Search Results for author:
Found 180 papers, 53 papers with code
Qwen Technical Report
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans.
Ranked #3 on
Multi-Label Text Classification
on CC3M-TagMask
Prompt Tuning for Generative Multimodal Pretrained Models
Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining.
Ranked #2 on
Visual Entailment
on SNLI-VE test
A Survey on Large Language Model based Autonomous Agents
In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of LLM-based autonomous agents from a holistic perspective.
DeepSeek-VL: Towards Real-World Vision-Language Understanding
The DeepSeek-VL family (both 1. 3B and 7B models) showcases superior user experiences as a vision-language chatbot in real-world applications, achieving state-of-the-art or competitive performance across a wide range of visual-language benchmarks at the same model size while maintaining robust performance on language-centric benchmarks.
Ranked #28 on
Visual Question Answering
on MM-Vet
FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis.
Face Parsing with RoI Tanh-Warping
It uses hierarchical local based method for inner facial components and global methods for outer facial components.
General Facial Representation Learning in a Visual-Linguistic Manner
In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner.
Ranked #1 on
Face Parsing
on CelebAMask-HQ
(using extra training data)
Dynamic Graph Representation Learning via Self-Attention Networks
Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization.
Unsupervised Pre-training for Person Re-identification
In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation.
Ranked #1 on
Person Re-Identification
on Market-1501
(using extra training data)
Large-Scale Pre-training for Person Re-identification with Noisy Labels
Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning.
Ranked #7 on
Person Re-Identification
on CUHK03
User Behavior Simulation with Large Language Model based Agents
Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process.
Rethinking the Hyperparameters for Fine-tuning
Our findings challenge common practices of fine-tuning and encourages deep learning practitioners to rethink the hyperparameters for fine-tuning.
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
As a starting point, we provide presets of 7 different modalities and 23 highly-diverse example tasks in OFASys, with which we also develop a first-in-kind, single model, OFA+, that can handle text, image, speech, video, and motion data.
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion.
Ranked #1 on
Point Cloud Completion
on ShapeNet
(Earth Mover's Distance metric)
Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining
However, it is challenging for existing methods to model long-range global information, where convolutional neural networks (CNNs) are constrained by their local receptive fields, and vision transformers (ViTs) suffer from high quadratic complexity of their attention mechanism.
Face X-ray for More General Face Forgery Detection
For this reason, face X-ray provides an effective way for detecting forgery generated by most existing face manipulation algorithms.
Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection
Graph-based fraud detection approaches have escalated lots of attention recently due to the abundant relational information of graph-structured data, which may be beneficial for the detection of fraudsters.
Ranked #4 on
Fraud Detection
on Amazon-Fraud
Omni-DETR: Omni-Supervised Object Detection with Transformers
This is enabled by a unified architecture, Omni-DETR, based on the recent progress on student-teacher framework and end-to-end transformer based object detection.
Ranked #14 on
Semi-Supervised Object Detection
on COCO 2% labeled data
Position Focused Attention Network for Image-Text Matching
Then, an attention mechanism is proposed to model the relations between the image region and blocks and generate the valuable position feature, which will be further utilized to enhance the region expression and model a more reliable relationship between the visual image and the textual sentence.
X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
Recently, approaches based on deep learning and methods for contextual information extraction have served in many image segmentation tasks.
Real-Time Neural Character Rendering with Pose-Guided Multiplane Images
We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality.
Boosting 3D Object Detection via Object-Focused Image Fusion
Given a set of point features and image feature maps, DeMF adaptively aggregates image features by taking the projected 2D location of the 3D point as reference.
Ranked #5 on
3D Object Detection
on SUN-RGBD val
CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions.
GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation
We study the problem of making item recommendations to ephemeral groups, which comprise users with limited or no historical activities together.
AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose
We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance.
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
The second step involves preserving dataset diversity through a clustering process. In our experiment, CaR selected a subset containing only 1. 96% of Alpaca's IT data, yet the underlying AlpaCaR model trained on this subset outperforms Alpaca by an average of 32. 1% in GPT-4 evaluations.
InterFormer: Real-time Interactive Image Segmentation
Interactive image segmentation enables annotators to efficiently perform pixel-level annotation for segmentation tasks.
ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment
On the other hand, AAM is an attention module which can get anisotropic attention mask focusing on the region of point and its local edge connected by adjacent points, it has a stronger response in tangent than in normal, which means relaxed constraints in the tangent.
Ranked #5 on
Face Alignment
on 300W
pNovo 3: precise de novo peptide sequencing using a learning-to-rank framework
In order to solve this problem, we developed pNovo 3, which used a learning-to-rank framework to distinguish similar peptide candidates for each spectrum.
Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds
Each situation corresponds to a state instance wherein a robot is potentially unable to complete a task using a solution that normally works.
Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors
Through further analysis of the ASR outputs, we find that in some cases the sentiment words, the key sentiment elements in the textual modality, are recognized as other words, which makes the sentiment of the text change and hurts the performance of multimodal sentiment models directly.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN
However, both strategies are faced with some immediate problems: raw features cannot represent various properties of nodes (e. g., structure information), and representations learned by supervised GNN may suffer from the poor performance of the classifier on the poisoned graph.
CLCI-Net: Cross-Level fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke
To address these challenges, this paper proposes a Cross-Level fusion and Context Inference Network (CLCI-Net) for the chronic stroke lesion segmentation from T1-weighted MR images.
Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark
Most existing works on few-shot object detection (FSOD) focus on a setting where both pre-training and few-shot learning datasets are from a similar domain.
Interpretable Online Log Analysis Using Large Language Models with Prompt Strategies
LogPrompt employs large language models (LLMs) to perform online log analysis tasks via a suite of advanced prompt strategies tailored for log tasks, which enhances LLMs' performance by up to 380. 7% compared with simple prompts.
An Early Evaluation of GPT-4V(ision)
In this paper, we evaluate different abilities of GPT-4V including visual understanding, language understanding, visual puzzle solving, and understanding of other modalities such as depth, thermal, video, and audio.
A New Creative Generation Pipeline for Click-Through Rate with Stable Diffusion Model
2) Prompt model is designed to generate individualized creatives for different user groups, which can further improve the diversity and quality.
Normalization of Language Embeddings for Cross-Lingual Alignment
Learning a good transfer function to map the word vectors from two languages into a shared cross-lingual word vector space plays a crucial role in cross-lingual NLP.
Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task
We generate pseudo MQM data using parallel data from the WMT translation task.
The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning
Recent advances in deep learning have facilitated the demand of neural models for real applications.
Ranked #2 on
Sentiment Analysis
on MPQA
Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems
This paper presents the Delayed Propagation Transformer (DePT), a new transformer-based model that specializes in the global modeling of CPS while taking into account the immutable constraints from the physical world.
Patch-Wise Spatial-Temporal Quality Enhancement for HEVC Compressed Video
To overcome these limitations, we propose a patch-wise spatial-temporal quality enhancement network which firstly extracts spatial and temporal features, then recalibrates and fuses the obtained spatial and temporal features.
M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation
End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder.
Investigating Pre-trained Audio Encoders in the Low-Resource Condition
Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks.
Deep Ensemble Shape Calibration: Multi-Field Post-hoc Calibration in Online Advertising
Shape calibration is defined as no over- or under-estimation for each subset of the pCTR within the specified range under condition of concerned fields.
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints
To this end, we propose a plug-in algorithm for this line of work, i. e., Aligned Constrained Training (ACT), which alleviates this problem by familiarizing the model with the source-side context of the constraints.
Self-supervised Rewiring of Pre-trained Speech Encoders: Towards Faster Fine-tuning with Less Labels in Speech Processing
Pre-trained speech Transformers have facilitated great success across various speech processing tasks.
Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models
To translate well, machine translation (MT) systems and general-purposed language models (LMs) need a deep understanding of both source and target languages and cultures.
Multi-modal vision-language model for generalizable annotation-free pathological lesions localization and clinical diagnosis
Defining pathologies automatically from medical images aids the understanding of the emergence and progression of diseases, and such an ability is crucial in clinical diagnostics.
Collective Human Opinions in Semantic Textual Similarity
Despite the subjective nature of semantic textual similarity (STS) and pervasive disagreements in STS annotation, existing benchmarks have used averaged human ratings as the gold standard.
Zero-Annotation Object Detection with Web Knowledge Transfer
Object detection is one of the major problems in computer vision, and has been extensively studied.
Exploiting Web Images for Weakly Supervised Object Detection
Object detection without bounding box annotations, i. e, weakly supervised detection methods, are still lagging far behind.
Ranked #17 on
Weakly Supervised Object Detection
on PASCAL VOC 2012 test
(using extra training data)
MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information
As the proposed PI loss is convex and SGD compatible and the framework itself is a fully convolutional network, MIML-FCN+ can be easily integrated with state of-the-art deep learning networks.
Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations
Experimental results demonstrate the effectiveness of the proposed semantic descriptor and the usefulness of incorporating the structured semantic correlations.
Exploit Bounding Box Annotations for Multi-label Object Recognition
With strong labels, our framework is able to achieve state-of-the-art results in both datasets.
Ranked #16 on
Multi-Label Classification
on PASCAL VOC 2007
A Comparative Study of Object Trackers for Infrared Flying Bird Tracking
Bird strikes present a huge risk for aircraft, especially since traditional airport bird surveillance is mainly dependent on inefficient human observation.
A Parallel Way to Select the Parameters of SVM Based on the Ant Optimization Algorithm
A large number of experimental data shows that Support Vector Machine (SVM) algorithm has obvious advantages in text classification, handwriting recognition, image classification, bioinformatics, and some other fields.
An End-to-End Multi-task Learning Model for Fact Checking
With huge amount of information generated every day on the web, fact checking is an important and challenging task which can help people identify the authenticity of most claims as well as providing evidences selected from knowledge source like Wikipedia.
Efficient 3D Room Shape Recovery From a Single Panorama
We propose a method to recover the shape of a 3D room from a full-view indoor panorama.
Real-Time Steganalysis for Stream Media Based on Multi-channel Convolutional Sliding Windows
To solve these two challenges, in this paper, combined with the sliding window detection algorithm and Convolution Neural Network we propose a real-time VoIP steganalysis method which based on multi-channel convolution sliding windows.
Mask-Guided Portrait Editing with Conditional GANs
Portrait editing is a popular subject in photo manipulation.
Predicting Next-Season Designs on High Fashion Runway
Fashion is a large and fast-changing industry.
Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes
However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost.
motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks
Supervised machine learning tasks in networks such as node classification and link prediction require us to perform feature engineering that is known and agreed to be the key to success in applied machine learning.
Multi-Task Incremental Learning for Object Detection
For the difficult cases, where the domain gaps and especially category differences are large, we explore three different exemplar sampling methods and show the proposed adaptive sampling method is effective to select diverse and informative samples from entire datasets, to further prevent forgetting.
Feedback Graph Convolutional Network for Skeleton-based Action Recognition
It transmits the high-level semantic features to the low-level layers and flows temporal information stage by stage to progressively model global spatial-temporal features for action recognition; (3) The FGCN model provides early predictions.
Ranked #34 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study
While feasible, digital attacks have limited applicability in attacking deployed systems, including face recognition systems, where an adversary typically has access to the input and not the transmission channel.
Fashion Recommendation and Compatibility Prediction Using Relational Network
There are a few approaches that consider an entire outfit, but these approaches have limitations such as requiring rich semantic information, category labels, and fixed order of items.
Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation
The rapid proliferation of new users and items on the social web has aggravated the gray-sheep user/long-tail item challenge in recommender systems.
Category-Specific CNN for Visual-aware CTR Prediction at JD.com
Existing algorithms usually extract visual features using off-the-shelf Convolutional Neural Networks (CNNs) and late fuse the visual and non-visual features for the finally predicted CTR.
The HW-TSC Video Speech Translation System at IWSLT 2020
The paper presents details of our system in the IWSLT Video Speech Translation evaluation.
Edge Computing for Real-Time Near-Crash Detection for Smart Transportation Applications
It is among the first efforts in applying edge computing for real-time traffic video analytics and is expected to benefit multiple sub-fields in smart transportation research and applications.
A coarse-to-fine framework for unsupervised multi-contrast MR image deformable registration with dual consistency constraint
Multi-contrast magnetic resonance (MR) image registration is useful in the clinic to achieve fast and accurate imaging-based disease diagnosis and treatment planning.
On Position Embeddings in BERT
Various Position Embeddings (PEs) have been proposed in Transformer based architectures~(e. g. BERT) to model word order.
Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions
Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers.
Large-Scale Training System for 100-Million Classification at Alibaba
In the last decades, extreme classification has become an essential topic for deep learning.
Gaussian State-Based Quantum Illumination with Simple Photodetection
We use the continuous-variable Gaussian quantum information formalism to show that quantum illumination is better for object detection compared with coherent states of the same mean photon number, even for simple direct photodetection.
Object Detection
Quantum Physics
Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering
Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities.
Learning from Noisy Labels via Dynamic Loss Thresholding
During the training process, DLT records the loss value of each sample and calculates dynamic loss thresholds.
Task and Situation Structures for Service Agent Planning
Everyday tasks are characterized by their varieties and variations, and frequently are not clearly specified to service agents.
The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation
This paper describes our work in participation of the IWSLT-2021 offline speech translation task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection
Modeling inter-dependencies between time-series is the key to achieve high performance in anomaly detection for multivariate time-series data.
How Does Adversarial Fine-Tuning Benefit BERT?
Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning.
Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph
The structural information of Knowledge Bases (KBs) has proven effective to Question Answering (QA).
Adversarial Example Detection Using Latent Neighborhood Graph
We present the first graph-based adversarial detection method that constructs a Latent Neighborhood Graph (LNG) around an input example to determine if the input example is adversarial.
Few-shot graph link prediction with domain adaptation
In this work, we propose an adversarial training based modification to the current state-of-the-arts link prediction method to solve this problem.
HI-CMLM: Improve CMLM with Hybrid Decoder Input
Mask-predict CMLM (Ghazvininejad et al., 2019) has achieved stunning performance among non-autoregressive NMT models, but we find that the mechanism of predicting all of the target words only depending on the hidden state of [MASK] is not effective and efficient in initial iterations of refinement, resulting in ungrammatical repetitions and slow convergence.
Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation
Based on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT.
Efficient Transfer Learning for Quality Estimation with Bottleneck Adapter Layer
Compared with the commonly used NuQE baseline, BAL-QE achieves 47% (En-Ru) and 75% (En-De) of performance promotions.
Unified Humor Detection Based on Sentence-pair Augmentation and Transfer Learning
We propose a unified multilingual model for humor detection which can be trained under a transfer learning framework.
HW-TSC’s Participation in the WAT 2020 Indic Languages Multilingual Task
This paper describes our work in the WAT 2020 Indic Multilingual Translation Task.
HW-TSC’s Participation in the WMT 2020 News Translation Shared Task
We also conduct experiment with similar language augmentation, which lead to positive results, although not used in our submission.
HW-TSC’s Participation at WMT 2020 Automatic Post Editing Shared Task
The paper presents the submission by HW-TSC in the WMT 2020 Automatic Post Editing Shared Task.
Huawei’s Submissions to the WMT20 Biomedical Translation Task
This paper describes Huawei’s submissions to the WMT20 biomedical translation shared task.
HW-TSC’s Participation at WMT 2020 Quality Estimation Shared Task
This paper presents our work in the WMT 2020 Word and Sentence-Level Post-Editing Quality Estimation (QE) Shared Task.
How Length Prediction Influence the Performance of Non-Autoregressive Translation?
Length prediction is a special task in a series of NAT models where target length has to be determined before generation.
Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models
Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but it reaches the upper bound of translation quality when the number of encoder layers exceeds 18.
Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation
An effective training strategy to improve the performance of AT models is Self-Distillation Mixup (SDM) Training, which pre-trains a model on raw data, generates distilled data by the pre-trained model itself and finally re-trains a model on the combination of raw data and distilled data.
Diformer: Directional Transformer for Neural Machine Translation
In this paper, we aim to close the gap by preserving the original objective of AR and NAR under a unified framework.
Rethinking Feature Uncertainty in Stochastic Neural Networks for Adversarial Robustness
Extensive experiments on well-known white- and black-box attacks show that MFDV-SNN achieves a significant improvement over existing methods, which indicates that it is a simple but effective method to improve model robustness.
HW-TSC’s Participation in the WMT 2021 News Translation Shared Task
This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task.
HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task.
HW-TSC’s Participation in the WMT 2021 Large-Scale Multilingual Translation Task
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to the WMT 2021 Large-Scale Multilingual Translation Task.
HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to WMT 2021 Efficiency Shared Task.
HW-TSC’s Submissions to the WMT21 Biomedical Translation Task
This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC).
HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task.
Forecast-based Multi-aspect Framework for Multivariate Time-series Anomaly Detection
Today's cyber-world is vastly multivariate.
Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)
Few-shot relation learning refers to infer facts for relations with a limited number of observed triples.
The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation
For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation
The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022.
HW-TSC’s Participation in the IWSLT 2022 Isometric Spoken Language Translation
This paper presents our submissions to the IWSLT 2022 Isometric Spoken Language Translation task.
Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference
Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels due to its subjectivity.
Instance-wise Prompt Tuning for Pretrained Language Models
Prompt Learning has recently gained great popularity in bridging the gap between pretraining tasks and various downstream tasks.
Traffic-Twitter Transformer: A Nature Language Processing-joined Framework For Network-wide Traffic Forecasting
To better manage future roadway capacity and accommodate social and human impacts, it is crucial to propose a flexible and comprehensive framework to predict physical-aware long-term traffic conditions for public users and transportation agencies.
MACSA: A Multimodal Aspect-Category Sentiment Analysis Dataset with Multimodal Fine-grained Aligned Annotations
In this paper, we propose a new dataset, the Multimodal Aspect-Category Sentiment Analysis (MACSA) dataset, which contains more than 21K text-image pairs.
HW-TSC at SemEval-2022 Task 7: Ensemble Model Based on Pretrained Models for Identifying Plausible Clarifications
This paper describes the system for the identifying Plausible Clarifications of Implicit and Underspecified Phrases.
MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
Second, masked self-distillation is also consistent with vision-language contrastive from the perspective of training objective as both utilize the visual encoder for feature aligning, and thus is able to learn local semantics getting indirect supervision from the language.
ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers
Combined with a matching loss, it can effectively find objects that are similar to the input patch and complete the missing annotations.
Robot Task Planning and Situation Handling in Open Worlds
This paper introduces a novel algorithm (COWP) for open-world task planning and situation handling that dynamically augments the robot's action knowledge with task-oriented common sense.
数字人文视角下的《史记》《汉书》比较研究(A Comparative Study of Shiji and Hanshu from the Perspective of Digital Humanities)
"《史记》和《汉书》具有经久不衰的研究价值。尽管两书异同的研究已经较为丰富, 但研究的全面性、完备性、科学性、客观性均仍显不足。在数字人文的视角下, 本文利用计算语言学方法, 通过对字、词、命名实体、段落等的多粒度、多角度分析, 开展对于《史》《汉》的比较研究。首先, 本文对于《史》《汉》中的字、词、命名实体的分布和特点进行对比, 以遍历穷举的考察方式提炼出两书在主要内容上的相同点与不同点, 揭示了汉武帝之前和汉武帝到西汉灭亡两段历史时期在政治、文化、思想上的重要变革与承袭。其次, 本文使用一种融入命名实体作为外部特征的文本相似度算法对于《史记》《汉书》的异文进行自动发现, 成功识别出过去研究者通过人工手段没有发现的袭用段落, 使得我们对于《史》《汉》的承袭关系形成更加完整和立体的认识。再次, 本文通过计算异文段落之间的最长公共子序列来自动得出两段异文之间存在的差异, 从宏观统计上证明了《汉书》文字风格《史记》的差别, 并从微观上进一步对二者语言特点进行了阐释, 为理解《史》《汉》异文特点提供了新的角度和启发。本研究站在数字人文的视域下, 利用先进的计算方法对于传世千年的中国古代经典进行了再审视、再发现, 其方法对于今人研究古籍有一定的借鉴价值。”
HwTscSU’s Submissions on WAT 2022 Shared Task
In this paper we describe our submission to the shared tasks of the 9th Workshop on Asian Translation (WAT 2022) on NICT–SAP under the team name ”HwTscSU”.
RedApt: An Adaptor for wav2vec 2 Encoding \\ Faster and Smaller Speech Translation without Quality Compromise
Pre-trained speech Transformers in speech translation (ST) have facilitated state-of-the-art (SotA) results; yet, using such encoders is computationally expensive.
Towards Generating Adversarial Examples on Mixed-type Data
The existence of adversarial attacks (or adversarial examples) brings huge concern about the machine learning (ML) model's safety issues.
SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction
Graph neural networks have achieved significant success in representation learning.
Denoising Self-attentive Sequential Recommendation
Transformer-based sequential recommenders are very powerful for capturing both short-term and long-term sequential item dependencies.
TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systems
We found that our TinyKG with INT2 quantization aggressively reduces the memory footprint of activation maps with $7 \times$, only with $2\%$ loss in accuracy, allowing us to deploy KGNNs on memory-constrained devices.
P-Transformer: Towards Better Document-to-Document Neural Machine Translation
To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative position information in both self-attention and cross-attention.
FreeEnricher: Enriching Face Landmarks without Additional Cost
To evaluate our method, we manually label the dense landmarks on 300W testset.
Ranked #1 on
Face Alignment
on 300W
SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines
To this end, we propose SwiftAvatar, a novel avatar auto-creation framework that is evidently superior to previous works.
KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation.
A Meta-Learning Approach to Predicting Performance and Data Requirements
The PPL improves the performance estimation on average by 37% across 16 classification and 33% across 10 detection datasets, compared to the power law.
MGA: Medical generalist agent through text-guided knowledge transformation
To this end, we propose a novel medical generalist agent, MGA, that can address three kinds of common clinical tasks via clinical reports knowledge transformation.
ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-real Novel View Synthesis via Contrastive Learning
In this work, we first investigate the effects of synthetic data in synthetic-to-real novel view synthesis and surprisingly observe that models trained with synthetic data tend to produce sharper but less accurate volume densities.
Few-shot Class-incremental Learning for Cross-domain Disease Classification
The ability to incrementally learn new classes from limited samples is crucial to the development of artificial intelligence systems for real clinical application.
Context-aware Domain Adaptation for Time Series Anomaly Detection
We formulate context sampling into the Markov decision process and exploit deep reinforcement learning to optimize the time series domain adaptation process via context sampling and design a tailored reward function to generate domain-invariant features that better align two domains for anomaly detection.
Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts
We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Musketeer.
Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge
Unfortunately, obtaining the annotations needed to train machine learning models to identify and localize surgical tools is a difficult task.
Guided Recommendation for Model Fine-Tuning
With thousands of historical training jobs, a recommendation system can be learned to predict the model selection score given the features of the dataset and the model as input.
Imbalanced Aircraft Data Anomaly Detection
Anomaly detection in temporal data from sensors under aviation scenarios is a practical but challenging task: 1) long temporal data is difficult to extract contextual information with temporal correlation; 2) the anomalous data are rare in time series, causing normal/abnormal imbalance in anomaly detection, making the detector classification degenerate or even fail.
UNIMO-3: Multi-granularity Interaction for Vision-Language Representation Learning
The experimental results show that our model achieves state-of-the-art performance in various downstream tasks, and through ablation study can prove that effective cross-layer learning improves the model's ability of multimodal representation.
Text Style Transfer Back-Translation
To address this issue, we propose Text Style Transfer Back Translation (TST BT), which uses a style transfer model to modify the source side of BT data.
Knowledge-Prompted Estimator: A Novel Approach to Explainable Machine Translation Assessment
Cross-lingual Machine Translation (MT) quality estimation plays a crucial role in evaluating translation performance.
Knowledge-Driven Resource Allocation for D2D Networks: A WMMSE Unrolled Graph Neural Network Approach
This paper proposes an novel knowledge-driven approach for resource allocation in device-to-device (D2D) networks using a graph neural network (GNN) architecture.
Sharpness-Aware Graph Collaborative Filtering
Graph Neural Networks (GNNs) have achieved impressive performance in collaborative filtering.
LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network
In this paper, we propose, to the best of our knowledge, the first framework that introduces the contrastive language-image pre-training framework (CLIP) to accurately estimate the blur map from a DP pair unsupervisedly.
Flocking control against the malicious agent
This paper investigates the flocking control of a swarm with a malicious agent that falsifies its controller parameters to cause collision, division, and escape of agents in the swarm.
UAV 3-D path planning based on MOEA/D with adaptive areal weight adjustment
Unmanned aerial vehicles (UAVs) are desirable platforms for time-efficient and cost-effective task execution.
Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation
Despite their success, Transformer-based models often require the optimization of a large number of parameters, making them difficult to train from sparse data in sequential recommendation.
Adversarial Collaborative Filtering for Free
In this paper, we present Sharpness-aware Collaborative Filtering (SharpCF), a simple yet effective method that conducts adversarial training without extra computational cost over the base optimizer.
Tackling Diverse Minorities in Imbalanced Classification
Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers.
Hessian-aware Quantized Node Embeddings for Recommendation
To address the gradient mismatch problem in STE, we further consider the quantized errors and its second-order derivatives for better stability.
PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models
Personalized text-to-image generation has emerged as a powerful and sought-after tool, empowering users to create customized images based on their specific concepts and prompts.
Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning
Recently, multi-modal vision-language foundation models have gained significant attention in the medical field.
A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting
End-to-end automatic speech recognition (ASR) systems often struggle to recognize rare name entities, such as personal names, organizations, and terminologies not frequently encountered in the training data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Local and Global Logit Adjustments for Long-Tailed Learning
LGLA consists of two core components: a Class-aware Logit Adjustment (CLA) strategy and an Adaptive Angular Weighted (AAW) loss.
Data-driven Traffic Simulation: A Comprehensive Review
The primary objective of this paper is to review current research efforts and provide a futuristic perspective that will benefit future developments in the field.
INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion
WLAC predicts a target word given a source sentence, translation context, and a human typed character sequence.
Language-driven All-in-one Adverse Weather Removal
Then, with the guidance of degradation prior, we sparsely select restoration experts from a candidate list dynamically based on a Mixture-of-Experts (MoE) structure.
On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications
The advent of large language models (LLMs) has heightened interest in their potential for multimodal applications that integrate language and vision.
MLIP: Medical Language-Image Pre-training with Masked Local Representation Learning
Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs.
Enhancing Representation in Medical Vision-Language Foundation Models via Multi-Scale Information Extraction Techniques
The development of medical vision-language foundation models has attracted significant attention in the field of medicine and healthcare due to their promising prospect in various clinical applications.
Multimodal self-supervised learning for lesion localization
Multimodal deep learning utilizing imaging and diagnostic reports has made impressive progress in the field of medical imaging diagnostics, demonstrating a particularly strong capability for auxiliary diagnosis in cases where sufficient annotation information is lacking.
Can AI Write Classical Chinese Poetry like Humans? An Empirical Study Inspired by Turing Test
Some argue that the essence of humanity, such as creativity and sentiment, can never be mimicked by machines.
R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translation
Moreover, these strategies are more suitable for end-to-end systems than cascade systems.
UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction
Previous works usually adopt end-to-end models and has strong dependency on Pseudo Paired Data and Original Paired Data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Using Large Language Model for End-to-End Chinese ASR and NER
In this work, we connect the Whisper encoder with ChatGLM3 and provide in-depth comparisons of these two approaches using Chinese automatic speech recognition (ASR) and name entity recognition (NER) tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement
Particularly, raw radiology reports are refined to highlight the key information according to a constructed clinical dictionary and two model-optimized knowledge-enhancement metrics.
Consistency Enhancement-Based Deep Multiview Clustering via Contrastive Learning
Furthermore, the representation process for clustering is enhanced through spectral clustering, and the consistency across multiple views is improved.
Rethinking Personalized Federated Learning with Clustering-based Dynamic Graph Propagation
Subsequently, we design a precise personalized model distribution strategy to allow clients to obtain the most suitable model from the server side.
DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators
In this paper, we propose an alternative adaptation approach, named Decoding-enhanced Multi-phase Prompt Tuning (DeMPT), to make LLMs discriminately model and utilize the inter- and intra-sentence context and more effectively adapt LLMs to context-aware NMT.
A Novel Paradigm Boosting Translation Capabilities of Large Language Models
Experimental results conducted using the Llama2 model, particularly on Chinese-Llama2 after monolingual augmentation, demonstrate the improved translation capabilities of LLMs.
From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation
Machine Translation Quality Estimation (MTQE) is the task of estimating the quality of machine-translated text in real time without the need for reference translations, which is of great importance for the development of MT.
CHisIEC: An Information Extraction Corpus for Ancient Chinese History
Additionally, we have evaluated the capabilities of Large Language Models (LLMs) in the context of tasks related to ancient Chinese history.
Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and test data contamination.
Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy.
Mixed-Query Transformer: A Unified Image Segmentation Architecture
Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task.
OSR-ViT: A Simple and Modular Framework for Open-Set Object Detection and Discovery
Our method also excels in low-data settings, outperforming supervised baselines using a fraction of the training data.
Double Mixture: Towards Continual Event Detection from Speech
To address the challenges of catastrophic forgetting and effective disentanglement, we propose a novel method, 'Double Mixture.'
