Search Results for author:
Found 173 papers, 61 papers with code
When does Further Pre-training MLM Help? An Empirical Study on Task-Oriented Dialog Pre-training
Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks’ performances.
An Empirical Study of Federated Prompt Learning for Vision Language Model
This paper systematically investigates the behavioral differences between language prompt learning (LPT) and vision prompt learning (VPT) under data heterogeneity challenges, including label skew and domain shift.
OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
OMCRG reflects natural dyadic interactions and poses new challenges in achieving synchronization between the generated audio and facial responses of the listener.
Audio-Visual Synchronization
Conversational Response Generation
+3
DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval
Composed Image Retrieval (CIR) aims to retrieve target images from a gallery based on a reference image and modification text as a combined query.
NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
A total of 211 participants have registered in the structure track.
Bronchovascular Tree-Guided Weakly Supervised Learning Method for Pulmonary Segment Segmentation
Pulmonary segment segmentation is crucial for cancer localization and surgical planning.
Safety2Drive: Safety-Critical Scenario Benchmark for the Evaluation of Autonomous Driving
(3) Safety2Drive supports multi-dimensional evaluation.
Agent-as-a-Service based on Agent Network
AaaS-AN unifies the entire agent lifecycle, including construction, integration, interoperability, and networked collaboration, through two core components: (1) a dynamic Agent Network, which models agents and agent groups as vertexes that self-organize within the network based on task and role dependencies; (2) service-oriented agents, incorporating service discovery, registration, and interoperability protocols.
On relative universality, regression operator, and conditional independence
The notion of relative universality with respect to a {\sigma}-field was introduced to establish the unbiasedness and Fisher consistency of an estimator in nonlinear sufficient dimension reduction.
NuWa: Deriving Lightweight Task-Specific Vision Transformers for Edge Devices
NuWa can transfer task-specific knowledge extracted from the base ViT into small ViTs that fully leverage constrained resources on edge devices to maximize model accuracy with inference latency assurance.
Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios
However, the safety and robustness assessment of autonomous driving has not received sufficient attention.
Assessing Validity of ICD-10 Administrative Data in Coding Comorbidities
The C-statistics for predicting in-hospital mortality using comorbidities by ICD-10 were 0. 84 in 2003, 0. 81 in 2015, and 0. 78 in 2022.
Can Video Diffusion Model Reconstruct 4D Geometry?
Reconstructing dynamic 3D scenes (i. e., 4D geometry) from monocular video is an important yet challenging problem.
4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding
Multimodal Large Language Models (MLLMs) have demonstrated impressive 2D image/video understanding capabilities.
High Accuracy Pulmonary Vessel Segmentation for Contrast and Non-contrast CT Images and Clinical Evaluation
However, the segmentation precision of these methods is insufficient, and support for NCCT (Non-Contrast Computed Tomography) types of data is also a requirement in some clinical scenarios.
Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation Models
We propose a novel efficient FDS method based on feature matching.
Few-Shot Semantic Segmentation
Manufacturing Quality Control
+4
Visual-Instructed Degradation Diffusion for All-in-One Image Restoration
Image restoration tasks like deblurring, denoising, and dehazing usually need distinct models for each degradation type, restricting their generalization in real-world scenarios with mixed or unknown degradations.
Reversing Flow for Image Restoration
Image restoration aims to recover high-quality (HQ) images from degraded low-quality (LQ) ones by reversing the effects of degradation.
Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering
Large Language Models (LLMs) have achieved impressive results in knowledge-based Visual Question Answering (VQA).
Prompting Large Language Models with Rationale Heuristics for Knowledge-based Visual Question Answering
Despite the encouraging results of previous studies, prior methods prompt LLMs to predict answers directly, neglecting intermediate thought processes.
WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network
We address the challenge of WiFi-based temporal activity detection and propose an efficient Dual Pyramid Network that integrates Temporal Signal Semantic Encoders and Local Sensitive Response Encoders.
Belted and Ensembled Neural Network for Linear and Nonlinear Sufficient Dimension Reduction
We introduce a unified, flexible, and easy-to-implement framework of sufficient dimension reduction that can accommodate both linear and nonlinear dimension reduction, and both the conditional distribution and the conditional mean as the targets of estimation.
mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA
Thus, multimodal Retrieval-Augmented Generation (mRAG) is naturally introduced to provide MLLMs with comprehensive and up-to-date knowledge, effectively expanding the knowledge scope.
SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning
The quality analysis of ROIs can provide fine-grained guidance for image quality improvement and is crucial for scenarios focusing on region-level quality.
DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning
Semi-supervised learning (SSL) leverages limited labeled and abundant unlabeled data but often faces challenges with data imbalance, especially in 3D contexts.
SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking
Specifically, we propose a Task-specific Hybrid Matching module for a weight-shared cross-attention-based decoder that matches the targets of track queries with multiple object queries to exploit promising candidates overlooked by the self-attention mechanism.
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
Bird's-eye-view (BEV) map layout estimation requires an accurate and full understanding of the semantics for the environmental elements around the ego car to make the results coherent and realistic.
LLM-Aided Efficient Hardware Design Automation
With the rapidly increasing complexity of modern chips, hardware engineers are required to invest more effort in tasks such as circuit design, verification, and physical implementation.
SAM-Guided Masked Token Prediction for 3D Scene Understanding
Foundation models have significantly enhanced 2D task performance, and recent works like Bridge3D have successfully applied these models to improve 3D scene understanding through knowledge distillation, marking considerable advancements.
SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data
Facial expression datasets remain limited in scale due to privacy concerns, the subjectivity of annotations, and the labor-intensive nature of data collection.
Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression
In this paper, we take a step further to explore parameter sharing across different layers with SVD to achieve more effective compression for LLMs.
Token Caching for Diffusion Transformer Acceleration
Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance.
Multi-View Adaptive Contrastive Learning for Information Retrieval Based Fault Localization
Most studies focused on information retrieval-based techniques for fault localization, which built representations for bug reports and source code files and matched their semantic vectors through similarity measurement.
MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation
With the rising demand for high-resolution (HR) images, No-Reference Image Quality Assessment (NR-IQA) gains more attention, as it can ecaluate image quality in real-time on mobile devices and enhance user experience.
An Efficient General-Purpose Optical Accelerator for Neural Networks
Experimental results show that with a given number of MZIs, the mapping efficiency of neural networks on the proposed architecture can be enhanced by 21. 87%, 21. 20%, 24. 69%, and 25. 52% for VGG16 and Resnet18 on datasets Cifar10 and Cifar100, respectively.
TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks
Neural radiance fields (NeRFs) generally require many images with accurate poses for accurate novel view synthesis, which does not reflect realistic setups where views can be sparse and poses can be noisy.
SuperEncoder: Towards Universal Neural Approximate Quantum State Preparation
Numerous quantum algorithms operate under the assumption that classical data has already been converted into quantum states, a process termed Quantum State Preparation (QSP).
MIBench: Evaluating Multimodal Large Language Models over Multiple Images
However, most existing MLLMs and benchmarks primarily focus on single-image input scenarios, leaving the performance of MLLMs when handling realistic multiple images underexplored.
How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?
Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency.
EA-VTR: Event-Aware Video-Text Retrieval
EA-VTR can efficiently encode frame-level and video-level visual representations simultaneously, enabling detailed event content and complex event temporal cross-modal alignment, ultimately enhancing the comprehensive understanding of video events.
Automated C/C++ Program Repair for High-Level Synthesis via Large Language Models
Since Large Language Models (LLMs) have the ability to automate code generation, they can also be used for automated program repair in HLS.
Classification-Based Automatic HDL Code Generation Using LLMs
In this work, we introduce a human-expert-inspired method to mitigate the hallucination of LLMs and improve the performance in HDL code generation.
BasisN: Reprogramming-Free RRAM-Based In-Memory-Computing by Basis Combination for Deep Neural Networks
BasisN introduces a novel representation of the kernels in DNN layers as combinations of global basis vectors shared between all layers with quantized coefficients.
LiveMind: Low-latency Large Language Models with Simultaneous Inference
By employing an large LLM for inference and a small LLM for output, we achieve an average 37% reduction in response latency, alongside a 4. 30% improvement in accuracy on the MMLU-Pro dataset compared with the baseline.
Root Cause Localization for Microservice Systems in Cloud-edge Collaborative Environments
Experiments conducted on the dataset collected from the benchmark show that MicroCERCL can accurately localize the root cause of microservice systems in such environments, significantly outperforming state-of-the-art approaches with an increase of at least 24. 1% in top-1 accuracy.
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
To this end, we propose a novel diffusion-based pipeline that generates high-quality multi-view videos centered around a dynamic 3D object from text.
DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detection
Cooperation between temporal convolutional networks (TCN) and graph convolutional networks (GCN) as a processing module has shown promising results in skeleton-based video anomaly detection (SVAD).
Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
Foundational generative models should be traceable to protect their owners and facilitate safety regulation.
NTIRE 2024 Quality Assessment of AI-Generated Content Challenge
A total of 196 participants have registered in the video track.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
End-To-End Training and Testing Gamification Framework to Learn Human Highway Driving
The proposed solution is validated in GTA V games, and the results demonstrate the effectiveness of this end-to-end gamification framework for learning human driving skills.
A Copula Graphical Model for Multi-Attribute Data using Optimal Transport
Motivated by modern data forms such as images and multi-view data, the multi-attribute graphical model aims to explore the conditional independence structure among vectors.
PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts
On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements.
Benchmarking Segmentation Models with Mask-Preserved Attribute Editing
We evaluate a broad variety of semantic segmentation models, spanning from conventional close-set models to recent open-vocabulary large models on their robustness to different types of variations.
Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training
In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment.
NARUTO: Neural Active Reconstruction from Uncertain Target Observations
We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction.
Location-guided Head Pose Estimation for Fisheye Image
Camera with a fisheye or ultra-wide lens covers a wide field of view that cannot be modeled by the perspective projection.
Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval
In this work, we propose the UNIFY framework, which learns lexicon representations to capture fine-grained semantics and combines the strengths of latent and lexicon representations for video-text retrieval.
EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network Acceleration
The experimental results confirmed the reduction of circuit area by up to 48. 79% and the reduction of power consumption of executing DNNs by up to 64. 41%, while the accuracy of the neural networks can still be well maintained.
Pruner: A Speculative Exploration Mechanism to Accelerate Tensor Program Tuning
Results show that in online cost model tuning scenarios, Pruner and MoA-Pruner can achieve an average speedup of $2. 6 \times$ and $4. 82 \times$ compared to Ansor.
NFT1000: A Cross-Modal Dataset for Non-Fungible Token Retrieval
In this paper, we will introduce a benchmark dataset named "NFT Top1000 Visual-Text Dataset" (NFT1000), containing 7. 56 million image-text pairs, and being collected from 1000 most famous PFP1 NFT collections2 by sales volume on the Ethereum blockchain.
CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Accelerators
Based on the proposed abstraction, CIM-MLC can compile tasks onto a wide range of CIM accelerators having different devices, architectures, and programming interfaces.
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.
Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance
At the second stage the image-wise compensatory information is derived with the compensatory kernels and embedded into the rescaled input images.
Tune-An-Ellipse: CLIP Has Potential to Find What You Want
Visual prompting of large vision language models such as CLIP exhibits intriguing zero-shot capabilities.
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.
Dataset Distillation via Adversarial Prediction Matching
This ensures the memory efficiency of our method and provides a flexible tradeoff between time and memory budgets, allowing us to distil ImageNet-1K using a minimum of only 6. 5GB of GPU memory.
OplixNet: Towards Area-Efficient Optical Split-Complex Networks with Real-to-Complex Data Assignment and Knowledge Distillation
In conventional ONNs, light amplitudes are modulated at the input and detected at the output.
Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder
However, a notable limitation of these approaches is that they do not fully utilize the multi-view attributes inherent in 3D point clouds, which is crucial for a deeper understanding of 3D structures.
Knowledge Graph Construction in Power Distribution Networks
In this paper, we propose a method for knowledge graph construction in power distribution networks.
ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking
To this end, we non-uniformly resize the cropped image to have a smaller input size while the resolution of the area where the target is more likely to appear is higher and vice versa.
Automatic Animation of Hair Blowing in Still Portrait Photos
Considering the complexity of hair structure, we innovatively treat hair wisp extraction as an instance segmentation problem, where a hair wisp is referred to as an instance.
Early-Exit with Class Exclusion for Efficient Inference of Neural Networks
Deep neural networks (DNNs) have been successfully applied in various fields.
Logic Design of Neural Networks for High-Throughput and Low-Power Applications
However, under a given area constraint, the number of MAC units in such platforms is limited, so MAC units have to be reused to perform MAC operations in a neural network.
FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection
Image reconstruction-based anomaly detection models are widely explored in industrial visual inspection.
Ranked #17 on
Anomaly Detection
on VisA
On Exact Bayesian Credible Sets for Classification and Pattern Recognition
As a result, there is as of today no general way to construct an exact credible set for classification.
Learning to Identify Critical States for Reinforcement Learning from Videos
Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions.
Spectral Regularized Kernel Goodness-of-Fit Tests
Maximum mean discrepancy (MMD) has enjoyed a lot of success in many machine learning and statistical applications, including non-parametric hypothesis testing, because of its ability to handle non-Euclidean data.
On Sufficient Graphical Models
We introduce a sufficient graphical model by applying the recently developed nonlinear sufficient dimension reduction techniques to the evaluation of conditional independence.
Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting
However, the fine-tuned PLMs often overwhelmingly focus on the textual information and overlook structural knowledge.
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors.
CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality
To alleviate these limitations, in this paper, we present CATS, a pragmatic Chinese answer-to-sequence dataset with large scale and high quality.
Dynamically Masked Discriminator for Generative Adversarial Networks
By treating the generated data in training as a stream, we propose to detect whether the discriminator slows down the learning of new knowledge in generated data.
Computational and Storage Efficient Quadratic Neurons for Deep Neural Networks
Deep neural networks (DNNs) have been widely deployed across diverse domains such as computer vision and natural language processing.
Mindstorms in Natural Language-Based Societies of Mind
What should be the social structure of an NLSOM?
Exploiting Correlations Between Contexts and Definitions with Multiple Definition Modeling
In this paper, we carefully design a new task called Multiple Definition Modeling (MDM) that pool together all contexts and definition of target words.
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding.
Component-aware anomaly detection framework for adjustable and logical industrial visual inspection
Meanwhile, segmenting a product image into multiple components provides a novel perspective for industrial visual inspection, demonstrating great potential in model customization, noise resistance, and anomaly classification.
Ranked #9 on
Anomaly Detection
on MVTec LOCO AD
CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction
Recent advances in neural reconstruction using posed image sequences have made remarkable progress.
LLM as A Robotic Brain: Unifying Egocentric Memory and Control
In this paper, we propose a novel and generalizable framework called LLM-Brain: using Large-scale Language Model as a robotic brain to unify egocentric memory and control.
PowerPruning: Selecting Weights and Activations for Power-Efficient Neural Network Acceleration
To address this challenge, we propose PowerPruning, a novel method to reduce power consumption in digital neural network accelerators by selecting weights that lead to less power consumption in MAC operations.
Understanding Bugs in Multi-Language Deep Learning Frameworks
Third, we found that 28. 6%, 31. 4%, and 16. 0% of bugs in MXNet, PyTorch, and TensorFlow are MPL bugs, respectively; the PL combination of Python and C/C++ is most used in fixing more than 92% MPL bugs in all DLFs.
Improving GAN Training via Feature Space Shrinkage
The evaluation results demonstrate that our AdaptiveMix can facilitate the training of GANs and effectively improve the image quality of generated samples.
Mean Parity Fair Regression in RKHS
We study the fair regression problem under the notion of Mean Parity (MP) fairness, which requires the conditional mean of the learned function output to be constant with respect to the sensitive attributes.
Variation Enhanced Attacks Against RRAM-based Neuromorphic Computing System
The RRAM-based neuromorphic computing system has amassed explosive interests for its superior data processing capability and energy efficiency than traditional architectures, and thus being widely used in many data-centric applications.
Plan-then-Seam: Towards Efficient Table-to-Text Generation
Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables.
Learning To Exploit the Sequence-Specific Prior Knowledge for Image Processing Pipelines Optimization
The ISP is less programmable and consists of a series of processing modules.
AdaptiveMix: Improving GAN Training via Feature Space Shrinkage
The evaluation results demonstrate that our AdaptiveMix can facilitate the training of GANs and effectively improve the image quality of generated samples.
AUNet: Learning Relations Between Action Units for Face Forgery Detection
Observing that face manipulation may alter the relation between different facial action units (AU), we propose the Action Units Relation Learning framework to improve the generality of forgery detection.
ViLEM: Visual-Language Error Modeling for Image-Text Retrieval
ViLEM then enforces the model to discriminate the correctness of each word in the plausible negative texts and further correct the wrong words via resorting to image information.
Ranked #46 on
Visual Reasoning
on Winoground
NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation
Temporal video segmentation is the get-to-go automatic video analysis, which decomposes a long-form video into smaller components for the following-up understanding tasks.
Order-Prompted Tag Sequence Generation for Video Tagging
This paper proposes a novel generative model, Order-Prompted Tag Sequence Generation (OP-TSG), according to the above characteristics.
Spectral Regularized Kernel Two-Sample Tests
First, we show the popular MMD (maximum mean discrepancy) two-sample test to be not optimal in terms of the separation boundary measured in Hellinger distance.
Hierarchical Terrain Attention and Multi-Scale Rainfall Guidance For Flood Image Prediction
With the deterioration of climate, the phenomenon of rain-induced flooding has become frequent.
Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shape
As a result, backdoor pattern designed for one certain 3D data structure will be disable for other data structures of the same 3D scene.
CorrectNet: Robustness Enhancement of Analog In-Memory Computing for Neural Networks by Error Suppression and Compensation
These acceleration platforms rely on analog properties of the devices and thus suffer from process variations and noise.
SteppingNet: A Stepping Neural Network with Incremental Accuracy Enhancement
In such platforms, neural networks need to provide acceptable results quickly and the accuracy of the results should be able to be enhanced dynamically according to the computational resources available in the computing system.
Class-based Quantization for Neural Networks
In the proposed method, the importance score of each filter or neuron with respect to the number of classes in the dataset is first evaluated.
Coarse-Super-Resolution-Fine Network (CoSF-Net): A Unified End-to-End Neural Network for 4D-MRI with Simultaneous Motion Estimation and Super-Resolution
Four-dimensional magnetic resonance imaging (4D-MRI) is an emerging technique for tumor motion management in image-guided radiation therapy (IGRT).
Decoupled Mixup for Generalized Visual Recognition
Since the observation is that noise-prone regions such as textural and clutter backgrounds are adverse to the generalization ability of CNN models during training, we enhance features from discriminative regions and suppress noise-prone ones when combining an image pair.
Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection
The model with an overly strong generalization capability can even well reconstruct the abnormal regions, making them less distinguishable, while the model with a poor generalization capability can not reconstruct those changeable high-frequency components in the normal regions, which ultimately leads to false positives.
Ranked #22 on
Anomaly Detection
on VisA
Class-Level Confidence Based 3D Semi-Supervised Learning
Firstly, a dynamic thresholding strategy is proposed to utilize more unlabeled data, especially for low learning status classes.
Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completion
To remedy the KG structure information loss from the "flat" text, we further improve the input representations of entities and relations, and the inference algorithm in KG-S2S.
Combating Mode Collapse in GANs via Manifold Entropy Estimation
In this paper, we propose a novel training pipeline to address the mode collapse issue of GANs.
Cross-Architecture Knowledge Distillation
However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN.
Nonlinear Sufficient Dimension Reduction for Distribution-on-Distribution Regression
We introduce a new approach to nonlinear sufficient dimension reduction in cases where both the predictor and the response are distributional data, modeled as members of a metric space.
PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning
The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video.
Narrowing the Gap: Improved Detector Training with Noisy Location Annotations
Experiments for both synthesized and real-world scenarios consistently demonstrate the effectiveness of our approach, e. g., our method increases the degraded performance of the FCOS detector from 33. 6% AP to 35. 6% AP on COCO.
Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement
To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net).
SubGraph Networks based Entity Alignment for Cross-lingual Knowledge Graph
Cross-lingual knowledge graph entity alignment aims to discover the cross-lingual links in the multi-language KGs, which is of great significance to the NLP applications and multi-language KGs fusion.
Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning
They base the visual grounding on the features from pre-generated proposals or anchors, and fuse these features with the text embeddings to locate the target mentioned by the text.
CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation
In this paper, we propose to CREATE, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration benchmark, to facilitate research and application in video titling and video retrieval in Chinese.
Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions.
Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels
To provide an alternative, we propose a novel approach that utilizes monocular RGB images and point clouds to generate pseudo scene flow labels for training scene flow networks.
Continual Prompt Tuning for Dialog State Tracking
A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle.
Learning Target-aware Representation for Visual Tracking via Informative Interactions
The proposed GIM module and InBN mechanism are general and applicable to different backbone types including CNN and Transformer for improvements, as evidenced by our extensive experiments on multiple benchmarks.
An additive graphical model for discrete data
We introduce a nonparametric graphical model for discrete node variables based on additive conditional independence.
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot online adaptation without requiring offline training.
EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching
The datasets will be released to facilitate the development of video captioning metrics.
Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos
In this paper, we propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information.
Multimodal Semi-Supervised Learning for 3D Objects
This paper explores how the coherence of different modelities of 3D data (e. g. point cloud, image, and mesh) can be used to improve data efficiency for both 3D classification and retrieval tasks.
MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction
In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document.
Dimension Reduction for Fréchet Regression
In this paper, we introduce a flexible sufficient dimension reduction (SDR) method for Fr\'echet regression to achieve two purposes: to mitigate the curse of dimensionality caused by high-dimensional predictors and to provide a visual inspection tool for Fr\'echet regression.
Self-Supervised Modality-Invariant and Modality-Specific Feature Learning for 3D Objects
Our proposed novel self-supervised model learns two types of distinct features: modality-invariant features and modality-specific features.
Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
Unlike the existing methods that use sparse LiDAR mainly in a manner of time-consuming iterative post-processing, our model fuses monocular image features and sparse LiDAR features to predict initial depth maps.
Ranked #1 on
Depth Completion
on KITTI
SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction
CDI builds the global attention and interaction among different levels in decoupled space which also solves the problem of heavy computation.
Learn to Match: Automatic Matching Network Design for Visual Tracking
Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants.
PSE-Match: A Viewpoint-free Place Recognition Method with Parallel Semantic Embedding
Accurate localization on autonomous driving cars is essential for autonomy and driving safety, especially for complex urban streets and search-and-rescue subterranean environments where high-accurate GPS is not available.
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition.
Ranked #13 on
Skeleton Based Action Recognition
on N-UCLA
Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules
However, due to the vast diversity of images, it is not optimal to use one model for all images, even different regions within one image.
Automatic Construction of Enterprise Knowledge Base
In this paper, we present an automatic knowledge base construction system from large scale enterprise documents with minimal efforts of human intervention.
SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
We propose a novel scene flow estimation approach to capture and infer 3D motions from point clouds.
A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Tracking
In this paper, we show the existence of universal perturbations that can enable the targeted attack, e. g., forcing a tracker to follow the ground-truth trajectory with specified offsets, to be video-agnostic and free from inference in a network.
PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling
However, the most suitable positions for inferring different targets, i. e., the object category and boundaries, are generally different.
One More Check: Making "Fake Background" Be Tracked Again
Eventually, it helps to reload the ``fake background'' and repair the broken tracklets.
Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model
Inspired by the findings of our investigation, we propose a novel multi-modal video saliency model consisting of three branches: visual, audio and face.
AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
Specifically, a new generator architecture is proposed to simultaneously transfer color/texture styles and transform local facial shapes into anime-like counterparts based on the style of a reference anime-face, while preserving the global structure of the source photo-face.
On Forward Sufficient Dimension Reduction for Categorical and Ordinal Responses
Like other forward regression-based sufficient dimension reduction methods, our approach avoids the relatively stringent distributional requirements necessary for inverse regression alternatives.
Dimensionality Reduction
Methodology
Periodic repeating fast radio bursts: interaction between a magnetized neutron star and its planet in an eccentric orbit
Fast radio bursts (FRBs) are mysterious transient phenomena.
High Energy Astrophysical Phenomena
FGNET-RH: Fine-Grained Named Entity Typing via Refinement in Hyperbolic Space
Fine-Grained Named Entity Typing (FG-NET) aims at classifying the entity mentions into a wide range of entity types (usually hundreds) depending upon the context.
Named Entity Recognition in the Style of Object Detection
In this work, we propose a two-stage method for named entity recognition (NER), especially for nested NER.
Cross-Lingual Named Entity Recognition Using Parallel Corpus: A New Approach Using XLM-RoBERTa Alignment
We built an entity alignment model on top of XLM-RoBERTa to project the entities detected on the English part of the parallel data to the target language sentences, whose accuracy surpasses all previous unsupervised models.
Ranked #2 on
Cross-Lingual NER
on CoNLL 2003
High Quality Disparity Remapping With Two-Stage Warping
In the second stage, we derive another warping model to refine warping results in less important regions by eliminating serious distortions in shape, disparity and 3D structure.
Vocal Bursts Intensity Prediction
Vocal Bursts Valence Prediction
DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection
Furthermore, these two components are both plug-and-play and can be embedded in any backbone.
Rethinking the competition between detection and ReID in Multi-Object Tracking
However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm.
Ranked #1 on
Multi-Object Tracking
on HiEve
(using extra training data)
Towards Accurate Pixel-wise Object Tracking by Attention Retrieval
We first build a look-up-table (LUT) with the ground-truth mask in the starting frame, and then retrieves the LUT to obtain an attention map for spatial constraints.
Ocean: Object-aware Anchor-free Tracking
In this paper, we propose a novel object-aware anchor-free network to address this issue.
Ranked #2 on
Visual Object Tracking
on VOT2019
Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representations
Fine-Grained Named Entity Typing (FG-NET) is a key component in Natural Language Processing (NLP).
Object Relational Graph with Teacher-Recommended Learning for Video Captioning
In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy.
Ranked #9 on
Video Captioning
on VATEX
(using extra training data)
HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition
To tackle Named Entity Recognition (NER) tasks, supervised methods need to obtain sufficient cleanly annotated data, which is labor and time consuming.
VATEX Captioning Challenge 2019: Multi-modal Information Fusion and Multi-stage Training Strategy for Video Captioning
Multi-modal information is essential to describe what has happened in a video.
An Overview of In-memory Processing with Emerging Non-volatile Memory for Data-intensive Applications
The conventional von Neumann architecture has been revealed as a major performance and energy bottleneck for rising data-intensive applications.
Multimodal Semantic Attention Network for Video Captioning
Inspired by the fact that different modalities in videos carry complementary information, we propose a Multimodal Semantic Attention Network(MSAN), which is a new encoder-decoder framework incorporating multimodal semantic attributes for video captioning.
Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
Furthermore, since different layers in a deep network capture feature maps of different scales, we use these feature maps to construct a spatial pyramid and then utilize multi-scale information to obtain more accurate attention scores, which are used to weight the local features in all spatial positions of feature maps to calculate attention maps.
Depth-Aware Stereo Video Retargeting
As compared with traditional video retargeting, stereo video retargeting poses new challenges because stereo video contains the depth information of salient objects and its time dynamics.
Automatic Difficulty Assessment for Chinese Texts
We present a web-based interface that automatically assesses reading difficulty of Chinese texts.
Spatio-Temporal Self-Organizing Map Deep Network for Dynamic Object Detection From Videos
In dynamic object detection, it is challenging to construct an effective model to sufficiently characterize the spatial-temporal properties of the background.
Linear Contour Learning: A Method for Supervised Dimension Reduction
We propose a novel approach to sufficient dimension reduction in regression, based on estimating contour directions of negligible variation for the response surface.
Removing Mixture of Gaussian and Impulse Noise by Patch-Based Weighted Means
We first establish a law of large numbers and a convergence theorem in distribution to show the rate of convergence of the non-local means filter for removing Gaussian noise.
Illumination Estimation Based on Bilayer Sparse Coding
In this paper, we propose a novel bilayer sparse coding model for illumination estimation that considers image similarity in terms of both low level color distribution and high level image scene content simultaneously.
