Search Results for author:
Found 89 papers, 48 papers with code
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models
To address this issue, we have created GVC data that allows for the combination of grounding and chat capabilities.
Convolutional Neural Networks for Segmentation of Malignant Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance)
Percent difference of tumor volume and overlap using the Dice Similarity Coefficient (DSC) were compared between the standard reference provided by the radiologist and CNN outputs for thresholds ranging from 0. 001 to 0. 9.
T-Rex: Counting by Visual Prompting
Guided by the visual feedback from T-Rex, users can also interactively refine the counting results by prompting on missing or falsely-detected objects.
Visual In-Context Prompting
In-context prompting in large language models (LLMs) has become a prevalent approach to improve zero-shot capabilities, but this idea is less explored in the vision domain.
Infinite forecast combinations based on Dirichlet process
Forecast combination integrates information from various sources by consolidating multiple forecast results from the target time series.
Probabilistic Forecast Reconciliation with Kullback-Leibler Divergence Regularization
As the popularity of hierarchical point forecast reconciliation methods increases, there is a growing interest in probabilistic forecast reconciliation.
LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models.
Ranked #1 on
LMM real-life tasks
on Leaderboard
An Approach for Multi-Object Tracking with Two-Stage Min-Cost Flow
Specifically, we employ the minimum network flow algorithm with high-confidence detections as input in the first stage to obtain the candidate tracklets that need correction.
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
We present Set-of-Mark (SoM), a new visual prompting method, to unleash the visual grounding abilities of large multimodal models (LMMs), such as GPT-4V.
Forecasting large collections of time series: feature-based methods
In economics and many other forecasting domains, the real world problems are too complex for a single model that assumes a specific data generation process.
Incentivizing Massive Unknown Workers for Budget-Limited Crowdsensing: From Off-Line and On-Line Perspectives
Moreover, the standard CMAB usually assumes the workers always stay in the system, whereas the workers may join in or depart from the system over time, such that what we have learnt for an individual worker cannot be applied after the worker leaves.
Neural Interactive Keypoint Detection
Click-Pose explores how user feedback can cooperate with a neural keypoint detector to correct the predicted keypoints in an interactive way for a faster and more effective annotation process.
A Forecaster's Review of Judea Pearl's Causality: Models, Reasoning and Inference, Second Edition, 2009
With the big popularity and success of Judea Pearl's original causality book, this review covers the main topics updated in the second edition in 2009 and illustrates an easy-to-follow causal inference strategy in a forecast scenario.
DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting
Existing feature lifting approaches, such as Lift-Splat-based and 2D attention-based, either use estimated depth to get pseudo LiDAR features and then splat them to a 3D space, which is a one-pass operation without feature refinement, or ignore depth and lift features by 2D attention mechanisms, which achieve finer semantics while suffering from a depth ambiguity problem.
Semantic-SAM: Segment and Recognize Anything at Any Granularity
In this paper, we introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity.
You Can Mask More For Extremely Low-Bitrate Image Compression
Extensive experiments have demonstrated that our approach outperforms recent state-of-the-art methods in R-D performance, visual quality, and downstream applications, at very low bitrates.
Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidance
In this work, we explore the potential of resolution fields in scalable image compression and propose the reciprocal pyramid network (RPN) that fulfills the need for more adaptable and versatile compression.
detrex: Benchmarking Detection Transformers
To address this issue, we develop a unified, highly modular, and lightweight codebase called detrex, which supports a majority of the mainstream DETR-based instance recognition algorithms, covering various fundamental tasks, including object detection, segmentation, and pose estimation.
A Strong and Reproducible Object Detector with Only Public Datasets
This work presents Focal-Stable-DINO, a strong and reproducible object detection model which achieves 64. 6 AP on COCO val2017 and 64. 8 AP on COCO test-dev using only 700M parameters without any test time augmentation.
Ranked #4 on
Object Detection
on COCO test-dev
Segment Everything Everywhere All at Once
In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).
Detection Transformer with Stable Matching
We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is highlighted by the one-to-one matching design in DETR.
Exploring Data Geometry for Continual Learning
Our method dynamically expands the geometry of the underlying space to match growing geometric structures induced by new data, and prevents forgetting by keeping geometric structures of old data into account.
Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning
Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain, relying on the intrinsic interactions between visual and semantic information.
A Simple Framework for Open-Vocabulary Segmentation and Detection
We present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets.
Ranked #2 on
Instance Segmentation
on ADE20K val
(using extra training data)
MP-Former: Mask-Piloted Transformer for Image Segmentation
We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation.
Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR
Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance.
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion.
Ranked #1 on
Zero-Shot Object Detection
on ODinW
(using extra training data)
Introducing Depth into Transformer-based 3D Object Detection
To address the second issue, we introduce an auxiliary learning task called Depth-aware Negative Suppression loss.
Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation
This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information.
Ranked #2 on
2D Human Pose Estimation
on Human-Art
Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR
Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance.
Technical Report -- Competition Solution for Prompt Tuning using Pretrained Language Model
Prompt tuning recently becomes a hot-spot in the applications of large pretrained language models on specific downstream tasks.
Integrated optimization of train timetables rescheduling and response vehicles on a disrupted metro line
Numerical cases of Beijing Metro Line 9 verify the efficiency and effectiveness of our proposed model, and results show that: (1) when occurring a disruption event during peak hours, the impact on the normal timetable is greater, and passengers in the direction with fewer train services are more affected; (2) if passengers stranded at the terminal stations of disruption area are not transported in time, they will rapidly increase at a speed of more than 300 passengers per minute; (3) compared with the fixed shortest path, using the response vehicles reduces the total travel time about 7%.
Learning Detail-Structure Alternative Optimization for Blind Super-Resolution
Recent blind SR methods suggest to reconstruct SR images relying on blur kernel estimation.
Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution
In this paper, we analyze the degradation of a high-resolution (HR) image from image intrinsic components according to a degradation-based formulation model.
DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding
As phrase extraction can be regarded as a $1$D text segmentation problem, we formulate PEG as a dual detection problem and propose a novel DQ-DETR model, which introduces dual queries to probe different features from image and text for object prediction and phrase mask prediction.
Ranked #6 on
Referring Expression Comprehension
on RefCOCO
A Unified Mutual Supervision Framework for Referring Expression Segmentation and Generation
Our mutual supervision contains two directions.
Cloud removal Using Atmosphere Model
Cloud removal is an essential task in remote sensing data analysis.
Intelligent detect for substation insulator defects based on CenterMask
Based on the end-to-end learning paradigm, this paper proposes an intelligent detection method for substation insulator defects based on CenterMask.
Machine Learning Prediction of COVID-19 Severity Levels From Salivaomics Data
The clinical spectrum of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the strain of coronavirus that caused the COVID-19 pandemic, is broad, extending from asymptomatic infection to severe immunopulmonary reactions that, if not categorized properly, may be life-threatening.
Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation
In this paper we present Mask DINO, a unified object detection and segmentation framework.
Ranked #1 on
Panoptic Segmentation
on COCO test-dev
(using extra training data)
Multi-objective Optimization of Clustering-based Scheduling for Multi-workflow On Clouds Considering Fairness
There is a limited research on multi-objective optimization for multi-workflow scheduling.
Forecast combinations: an over 50-year review
Forecast combinations have flourished remarkably in the forecasting community and, in recent years, have become part of the mainstream of forecasting research and activities.
Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation
We conduct experiments on three popular datasets for document-level machine translation and our model has an average improvement of 0. 91 s-BLEU over the sentence-level baseline.
Optimal reconciliation with immutable forecasts
In this paper, we formulate reconciliation methodology that keeps forecasts of a pre-specified subset of variables unchanged or "immutable".
APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction
In many web applications, deep learning-based CTR prediction models (deep CTR models for short) are widely adopted.
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results.
Ranked #1 on
Real-Time Object Detection
on COCO 2017 val
Vision-Language Intelligence: Tasks, Representation Learning, and Large Models
This survey is inspired by the remarkable progress in both computer vision and natural language processing, and recent trends shifting from single modality processing to multiple modality comprehension.
DN-DETR: Accelerate DETR Training by Introducing Query DeNoising
Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement.
A resource-efficient deep learning framework for low-dose brain PET image reconstruction and analysis
18F-fluorodeoxyglucose (18F-FDG) Positron Emission Tomography (PET) imaging usually needs a full-dose radioactive tracer to obtain satisfactory diagnostic results, which raises concerns about the potential health risks of radiation exposure, especially for pediatric patients.
Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability
The efficacy of our proposed three-staged collaborative learning algorithm is finally verified by extensive experiments on both synthetic and real datasets.
DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR.
Upright-Net: Learning Upright Orientation for 3D Point Cloud
A mass of experiments shows that the pose of the input 3D models exerts a tremendous influence on automatic 3D shape analysis.
Encoding Spatial Distribution of Convolutional Features for Texture Representation
Existing convolutional neural networks (CNNs) often use global average pooling (GAP) to aggregate feature maps into a single representation.
Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning
With this method, Yuan 1. 0, the current largest singleton language model with 245B parameters, achieves excellent performance on thousands GPUs during training, and the state-of-the-art results on NLP tasks.
Generalizable Person Re-identification Without Demographics
However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.
The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations
The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0. 913 (95% CI, 0. 898-0. 927), with a sensitivity of 0. 695 (95% CI, 0. 643-0. 748), a specificity of 0. 904 (95% CI, 0. 891 -0. 919), an accuracy of 0. 875(0. 861-0. 889), and a F1 of 0. 611(0. 568-0. 655).
Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection
For the cross-modality interaction in feature encoder, existing methods either indiscriminately treat RGB and depth modalities, or only habitually utilize depth cues as auxiliary information of the RGB branch.
Bayesian forecast combination using time-varying features
In this work, we propose a novel framework for density forecast combination by constructing time-varying weights based on time series features, which is called Feature-based Bayesian Forecasting Model Averaging (FEBAMA).
Deep Texture Recognition via Exploiting Cross-Layer Statistical Self-Similarity
In recent years, convolutional neural networks (CNNs) have become a prominent tool for texture recognition.
Rapid COVID-19 Risk Screening by Eye-region Manifestations
It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts.
Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction
Most of the existing methods adopt a DNN-based model to capture the cross features in an implicit manner.
Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline
Depth maps obtained by commercial depth sensors are always in low-resolution, making it difficult to be used in various computer vision tasks.
Graph Intention Network for Click-through Rate Prediction in Sponsored Search
Moreover, it is difficult for user to jump out of their specific historical behaviors for possible interest exploration, namely weak generalization problem.
Hierarchical forecasting with a top-down alignment of independent level forecasts
In this paper, we present a \emph{hierarchical-forecasting-with-alignment} approach that treats the bottom level forecasts as mutable to ensure higher forecasting accuracy on the upper levels of the hierarchy.
Spectrum Sharing for 6G Integrated Satellite-Terrestrial Communication Networks Based on NOMA and Cognitive Radio
ISTCN aims to provide high speed and pervasive network services by integrating broadband terrestrial mobile networks with satellite communication networks.
Towards Complete Scene and Regular Shape for Distortion Rectification by Curve-Aware Extrapolation
To our knowledge, we are the first to tackle the challenging rectification via outpainting, and our curve-aware strategy can reach a rectification construction with complete content and regular shape.
Forecast with Forecasts: Diversity Matters
In this work, we suggest a change of focus from the historical data to the produced forecasts to extract features.
A Distributed Privacy-Preserving Learning Dynamics in General Social Networks
In this paper, we study a distributed privacy-preserving learning problem in social networks with general topology.
Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration
In this paper, we present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction.
No Perfect Outdoors: Towards A Deep Profiling of GNSS-based Location Contexts
On one hand, we offer a more fine-grained semantic classification than binary indoor-outdoor detection.
Networking and Internet Architecture
A New Screening Method for COVID-19 based on Ocular Feature Recognition by Machine Learning Tools
After more than four months study, we found that the confirmed cases of COVID-19 present the consistent ocular pathological symbols; and we propose a new screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras, could reliably make a rapid risk screening of COVID-19 with very high accuracy.
SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration
Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and information omission.
Ranked #1 on
Dialogue Rewriting
on Multi-Rewrite
(BLEU-1 metric)
Distributed ARIMA Models for Ultra-long Time Series
Providing forecasts for ultra-long time series plays a vital role in various activities, such as investment decisions, industrial production arrangements, and farm management.
Applications Computation
Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention
Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature.
Model Embedded DRL for Intelligent Greenhouse Control
Greenhouse environment is the key to influence crops production.
Cost-Effective Testing of a Deep Learning Model through Input Reduction
Experiments with various DL models and datasets show that our approach can reduce the whole testing data to 4. 6\% on average, and can reliably estimate the performance of DL models.
Déjà vu: forecasting with similarity
Instead of extrapolating, the future paths of the similar reference series are aggregated and serve as the basis for the forecasts of the target series.
Methodology Applications
FFORMPP: Feature-based forecast model performance prediction
We model the forecast error as a function of time series features calculated from the historical time series with an efficient Bayesian multivariate surface regression approach.
Applications
Least Squares Approximation for a Distributed System
The finite sample performance and computational efficiency are further illustrated by an extensive numerical study and an airline dataset.
Que será será? The uncertainty estimation of feature-based time series forecasts
In the training part, we use a collection of time series to train a model to explore how time series features affect the interval forecasting accuracy of different forecasting methods, which makes our proposed framework interpretable in terms of the contribution of each feature to the models' uncertainty prediction.
Methodology Applications Computation
Remove Cosine Window from Correlation Filter-based Visual Trackers: When and How
Therefore, we in this paper investigate the feasibility to remove cosine window from CF trackers with spatial regularization.
Forecasting with time series imaging
Recently, the use of time series features for forecast model averaging has been an emerging research focus in the forecasting community.
GRATIS: GeneRAting TIme Series with diverse and controllable characteristics
The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks.
Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
Compared with SRDCF, STRCF with hand-crafted features provides a 5 times speedup and achieves a gain of 5. 4% and 3. 6% AUC score on OTB-2015 and Temple-Color, respectively.
Ranked #8 on
Visual Object Tracking
on VOT2017/18
Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks
Firstly, given one input image, feature description neural network (FDNN) is used to generate a new representation of this image, so that this image representation can be more efficiently compressed by standard codec, as compared to the input image.
A Modified Sigma-Pi-Sigma Neural Network with Adaptive Choice of Multinomials
We propose in this paper a modified Sigma-Pi-Sigma neural network (MSPSNN) with an adaptive approach to find a better multinomial for a given problem.
Extreme Learning Machine with Local Connections
This paper is concerned with the sparsification of the input-hidden weights of ELM (Extreme Learning Machine).
Integrating Boundary and Center Correlation Filters for Visual Tracking with Aspect Ratio Variation
The aspect ratio variation frequently appears in visual tracking and has a severe influence on performance.
Deep Models for Engagement Assessment With Scarce Label Information
We compared performances of the new data representations with the original EEG features for engagement assessment.
