarios - where leveraging existing repository-level libraries is the norm - remains challenging.
Explainable History Distillation by Marked Temporal Point Process
To efficiently solve \acrshort{ehd}, we rewrite the task into a \gls{01ip} and directly estimate the solution to the program by a model called \acrfull{model}.
PepLand: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids
In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation.
High-performance Power Allocation Strategies for Active IRS-aided Wireless Network
Due to its slow linear convergence from iterative GA, the proposed ESMPI-GA is high-complexity.
Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps
We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Encoder Representations from transFormers, to leverage priors in SD maps for the lane-topology prediction task.
CogVLM: Visual Expert for Pretrained Language Models
We introduce CogVLM, a powerful open-source visual language foundation model.
Ranked #4 on
Visual Question Answering (VQA)
on InfiMM-Eval
Diffusion-based Radiotherapy Dose Prediction Guided by Inter-slice Aware Structure Encoding
In the forward process, DiffDose transforms dose distribution maps into pure Gaussian noise by gradually adding small noise and a noise predictor is simultaneously trained to estimate the noise added at each timestep.
Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context
Unsupervised salient object detection aims to detect salient objects without using supervision signals eliminating the tedious task of manually labeling salient objects.
3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers
In this paper, we extend the 2D TransUNet architecture to a 3D network by building upon the state-of-the-art nnU-Net architecture, and fully exploring Transformers' potential in both the encoder and decoder design.
Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inference
Asynchronous time series, also known as temporal event sequences, are the basis of many applications throughout different industries.
Gene-induced Multimodal Pre-training for Image-omic Classification
Histology analysis of the tumor micro-environment integrated with genomic assays is the gold standard for most cancers in modern medicine.
Bandwidth-efficient Inference for Neural Image Compression
With neural networks growing deeper and feature maps growing larger, limited communication bandwidth with external memory (or DRAM) and power constraints become a bottleneck in implementing network inference on mobile and edge devices.
Enhancing Psychological Counseling with Large Language Model: A Multifaceted Decision-Support System for Non-Professionals
In the contemporary landscape of social media, an alarming number of users express negative emotions, some of which manifest as strong suicidal intentions.
Mind vs. Mouth: On Measuring Re-judge Inconsistency of Social Bias in Large Language Models
We propose that this re-judge inconsistency can be similar to the inconsistency between human's unaware implicit social bias and their aware explicit social bias.
A Unified Framework for 3D Point Cloud Visual Grounding
This elaborate design enables 3DRefTR to achieve both well-performing 3DRES and 3DREC capacities with only a 6% additional latency compared to the original 3DREC model.
Enhancing Recommender Systems with Large Language Model Reasoning Graphs
In this paper, we propose a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs.
Leveraging Large Language Models for Pre-trained Recommender Systems
In this paper, we propose RecSysLLM, a novel pre-trained recommendation model based on LLMs.
Polymerized Feature-based Domain Adaptation for Cervical Cancer Dose Map Prediction
Recently, deep learning (DL) has automated and accelerated the clinical radiation therapy (RT) planning significantly by predicting accurate dose maps.
Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
To obtain high-quality positron emission tomography (PET) scans while reducing radiation exposure to the human body, various approaches have been proposed to reconstruct standard-dose PET (SPET) images from low-dose PET (LPET) images.
Conditional Perceptual Quality Preserving Image Compression
We propose conditional perceptual quality, an extension of the perceptual quality defined in \citet{blau2018perception}, by conditioning it on user defined information.
Cross-heterogeneity Graph Few-shot Learning
In recent years, heterogeneous graph few-shot learning has been proposed to address the label sparsity issue in heterogeneous graphs (HGs), which contain various types of nodes and edges.
TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms
Specifically, the TriDo-Former consists of two cascaded networks, i. e., a sinogram enhancement transformer (SE-Former) for denoising the input LPET sinograms and a spatial-spectral reconstruction transformer (SSR-Former) for reconstructing SPET images from the denoised sinograms.
Kairos: Practical Intrusion Detection and Investigation using Whole-system Provenance
Sifting through their design documents, we identify four common dimensions that drive the development of provenance-based intrusion detection systems (PIDSes): scope (can PIDSes detect modern attacks that infiltrate across application boundaries?
Color Image Recovery Using Generalized Matrix Completion over Higher-Order Finite Dimensional Algebra
To improve the accuracy of color image completion with missing entries, we present a recovery method based on generalized higher-order scalars.
Continual Learning in Predictive Autoscaling
In order to surmount this challenge and effectively integrate new sample distribution, we propose a density-based sample selection strategy that utilizes kernel density estimation to calculate sample density as a reference to compute sample weight, and employs weight sampling to construct a new memory set.
Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation
In DIDA-CDR, we first propose an interpolative data augmentation approach to generating both relevant and diverse augmented user representations to augment sparser domain and explore potential user preferences.
AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception
Driver distraction has become a significant cause of severe traffic accidents over the past decade.
SL: Stable Learning in Source-Free Domain Adaption for Medical Image Segmentation
In this challenge defined as Source-Free UDA, the previous UDA medical methods are limited.
DiffDP: Radiotherapy Dose Prediction via a Diffusion Model
To alleviate this limitation, we innovatively introduce a diffusion-based dose prediction (DiffDP) model for predicting the radiotherapy dose distribution of cancer patients.
EasyTPP: Towards Open Benchmarking Temporal Point Processes
In this paper, we present EasyTPP, the first central repository of research assets (e. g., data, models, evaluation programs, documentations) in the area of event sequence modeling.
Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP).
Copy Is All You Need
The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary.
SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistency
Extensive studies have shown that deep learning models are vulnerable to adversarial and natural noises, yet little is known about model robustness on noises caused by different system implementations.
Improving the Transferability of Time Series Forecasting with Decomposition Adaptation
However, in time series forecasting, it is difficult to obtain enough data, which limits the performance of neural forecasting models.
A Unified Framework for Online Data-Driven Predictive Control with Robust Safety Guarantees
Despite great successes, model predictive control (MPC) relies on an accurate dynamical model and requires high onboard computational power, impeding its wider adoption in engineering systems, especially for nonlinear real-time systems with limited computation power.
Extended Neighboring Extremal Optimal Control with State and Preview Perturbations
In this work, an extended NE (ENE) framework is developed to systematically adapt the nominal control to both state and preview perturbations.
Asymptotic Performance Analysis of Large-Scale Active IRS-Aided Wireless Network
Numerical simulation results show that a 3-bit discrete phase shifter is required to achieve a trivial performance loss for a large-scale active IRS.
MedNgage: A Dataset for Understanding Engagement in Patient-Nurse Conversations
In this paper, we present a novel dataset (MedNgage), which consists of patient-nurse conversations about cancer symptom management.
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
To address the DoT problem, we propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution.
PandaGPT: One Model To Instruction-Follow Them All
To do so, PandaGPT combines the multimodal encoders from ImageBind and the large language models from Vicuna.
Joint Uplink and Downlink Resource Allocation Towards Energy-efficient Transmission for URLLC
With the proposed packet delivery mechanism, we jointly optimize bandwidth allocation and power control of uplink and downlink, antenna configuration, and subchannel assignment to minimize the average total power under the constraint of URLLC transmission requirements.
Privacy-preserving Adversarial Facial Features
In this paper, we propose an adversarial features-based face privacy protection (AdvFace) approach to generate privacy-preserving adversarial features, which can disrupt the mapping from adversarial features to facial images to defend against reconstruction attacks.
Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
In this tutorial, we aim to provide a holistic lens on emerging UQ methods for ML models with a particular focus on neural networks and the applications of these UQ methods in tackling engineering design as well as prognostics and health management problems.
Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation
In semi-supervised medical image segmentation, there exist empirical mismatch problems between labeled and unlabeled data distribution.
Image Segmentation
Semi-supervised Medical Image Segmentation
+1
FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model.
SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More
We can even outperform task-specific network models and achieve state-of-the-art performance in the task we tested: camouflaged object detection, shadow detection.
Experience-Based Evolutionary Algorithms for Expensive Optimization
Our experimental results on expensive multi-objective and constrained optimization problems demonstrate that experiences gained from related tasks are beneficial for the saving of evaluation budgets on the target problem.
Efficient Decision-based Black-box Patch Attacks on Video Recognition
First, STDE introduces target videos as patch textures and only adds patches on keyframes that are adaptively selected by temporal difference.
VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection
In autonomous driving, Vehicle-Infrastructure Cooperative 3D Object Detection (VIC3D) makes use of multi-view cameras from both vehicles and traffic infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.
SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation
For semantic segmentation in urban scene understanding, RGB cameras alone often fail to capture a clear holistic topology in challenging lighting conditions.
Ranked #8 on
Thermal Image Segmentation
on PST900
Calibration-free BEV Representation for Infrastructure Perception
Effective BEV object detection on infrastructure can greatly improve traffic scenes understanding and vehicle-toinfrastructure (V2I) cooperative perception.
Ranked #5 on
3D Object Detection
on DAIR-V2X-I
DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation
In recommendation scenarios, there are two long-standing challenges, i. e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks.
Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos.
IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning
We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks, including deep neural network (DNN) regression and neural operator learning (DeepONet).
Exploring Invariant Representation for Visible-Infrared Person Re-Identification
Cross-spectral person re-identification, which aims to associate identities to pedestrians across different spectra, faces a main challenge of the modality discrepancy.
A Counterfactual Collaborative Session-based Recommender System
Next, COCO-SBRS adopts counterfactual inference to recommend items based on the outputs of the pre-trained recommendation model considering the causalities to alleviate the data sparsity problem.
Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle
In this paper, we try to solve this problem by introducing a principled and unified framework based on Information Bottleneck (IB) theory, which further guides us to an automatic pruning approach.
Rethinking Safe Semi-supervised Learning: Transferring the Open-set Problem to A Close-set One
Conventional semi-supervised learning (SSL) lies in the close-set assumption that the labeled and unlabeled sets contain data with the same seen classes, called in-distribution (ID) data.
Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning
The second key element is that we design class balanced adaptive thresholds via considering the empirical distribution of all training data in local clients, to encourage a balanced training process.
MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery
Our strategy encourages unlabeled images to learn organ semantics in relative locations from the labeled images (cross-branch) and enhances the learning ability for small organs (within-branch).
GeneFormer: Learned Gene Compression using Transformer-based Context Modeling
Then, we propose fixed-length parallel grouping to accelerate the decoding speed of our autoregressive model.
SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud
However, these UDA solutions just yield unsatisfactory 3D detection results when there is a severe domain shift, e. g., from Waymo (64-beam) to nuScenes (32-beam).
A K-variate Time Series Is Worth K Words: Evolution of the Vanilla Transformer Architecture for Long-term Multivariate Time Series Forecasting
In this study, we point out that the current tokenization strategy in MTSF Transformer architectures ignores the token uniformity inductive bias of Transformers.
Generalizing Math Word Problem Solvers via Solution Diversification
In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator.
Meta Architecture for Point Cloud Analysis
However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field.
Ranked #2 on
3D Semantic Segmentation
on OpenTrench3D
ECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compression
For octree-based point cloud compression, previous works show that the information of ancestor nodes and sibling nodes are equally important for predicting current node.
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters
In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment.
FedVMR: A New Federated Learning method for Video Moment Retrieval
As the first that is explored in VMR field, the new task is defined as video moment retrieval with distributed data.
DPCNet: Dual Path Multi-Excitation Collaborative Network for Facial Expression Representation Learning in Videos
To obtain consistent prediction probabilities from the dual path, we further propose a dual path regularization loss, aiming to minimize the divergence between the distributions of two-path embeddings.
Ranked #13 on
Dynamic Facial Expression Recognition
on DFEW
Dynamic Facial Expression Recognition
Representation Learning
Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers
A common setup for a robotic agent is to have two different computers simultaneously: a resource-limited local computer tethered to the robot and a powerful remote computer connected wirelessly.
Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem
In this paper, we redesign the patch-based triplet loss in MDE to alleviate the ubiquitous edge-fattening issue.
Ranked #1 on
Unsupervised Monocular Depth Estimation
on Kitti Raw
Correcting the Sub-optimal Bit Allocation
In this paper, we investigate the problem of bit allocation in Neural Video Compression (NVC).
Spatial Moment Pooling Improves Neural Image Assessment
In recent years, there has been widespread attention drawn to convolutional neural network (CNN) based blind image quality assessment (IQA).
Multi-Sample Training for Neural Image Compression
This paper considers the problem of lossy neural image compression (NIC).
Multi-scale Attention Network for Single Image Super-Resolution
ConvNets can compete with transformers in high-level tasks by exploiting larger receptive fields.
HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification
A parallel hierarchy of local and global feature blocks is designed to efficiently extract local features and global representations at various semantic scales, with the flexibility to model at different scales and linear computational complexity relevant to image size.
Bit Allocation using Optimization
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC).
Flexible Neural Image Compression via Code Editing
Neural image compression (NIC) has outperformed traditional image codecs in rate-distortion (R-D) performance.
S$^3$R: Self-supervised Spectral Regression for Hyperspectral Histopathology Image Classification
More concretely, we propose to learn a set of linear coefficients that can be used to represent one band by the remaining bands via masking out these bands.
RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN
Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models.
Trustworthy Recommender Systems
However, researchers lack a systematic overview and discussion of the literature in this novel and fast developing field of TRSs.
Stochastic MPC with Dual Control for Autonomous Driving with Multi-Modal Interaction-Aware Predictions
The proposed approach is demonstrated on a longitudinal control example, with uncertainties in predictions of the autonomous and surrounding vehicles.
Effidit: Your AI Writing Assistant
In Effidit, we significantly expand the capacities of a writing assistant by providing functions in five categories: text completion, error checking, text polishing, keywords to sentences (K2S), and cloud input methods (cloud IME).
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions
Advances in perception for self-driving cars have accelerated in recent years due to the availability of large-scale datasets, typically collected at specific locations and under nice weather conditions.
Evaluating the Practicality of Learned Image Compression
On CPU, the latency of our implementation is comparable with JPEG XL.
Beyond CNNs: Exploiting Further Inherent Symmetries in Medical Image Segmentation
Automatic tumor or lesion segmentation is a crucial step in medical image analysis for computer-aided diagnosis.
Weakly Supervised Video Salient Object Detection via Point Supervision
Several works attempt to use scribble annotations to mitigate this problem, but point supervision as a more labor-saving annotation method (even the most labor-saving method among manual annotation methods for dense prediction), has not been explored.
Few-Shot Semantic Relation Prediction across Heterogeneous Graphs
In real-world scenarios, new semantic relations constantly emerge and they typically appear with only a few labeled data.
SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
Multi-agent systems with CBF-based controllers -- collision avoidance and liveness from instability
Monte Carlo simulations show that decentralized, host-only control policies and CCS lack liveness while the PCCA policy performs as well as the Centralized.
Unsupervised Domain Adaptation through Shape Modeling for Medical Image Segmentation
Previous methods proposed Variational Autoencoder (VAE) based models to learn the distribution of shape for a particular organ and used it to automatically evaluate the quality of a segmentation prediction by fitting it into the learned shape distribution.
Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera
We propose Neural-DynamicReconstruction (NDR), a template-free method to recover high-fidelity geometry and motions of a dynamic scene from a monocular RGB-D camera.
Review Neural Networks about Image Transformation Based on IGC Learning Framework with Annotated Information
From the perspective of this framework, we review those subtasks and give a unified interpretation of various scenarios.
Automatic Prosody Annotation with Pre-Trained Text-Speech Model
Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability.
PO-ELIC: Perception-Oriented Efficient Learned Image Coding
In the past years, learned image compression (LIC) has achieved remarkable performance.
Sequential/Session-based Recommendations: Challenges, Approaches, Applications and Opportunities
In recent years, sequential recommender systems (SRSs) and session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs to capture users' short-term but dynamic preferences for enabling more timely and accurate recommendations.
A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting
In this paper, based on the maximal information coefficient, we present two elaborate spatiotemporal representations, spatial correlation information (SCorr) and temporal correlation information (TCorr).
Ranked #1 on
Traffic Prediction
on HZME(outflow)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Effectively Using Long and Short Sessions for Multi-Session-based Recommendations
The RNN often used in previous work is not suitable to process short sessions, because RNN only focuses on the sequential relationship, which we find is not the only relationship between items in short sessions.
Language Models Can See: Plugging Visual Controls in Text Generation
MAGIC is a flexible framework and is theoretically compatible with any text generation tasks that incorporate image grounding.
Edge-enhanced Feature Distillation Network for Efficient Super-Resolution
With the recently massive development in convolution neural networks, numerous lightweight CNN-based image super-resolution methods have been proposed for practical deployments on edge devices.
Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks
Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost.
Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain
JPEG is a popular image compression method widely used by individuals, data center, cloud storage and network filesystems.
Adaptive Frequency Learning in Two-branch Face Forgery Detection
Face forgery has attracted increasing attention in recent applications of computer vision.
Weakly-Supervised Salient Object Detection Using Point Supervision
Then we develop a transformer-based point-supervised saliency detection model to produce the first round of saliency maps.
ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders.
Ranked #1 on
Image Compression
on kodak
ContrastMask: Contrastive Learning to Segment Every Thing
In this framework, annotated masks of seen categories and pseudo masks of unseen categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa.
FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos
Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos.
Multi-View Fusion Transformer for Sensor-Based Human Activity Recognition
In this paper, to extract a better feature for advancing the performance, we propose a novel method, namely multi-view fusion transformer (MVFT) along with a novel attention mechanism.
Post-Training Quantization for Cross-Platform Learned Image Compression
It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications.
A Contrastive Framework for Neural Text Generation
Text generation is of great importance to many natural language processing applications.
A Survey on Retrieval-Augmented Text Generation
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community.
Approximation of Images via Generalized Higher Order Singular Value Decomposition over Finite-dimensional Commutative Semisimple Algebra
Higher order singular value decomposition (HOSVD) extends the SVD and can approximate higher order data using sums of a few rank-one components.
Protum: A New Method For Prompt Tuning Based on "[MASK]"
In response to the above issue, we propose a new \textbf{Pro}mpt \textbf{Tu}ning based on "[\textbf{M}ASK]" (\textbf{Protum}) method in this paper, which constructs a classification task through the information carried by the hidden layer of "[MASK]" tokens and then predicts the labels directly rather than the answer tokens.
External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation with Limited Data
The spleen is one of the most commonly injured solid organs in blunt abdominal trauma.
Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation
In the second stage, we design a mesh refinement transformer (MRT) to respectively refine each coarse reconstruction result via a self-attention mechanism.
Ranked #64 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
Intriguing Findings of Frequency Selection for Image Deblurring
Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image.
Ranked #2 on
Deblurring
on RealBlur-R
Training Neural Networks for Solving 1-D Optimal Piecewise Linear Approximation
Our main contributions are that we propose the theorems to characterize the optimal solution of the PWLA problem and present the LNN method for solving it.
Exploring Dense Retrieval for Dialogue Response Selection
In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model.
WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification
Our proposed method can be easily applied to an existing convolutional neural network to improve mammographic image classification performance.
Ranked #1 on
Suspicous (BIRADS 4,5)-no suspicous (BIRADS 1,2,3) per image classification
on InBreast
Image Classification
Suspicous (BIRADS 4,5)-no suspicous (BIRADS 1,2,3) per image classification
HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning
Learned image compression is making good progress in recent years.
Post-Training Quantization Is All You Need to Perform Cross-Platform Learned Image Compression
It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications.
Fixed Neural Network Steganography: Train the images, not the network
Recent attempts at image steganography make use of advances in deep learning to train an encoder-decoder network pair to hide and retrieve secret messages in images.
Transductive Learning for Unsupervised Text Style Transfer
The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.
MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
Apply the trained FEM to acquire the novel data's features and recognize them.
OMPQ: Orthogonal Mixed Precision Quantization
Instead of solving a problem of the original integer programming, we propose to optimize a proxy metric, the concept of network orthogonality, which is highly correlated with the loss of the integer programming but also easy to optimize with linear programming.
Stylistic Retrieval-based Dialogue System with Unparallel Training Data
The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction.
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques
Thus, we propose RobustART, the first comprehensive Robustness investigation benchmark on ImageNet regarding ARchitecture design (49 human-designed off-the-shelf architectures and 1200+ networks from neural architecture search) and Training techniques (10+ techniques, e. g., data augmentation) towards diverse noises (adversarial, natural, and system noises).
MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers
Over the last few years, there are a growing number of datasets and deep learning-based methods proposed for effectively solving MWPs.
Ranked #8 on
Math Word Problem Solving
on Math23K
Real World Robustness from Systematic Noise
Systematic error, which is not determined by chance, often refers to the inaccuracy (involving either the observation or measurement process) inherent to a system.
ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding
%To facilitate the research on ASR-robust general language understanding, In this paper, we propose ASR-GLUE benchmark, a new collection of 6 different NLU tasks for evaluating the performance of models under ASR error across 3 different levels of background noise and 6 speakers with various voice characteristics.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A Unified Framework for Cross-Domain and Cross-System Recommendations
Moreover, to avoid negative transfer, we further propose a Personalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i. e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively.
Next-item Recommendations in Short Sessions
The obtained similar sessions are then utilized to complement and optimize the preference representation learned from the current short session by the local module for more accurate next-item recommendations in this short session.
BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
Maintaining consistent personas is essential for dialogue agents.
The Medical Segmentation Decathlon
Segmentation is so far the most widely investigated medical image processing task, but the various segmentation challenges have typically been organized in isolation, such that algorithm development was driven by the need to tackle a single specific clinical problem.
You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
Motivated by the necessity of efficient inference across various constraints on BERT, we propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere.
Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semi-supervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier.
Neural Machine Translation with Monolingual Translation Memory
Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal.
Optimal Estimator Design and Properties Analysis for Interconnected Systems with Asymmetric Information Structure
We found that there exists a critical probability such that the EEC is bounded if the delay probability is below the critical probability.
Graph Learning based Recommender Systems: A Review
Recent years have witnessed the fast development of the emerging topic of Graph Learning based Recommender Systems (GLRS).
Deep Learning based Multi-modal Computing with Feature Disentanglement for MRI Image Synthesis
To take full advantage of the complementary information provided by different modalities, multi-modal MRI sequences are utilized as input.
Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack
We argue this is due to the lack of rich information in the probability prediction and the overfitting caused by hard labels.
ISTR: End-to-End Instance Segmentation with Transformers
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #21 on
Instance Segmentation
on COCO test-dev
Distributed Eco-Driving Algorithm of Vehicle Platoon Using Traffic Light and Road Slope Information
This paper investigates the problem of ecological driving (eco-driving) of vehicle platoons.
Sketch and Customize: A Counterfactual Story Generator
In the sketch stage, a skeleton is extracted by removing words which are conflict to the counterfactual condition, from the original ending.
Checkerboard Context Model for Efficient Learned Image Compression
To the best of our knowledge, this is the first exploration on parallelization-friendly spatial context model for learned image compression.
Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection
Self-driving cars must detect other vehicles and pedestrians in 3D to plan safe routes and avoid collisions.
Distilling a Powerful Student Model via Online Knowledge Distillation
Besides, a self-distillation module is adopted to convert the feature map of deeper layers into a shallower one.
SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation
Hyperspectral imaging (HSI) unlocks the huge potential to a wide variety of applications relied on high-precision pathology image segmentation, such as computational pathology and precision medicine.
Cross-Domain Recommendation: Challenges, Progress, and Prospects
To address the long-standing data sparsity problem in recommender systems (RSs), cross-domain recommendation (CDR) has been proposed to leverage the relatively richer information from a richer domain to improve the recommendation performance in a sparser domain.
