Search Results for author:
Found 86 papers, 22 papers with code
Is Domain Adaptation Worth Your Investment? Comparing BERT and FinBERT on Financial Tasks
With the recent rise in popularity of Transformer models in Natural Language Processing, research efforts have been dedicated to the development of domain-adapted versions of BERT-like architectures.
ROCLING-2021 Shared Task: Dimensional Sentiment Analysis for Educational Texts
This paper presents the ROCLING 2021 shared task on dimensional sentiment analysis for educational texts which seeks to identify a real-value sentiment score of self-evaluation comments written by Chinese students in the both valence and arousal dimensions.
Discovering Financial Hypernyms by Prompting Masked Language Models
With the rising popularity of Transformer-based language models, several studies have tried to exploit their masked language modeling capabilities to automatically extract relational linguistic knowledge, although this kind of research has rarely investigated semantic relations in specialized domains.
Multilateral Temporal-view Pyramid Transformer for Video Inpainting Detection
The task of video inpainting detection is to expose the pixel-level inpainted regions within a video sequence.
Feature selection in linear SVMs via hard cardinality constraint: a scalable SDP decomposition approach
In this paper, we study the embedded feature selection problem in linear Support Vector Machines (SVMs), in which a cardinality constraint is employed, leading to a fully explainable selection model.
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts
We verify the effectiveness of the proposed explanations from two aspects: (1) Counterfactual Trace Visualization: the enhanced forgery images are useful to reveal artifacts by visually contrasting the original images and two different visualization methods; (2) Transferable Adversarial Attacks: the adversarial forgery images generated by attacking the detection model are able to mislead other detection models, implying the removed artifacts are general.
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture.
NeRF2Points: Large-Scale Point Cloud Generation From Street Views' Radiance Field Optimization
Neural Radiance Fields (NeRF) have emerged as a paradigm-shifting methodology for the photorealistic rendering of objects and environments, enabling the synthesis of novel viewpoints with remarkable fidelity.
Derivative-free tree optimization for complex systems
Our method demonstrates wide applicability to a wide range of real-world complex systems spanning materials, physics, and biology, considerably outperforming state-of-the-art algorithms.
Artifact Feature Purification for Cross-domain Detection of AI-generated Images
We also find that the artifact features APN focuses on across generators and scenes are global and diverse.
ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
Extensive experiments across OOD detection benchmarks empirically demonstrate that our proposed \textsc{ConjNorm} has established a new state-of-the-art in a variety of OOD detection setups, outperforming the current best method by up to 13. 25$\%$ and 28. 19$\%$ (FPR95) on CIFAR-100 and ImageNet-1K, respectively.
eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data
Both the ECInstruct dataset and the eCeLLM models show great potential in empowering versatile and effective LLMs for e-commerce.
Quantum error mitigation and correction mediated by Yang-Baxter equation and artificial neural network
The manuscript introduces the basics of quantum error sources and explores the potential of using classical computation for error mitigation.
Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR
Recently, there has been increasing concern about the vulnerability of deep neural network (DNN)-based synthetic aperture radar (SAR) automatic target recognition (ATR) to adversarial attacks, where a DNN could be easily deceived by clean input with imperceptible but aggressive perturbations.
URHand: Universal Relightable Hands
To simplify the personalization process while retaining photorealism, we build a powerful universal relightable prior based on neural relighting from multi-view images of hands captured in a light stage with hundreds of identities.
AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis
Audio-driven talking head synthesis is a promising topic with wide applications in digital human, film making and virtual reality.
Learning Dense Correspondence for NeRF-Based Face Reenactment
Therefore, we are inspired to ask: Can we learn the dense correspondence between different NeRF-based face representations without a 3D parametric model prior?
RS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion Models
Extensive empirical evaluations demonstrate that the introduced \themodel effectively corrects the racial stereotypes of the well-trained Stable Diffusion model while leaving the original model unchanged.
Modeling Sequences as Star Graphs to Address Over-smoothing in Self-attentive Sequential Recommendation
As widely demonstrated in the literature, this issue could lead to a loss of information in individual items, and significantly degrade models' scalability and performance.
Modeling Path Importance for Effective Alzheimer's Disease Drug Repurposing
Thus, leveraging learned embeddings allows MPI to effectively differentiate the importance among paths.
DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing
Based on DeltaSpace, we propose a novel framework called DeltaEdit, which maps the CLIP visual feature differences to the latent space directions of a generative model during the training phase, and predicts the latent space directions from the CLIP textual feature differences during the inference phase.
ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation
In this work, we introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text, by leveraging the power of off-the-shelf text-to-image generation methods (e. g., Stable Diffusion).
Towards Efficient and Effective Adaptation of Large Language Models for Sequential Recommendation
In addition, SSNA adapts the top-a layers of LLMs jointly, and integrates adapters sequentially for enhanced effectiveness (i. e., recommendation performance).
Weakly Supervised Semantic Segmentation by Knowledge Graph Inference
Extensive experimentation on both the multi-label classification and segmentation network stages underscores the effectiveness of the proposed graph reasoning approach for advancing WSSS.
USL-Net: Uncertainty Self-Learning Network for Unsupervised Skin Lesion Segmentation
Rather than risk potential pseudo-labeling errors or learning confusion by forcefully classifying these regions, we consider them as uncertainty regions, exempting them from pseudo-labeling and allowing the network to self-learn.
Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms
Recently, advancements in deep learning-based superpixel segmentation methods have brought about improvements in both the efficiency and the performance of segmentation.
Multi-modality Meets Re-learning: Mitigating Negative Transfer in Sequential Recommendation
Our experimental results demonstrate that ANT does not suffer from the negative transfer issue on any of the target tasks.
How to Evaluate Semantic Communications for Images with ViTScore Metric?
Experimental results demonstrate that ViTScore can better evaluate the image semantic similarity than the other 3 typical metrics, which indicates that ViTScore is an effective performance metric when deployed in SC scenarios.
DFGC-VRA: DeepFake Game Competition on Visual Realism Assessment
This paper presents the summary report on the DeepFake Game Competition on Visual Realism Assessment (DFGCVRA).
Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Models
Ligand-based drug design aims to identify novel drug candidates of similar shapes with known active molecules.
InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer
InfoStyler formulates the disentanglement representation learning as an information compression problem by eliminating style statistics from the content image and removing the content structure from the style image.
3D-Aware Adversarial Makeup Generation for Facial Privacy Protection
The privacy and security of face data on social media are facing unprecedented challenges as it is vulnerable to unauthorized access and identification.
RWKV: Reinventing RNNs for the Transformer Era
This work presents a significant step towards reconciling trade-offs between computational efficiency and model performance in sequence processing tasks.
Ranked #22 on
Natural Language Inference
on WNLI
Collaborative Feature Learning for Fine-grained Facial Forgery Detection and Segmentation
An important topic in manipulation detection is the localization of the fake regions.
Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition
The proposed method contributes a mixed clutter variants generation strategy and a new inference branch equipped with channel-weighted mean square error (CWMSE) loss for invariant representation learning.
IntrinsicNGP: Intrinsic Coordinate based Hash Encoding for Human NeRF
To achieve this target, we introduce a continuous and optimizable intrinsic coordinate rather than the original explicit Euclidean coordinate in the hash encoding module of instant-NGP.
Designing a 3D-Aware StyleNeRF Encoder for Face Editing
For more flexible face manipulation, we then design a dual-branch StyleFlow module to transfer the StyleNeRF codes with disentangled geometry and texture flows.
Visual Realism Assessment for Face-swap Videos
Visual realism assessment, or VRA, is essential for assessing the potential impact that may be brought by a specific face-swap video, and it is also important as a quality assessment metric to compare different face-swap methods.
Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization
To this end, we detach a sharpness term from the loss which reflects the impact of quantization noise.
SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video
Extensive experimental results on several different datasets demonstrate the effectiveness and efficiency of SelfNeRF to challenging monocular videos.
Recursive Attentive Methods with Reused Item Representations for Sequential Recommendation
Our run-time performance comparison signifies that RAM could also be more efficient on benchmark datasets.
Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense
Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers).
DFGC 2022: The Second DeepFake Game Competition
There is a two-party game between DeepFake creators and defenders.
MultiEarth 2022 -- The Champion Solution for the Matrix Completion Challenge via Multimodal Regression and Generation
Earth observation satellites have been continuously monitoring the earth environment for years at different locations and spectral bands with different modalities.
MultiEarth 2022 -- The Champion Solution for Image-to-Image Translation Challenge via Generation Models
The MultiEarth 2022 Image-to-Image Translation challenge provides a well-constrained test bed for generating the corresponding RGB Sentinel-2 imagery with the given Sentinel-1 VV & VH imagery.
Prospective Preference Enhanced Mixed Attentive Model for Session-based Recommendation
In this manuscript, we develop prospective preference enhanced mixed attentive model (P2MAM) to generate session-based recommendations using two important factors: temporal patterns and estimates of users' prospective preferences.
Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models
These fine-grained adversarial examples can be used for selecting robust backbone networks and auxiliary features.
UWC: Unit-wise Calibration Towards Rapid Network Compression
This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance.
Deep Stereo Image Compression via Bi-Directional Coding
Existing learning-based stereo compression methods usually adopt a unidirectional approach to encoding one image independently and the other image conditioned upon the first.
HeadNeRF: A Real-time NeRF-based Parametric Head Model
Different from existing related parametric models, we use the neural radiance fields as a novel 3D proxy instead of the traditional 3D textured mesh, which makes that HeadNeRF is able to generate high fidelity images.
Multi-View Stereo with Transformer
It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable matching for MVS.
Novel View Synthesis from a Single Image via Unsupervised learning
In particular, the network consists of a token transformation module (TTM) that facilities the transformation of the features extracted from a source viewpoint image into an intrinsic representation with respect to a pre-defined reference pose and a view generation module (VGM) that synthesizes an arbitrary view from the representation.
DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis
To evaluate the effectiveness and show the general use of our method, we conduct a set of experiments on makeup transfer and semantic image synthesis.
TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models
Each error is hence manually labeled with comprehensive annotations, including the span of the error, the associated span, minimal correction to the error, the type of the error, and rationale behind the error.
DFGC 2021: A DeepFake Game Competition
This competition provides a common platform for benchmarking the adversarial game between current state-of-the-art DeepFake creation and detection methods.
Robust Face-Swap Detection Based on 3D Facial Shape Information
Maliciously-manipulated images or videos - so-called deep fakes - especially face-swap images and videos have attracted more and more malicious attackers to discredit some key figures.
SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer
Since human faces are symmetrical in the UV space, we can conveniently remove the undesired shadow and occlusion from the reference image by carefully designing a Flip Attention Module (FAM).
Optical neural network architecture for deep learning with the temporal synthetic dimension
The physical concept of synthetic dimensions has recently been introduced into optics.
Optics
Variational quantum solver employing the PDS energy functional
Recently a new class of quantum algorithms that are based on the quantum computation of the connected moment expansion has been reported to find the ground and excited state energies.
Quantum Physics
Topological holographic quench dynamics in a synthetic dimension
The notion of topological phases extended to dynamical systems stimulates extensive studies, of which the characterization of non-equilibrium topological invariants is a central issue and usually necessitates the information of quantum dynamics in both the time and spatial dimensions.
Quantum Physics Optics
The Arecibo Ultra-Deep Survey
The mass range of detected galaxies is $\log(M_{\rm HI}~[h_{70}^{-2}{\rm M}_\odot]) = 6. 32 - 10. 76$.
Astrophysics of Galaxies
MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
To deal with this problem, we propose a novel multi-level statistics transfer model, which disentangles and transfers multi-level appearance features from person images and merges them with pose features to reconstruct the source person images themselves.
Rank Position Forecasting in Car Racing
Forecasting is challenging since uncertainty resulted from exogenous factors exists.
Hybrid Collaborative Filtering Models for Clinical Search Recommendation
With increasing and extensive use of electronic health records, clinicians are often under time pressure when they need to retrieve important information efficiently among large amounts of patients' health records in clinics.
Learning Pose-invariant 3D Object Reconstruction from Single-view Images
Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data.
M2: Mixed Models with Preferences, Popularities and Transitions for Next-Basket Recommendation
We compared M2 with different combinations of the factors with 5 state-of-the-art next-basket recommendation methods on 4 public benchmark datasets in recommending the first, second and third next basket.
Co-occurrence Background Model with Superpixels for Robust Background Initialization
Background initialization is an important step in many high-level applications of video processing, ranging from video surveillance to video inpainting. However, this process is often affected by practical challenges such as illumination changes, background motion, camera jitter and intermittent movement, etc. In this paper, we develop a co-occurrence background model with superpixel segmentation for robust background initialization.
HAM: Hybrid Associations Models for Sequential Recommendation
We compared HAM models with the most recent, state-of-the-art methods on six public benchmark datasets in three different experimental settings.
Cognitive Biomarker Prioritization in Alzheimer's Disease using Brain Morphometric Data
This method learns the latent scoring function that pushes the most effective cognitive assessments onto the top of the prioritization list.
A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems
However, the fact is, the state of an instance is changed according to the decision that the model made at different construction steps, and the node features should be updated correspondingly.
Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
The new types of generated images are emerging one after another, and the existing detection methods cannot cope well.
CNN-based Dual-Chain Models for Knowledge Graph Learning
We also present an extension of this model, which incorporates descriptions of entities and learns a second set of entity embeddings from the descriptions.
Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval
How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR.
Comprehensive Video Understanding: Video summarization with content-based video recommender design
In this paper, we formulate video summarization as a content-based recommender problem, which should distill the most useful content from a long video for users who suffer from information overload.
Point Clouds Learning with Attention-based Graph Convolution Networks
In addition, we introduce an additional global graph structure network to compensate for the relative information of the individual points in the graph structure network.
Q# and NWChem: Tools for Scalable Quantum Chemistry on Quantum Computers
Fault-tolerant quantum computation promises to solve outstanding problems in quantum chemistry within the next decade.
Quantum Physics Emerging Technologies Chemical Physics Computational Physics
On the generalization of GAN image forensics
Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect.
A deep Convolutional Neural Network for topology optimization with strong generalization ability
The performance of the proposed method was evaluated by comparing its efficiency and accuracy with SIMP on a series of typical optimization problems.
iQIYI-VID: A Large Dataset for Multi-modal Person Identification
Multi-modal person identification is a more promising way that we can jointly utilize face, head, body, audio features, and so on.
A Blended Deep Learning Approach for Predicting User Intended Actions
In this work, we focus on pre- dicting attrition, which is one of typical user intended actions.
Person Re-Identification by Semantic Region Representation and Topology Constraint
In this paper, we propose a novel person re-identification method, which consists of a reliable representation called Semantic Region Representation (SRR), and an effective metric learning with Mapping Space Topology Constraint (MSTC).
Extreme Network Compression via Filter Group Approximation
In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation.
YNU-HPCC at SemEval-2018 Task 3: Ensemble Neural Network Models for Irony Detection on Twitter
This paper describe the system we proposed to participate the first year of Irony detection in English tweets competition.
Chinese Grammatical Error Diagnosis Using Single Word Embedding
A computer-assisted learning tool which can automatically detect and correct Chinese grammatical errors is necessary for those foreign students.
A Tabu Search/Path Relinking Algorithm to Solve the Job Shop Scheduling Problem
We present an algorithm that incorporates a tabu search procedure into the framework of path relinking to tackle the job shop scheduling problem (JSP).
Data Structures and Algorithms
