Search Results for author:
Found 169 papers, 79 papers with code
Improving Conversational Recommendation Systems’ Quality with Context-Aware Item Meta-Information
In this paper, we propose a simple yet effective architecture comprising a pre-trained language model (PLM) and an item metadata encoder to integrate the recommendation and the dialog generation better.
The CRECIL Corpus: a New Dataset for Extraction of Relations between Characters in Chinese Multi-party Dialogues
We describe a new freely available Chinese multi-party dialogue dataset for automatic extraction of dialogue-based character relationships.
基于层次化语义框架的知识库属性映射方法(Property Mapping in Knowledge Base Under the Hierarchical Semantic Framework)
面向知识库的自动问答是自然语言处理的一项重要任务, 它旨在对用户提出的自然语言形式问题给出精炼、准确的回复。目前由于缺少数据集、特征不一致等因素, 导致难以使用通用的数据和方法实现领域知识库问答。因此, 本文将“问题意图”视作不同领域问答可能存在的共同特征, 将“问题”与三元组知识库中“关系谓词”的映射过程作为问答核心工作。为了考虑多种层次的语义避免重要信息的损失, 本文分别将“基于门控卷积的深层语义”和“基于交互注意力机制的浅层语义”两个方面通过门控感知机制相融合。我们在NLPCC-ICCPOL 2016 KBQA数据集上的实验表明, 本文提出的方法与现有的基于CDSSM和BDSSM相比, 效能有明显的提升。此外, 本文通过构造天文常识知识库, 将问题与关系谓词映射模型移植到特定领域, 结合Bi-LSTM-CRF模型构建了天文常识自动问答系统。
RiboDiffusion: Tertiary Structure-based RNA Inverse Folding with Generative Diffusion Models
A fundamental challenge is to find functional RNA sequences that satisfy given structural constraints, known as the inverse folding problem.
DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion
In this paper, we propose DeStein, a novel method that detoxififies LMs by altering their internal representations in the activation space with lower resource and time cost.
Enhancing Trust and Privacy in Distributed Networks: A Comprehensive Survey on Blockchain-based Federated Learning
While centralized servers pose a risk of being a single point of failure, decentralized approaches like blockchain offer a compelling solution by implementing a consensus mechanism among multiple entities.
MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation
Experimental results show that our framework outperforms existing open-ended text evaluation methods and achieves the highest correlation with human evaluation, which confirms the effectiveness and advancement of our framework in addressing the uncertainties and instabilities in evaluating LLMs-generated text.
HGT: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding
Table understanding (TU) has achieved promising advancements, but it faces the challenges of the scarcity of manually labeled tables and the presence of complex table structures. To address these challenges, we propose HGT, a framework with a heterogeneous graph (HG)-enhanced large language model (LLM) to tackle few-shot TU tasks. It leverages the LLM by aligning the table semantics with the LLM's parametric knowledge through soft prompts and instruction turning and deals with complex tables by a multi-task pre-training scheme involving three novel multi-granularity self-supervised HG pre-training objectives. We empirically demonstrate the effectiveness of HGT, showing that it outperforms the SOTA for few-shot complex TU on several benchmarks.
Compress3D: a Compressed Latent Space for 3D Generation from a Single Image
In this paper, we present a triplane autoencoder, which encodes 3D models into a compact triplane latent space to effectively compress both the 3D geometry and texture information.
DEE: Dual-stage Explainable Evaluation Method for Text Generation
Automatic methods for evaluating machine-generated texts hold significant importance due to the expanding applications of generative systems.
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
However, with the integration of additional modalities, MLLMs are exposed to new vulnerabilities, rendering them prone to structured-based jailbreak attacks, where semantic content (e. g., "harmful text") has been injected into the images to mislead MLLMs.
MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension
Large language models are playing an increasingly significant role in molecular research, yet existing models often generate erroneous information, posing challenges to accurate molecular comprehension.
A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism
As Large Language Models (LLMs) gain great success in real-world applications, an increasing number of users are seeking to develop and deploy their customized LLMs through cloud services.
Dual Graph Attention based Disentanglement Multiple Instance Learning for Brain Age Estimation
To overcome these limitations, we propose a Dual Graph Attention based Disentanglement Multi-instance Learning (DGA-DMIL) framework for improving brain age estimation.
RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
However, existing methods often struggle to capture environmental characteristics during the rendering process or produce adversarial textures that can precisely map to the target vehicle, resulting in suboptimal attack performance.
On the Expressive Power of a Variant of the Looped Transformer
Previous works try to explain this from the expressive power and capability perspectives that standard transformers are capable of performing some algorithms.
Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data
Table-to-Text Generation is a promising solution by facilitating the transformation of hybrid data into a uniformly text-formatted corpus.
Progress and Opportunities of Foundation Models in Bioinformatics
Central to our focus is the application of FMs to specific biological problems, aiming to guide the research community in choosing appropriate FMs for their research needs.
DefInt: A Default-interventionist Framework for Efficient Reasoning with Hybrid Large Language Models
Previous works like chain-of-thought (CoT) and tree-of-thoughts(ToT) have predominately focused on enhancing accuracy, but overlook the rapidly increasing token cost, which could be particularly problematic for open-ended real-world tasks with huge solution spaces.
GPAvatar: Generalizable and Precise Head Avatar from Image(s)
Head avatar reconstruction, crucial for applications in virtual reality, online meetings, gaming, and film industries, has garnered substantial attention within the computer vision community.
Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering
Central to our focus is the utilizing of language models and multimodal paradigms for medical question answering, aiming to guide the research community in selecting appropriate mechanisms for their specific medical research requirements.
DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
We propose DiffSHEG, a Diffusion-based approach for Speech-driven Holistic 3D Expression and Gesture generation with arbitrary length.
MEAOD: Model Extraction Attack against Object Detectors
The widespread use of deep learning technology across various industries has made deep neural network models highly valuable and, as a result, attractive targets for potential attackers.
Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion
Nonetheless, the performance of these methods is often constrained by the domain gap and looser constraints.
A Survey of Reasoning with Foundation Models
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation.
Unbiased organism-agnostic and highly sensitive signal peptide predictor with deep protein language model
Signal peptide (SP) is a short peptide located in the N-terminus of proteins.
A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing
This paper presents a video inversion approach for zero-shot video editing, which aims to model the input video with low-rank representation during the inversion process.
InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery
The rapid evolution of artificial intelligence in drug discovery encounters challenges with generalization and extensive training, yet Large Language Models (LLMs) offer promise in reshaping interactions with complex molecular data.
Ranked #20 on
Molecule Captioning
on ChEBI-20
CLiF-VQA: Enhancing Video Quality Assessment by Incorporating High-Level Semantic Information related to Human Feelings
In this paper, we propose CLiF-VQA, which considers both features related to human feelings and spatial features of videos.
On the Opportunities of Green Computing: A Survey
To tackle the challenges of computing resources and environmental impact of AI, Green Computing has become a hot research topic.
Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets
Furthermore, our in-depth analysis verifies that the advanced selection of review subsets and the two-stage training scheme are vital to boosting the summarization performance.
Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
Recent text-to-3D generation methods achieve impressive 3D content creation capacity thanks to the advances in image diffusion models and optimizing strategies.
Consistent123: Improve Consistency for One Image to 3D Object Synthesis
Large image diffusion models enable novel view synthesis with high quality and excellent zero-shot capability.
Curriculum-Driven Edubot: A Framework for Developing Language Learning Chatbots Through Synthesizing Conversational Data
Chatbots have become popular in educational settings, revolutionizing how students interact with material and how teachers teach.
Lyra: Orchestrating Dual Correction in Automated Theorem Proving
In addition, we introduce Conjecture Correction, an error feedback mechanism designed to interact with prover to refine formal proof conjectures with prover error messages.
Ranked #1 on
Automated Theorem Proving
on miniF2F-test
(Pass@100 metric)
Effective Whole-body Pose Estimation with Two-stages Distillation
Different from the previous self-knowledge distillation, this stage finetunes the student's head with only 20% training time as a plug-and-play training strategy.
Ranked #1 on
2D Human Pose Estimation
on COCO-WholeBody
(using extra training data)
MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions
Audio-driven portrait animation aims to synthesize portrait videos that are conditioned by given audio.
Audio-Driven 3D Facial Animation from In-the-Wild Videos
Consequently, their generalization capability remains limited.
Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation
The field of protein folding research has been greatly advanced by deep learning methods, with AlphaFold2 (AF2) demonstrating exceptional performance and atomic-level precision.
Progressive-Hint Prompting Improves Reasoning in Large Language Models
The performance of Large Language Models (LLMs) in reasoning tasks depends heavily on prompt design, with Chain-of-Thought (CoT) and self-consistency being critical methods that enhance this ability.
Ranked #2 on
Math Word Problem Solving
on SVAMP
User Adaptive Language Learning Chatbots with a Curriculum
Along with the development of systems for natural language understanding and generation, dialog systems have been widely adopted for language learning and practicing.
One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
It is challenging to perform this task with a single network due to resolution issues, i. e., the face and hands are usually located in extremely small regions.
Ranked #3 on
3D Human Pose Estimation
on UBody
FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation
This paper raises the new task of Fisheye Semantic Completion (FSC), where dense texture, structure, and semantics of a fisheye image are inferred even beyond the sensor field-of-view (FoV).
From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
We decompose the KD loss and find the non-target loss from it forces the student's non-target logits to match the teacher's, but the sum of the two non-target logits is different, preventing them from being identical.
Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding
We leverage the inherent properties of EG3D's latent space to design a discriminator and a background depth regularization.
Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family
ChatGPT is a powerful large language model (LLM) that covers knowledge resources such as Wikipedia and supports natural language question answering using its own knowledge.
Ranked #1 on
Knowledge Base Question Answering
on WebQuestionsSP
(Accuracy metric)
POSGen: Personalized Opening Sentence Generation for Online Insurance Sales
Such personalized opening sentence generation is challenging because (i) there are limited historical samples for conversation topic recommendation in online insurance sales and (ii) existing text generation schemes often fail to support customized topic ordering based on user preferences.
On Function-Coupled Watermarks for Deep Neural Networks
Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN providers implant secret information into the model so that they can later claim IP ownership by retrieving their embedded watermarks with some dedicated trigger inputs.
LipFormer: Learning to Lipread Unseen Speakers based on Visual-Landmark Transformers
However, generalizing these methods to unseen speakers incurs catastrophic performance degradation due to the limited number of speakers in training bank and the evident visual variations caused by the shape/color of lips for different speakers.
Drug Synergistic Combinations Predictions via Large-Scale Pre-Training and Graph Structure Learning
While previous methods reported fair performance, their models usually do not take advantage of multi-modal data and they are unable to handle new drugs or cell lines.
Learning Rain Location Prior for Nighttime Deraining
This learned prior contains location information of rain streaks and, when injected into deraining models, can significantly improve their performance.
L-CoIns: Language-Based Colorization With Instance Awareness
Language-based colorization produces plausible colors consistent with the language description provided by the user.
Accurate 3D Face Reconstruction with Facial Component Tokens
However, the current deep learning-based methods face significant challenges in achieving accurate reconstruction with disentangled facial parameters and ensuring temporal stability in single-frame methods for 3D face tracking on video data.
DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization
In this work, we propose DIONYSUS (dynamic input optimization in pre-training for dialogue summarization), a pre-trained encoder-decoder model for summarizing dialogues in any new domain.
DQnet: Cross-Model Detail Querying for Camouflaged Object Detection
Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue which inevitably leads to missing or redundant regions of objects.
An Empirical Study on the Efficacy of Deep Active Learning for Image Classification
Third, performing data selection in the SSAL setting can achieve a significant and consistent performance improvement, especially with abundant unlabeled data.
Learning Single Image Defocus Deblurring with Misaligned Training Pairs
First, in the deblurring module, a bi-directional optical flow-based deformation is introduced to tolerate spatial misalignment between deblurred and ground-truth images.
CT2: Colorization Transformer via Color Tokens
Automatic image colorization is an ill-posed problem with multi-modal uncertainty, and there remains two main challenges with previous methods: incorrect semantic colors and under-saturation.
Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems
Dialog systems are often designed or trained to output human-like responses.
Robust Human Matting via Semantic Guidance
Unlike previous works, our framework is data efficient, which requires a small amount of matting ground-truth to learn to estimate high quality object mattes.
GTAV-NightRain: Photometric Realistic Large-scale Dataset for Night-time Rain Streak Removal
In this paper, we propose GTAV-NightRain dataset, which is a large-scale synthetic night-time rain streak removal dataset.
ViTKD: Practical Guidelines for ViT feature knowledge distillation
In this paper, we explore the way of feature-based distillation for ViT.
Rethinking Knowledge Distillation via Cross-Entropy
Furthermore, we smooth students' target output to treat it as the soft target for training without teachers and propose a teacher-free new KD loss (tf-NKD).
Genome-wide nucleotide-resolution model of single-strand break site reveals species evolutionary hierarchy
Besides, SSBlazer is a lightweight model with robust cross-species generalization ability in the cross-species evaluation, which enables the large-scale genome-wide application in diverse species.
Deep Learning-enabled Spatial Phase Unwrapping for 3D Measurement
This system necessitates a robust spatial phase unwrapping (SPU) algorithm.
Using Chatbots to Teach Languages
This paper reports on progress towards building an online language learning tool to provide learners with conversational experience by using dialog systems as conversation practice partners.
A Multi-tasking Model of Speaker-Keyword Classification for Keeping Human in the Loop of Drone-assisted Inspection
A base model for a group of five authorized subjects is trained and tested on the inspection keyword dataset collected by this study.
E2Efold-3D: End-to-End Deep Learning Method for accurate de novo RNA 3D Structure Prediction
When E2Efold-3D is coupled with the experimental techniques, the RNA structure prediction field can be greatly advanced.
Do we really need temporal convolutions in action segmentation?
Most state-of-the-art methods focus on designing temporal convolution-based models, but the inflexibility of temporal convolutions and the difficulties in modeling long-term temporal dependencies restrict the potential of these models.
Ranked #1 on
Action Segmentation
on 50Salads
ProNet DB: A proteome-wise database for protein surface property representations and RNA-binding profiles
The rapid growth in the number of experimental and predicted protein structures and more complicated protein structures challenge users in computational biology for utilizing the structural information and protein surface property representation.
Learning Dual-Pixel Alignment for Defocus Deblurring
Generally, DPANet is an encoder-decoder with skip-connections, where two branches with shared parameters in the encoder are employed to extract and align deep features from left and right views, and one decoder is adopted to fuse aligned features for predicting the sharp image.
"Think Before You Speak": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs
Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses.
Temporally Efficient Vision Transformer for Video Instance Segmentation
To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeViT) for video instance segmentation (VIS).
Ranked #35 on
Video Instance Segmentation
on OVIS validation
Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions
Non-coding RNA structure and function are essential to understanding various biological processes, such as cell signaling, gene expression, and post-transcriptional regulations.
A physics and data co-driven surrogate modeling approach for temperature field prediction on irregular geometric domain
Second, a physics-driven CNN surrogate with partial differential equation (PDE) residuals as a loss function is utilized for fast meshing (meshing surrogate); then, we present a data-driven surrogate model based on the multi-level reduced-order method, aiming to learn solutions of temperature field in the above regular computational plane (thermal surrogate).
SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations
Unlike the original per grid cell object masks, SODAR is implicitly supervised to learn mask representations that encode geometric structure of nearby objects and complement adjacent representations with context.
What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
For legitimate inputs that are correctly inferred, the synthetic output tries to reconstruct the input.
Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval
In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly.
Active Learning for Open-set Annotation
To tackle this open-set annotation (OSA) problem, we propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation.
Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information
The encoder learns to map item metadata to embeddings that can reflect the semantic information in the dialog context.
Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation
To address these challenges, we present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation for knowledge-grounded dialogue generation tasks.
Contrastive Cycle Adversarial Autoencoders for Single-cell Multi-omics Alignment and Integration
Our approach can efficiently map the above data with high sparsity and noise from different spaces to a low-dimensional manifold in a unified space, making the downstream alignment and integration straightforward.
CLMB: deep contrastive learning for robust metagenomic binning
Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data.
HMD-AMP: Protein Language-Powered Hierarchical Multi-label Deep Forest for Annotating Antimicrobial Peptides
Identifying the targets of an antimicrobial peptide is a fundamental step in studying the innate immune response and combating antibiotic resistance, and more broadly, precision medicine and public health.
Multi-Class Anomaly Detection
However, we show that jointly using multiple one-class anomaly detectors to solve this problem yields poorer results as compared to training a single one-class anomaly detector on all normal object categories together.
Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations
Then we propose a hierarchical CB (HCB) algorithm to explore users' interest in the hierarchy tree.
Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval
In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly.
Orthogonal Graph Neural Networks
Graph neural networks (GNNs) have received tremendous attention due to their superiority in learning node representations.
FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks
In natural language processing (NLP), state-of-the-art (SOTA) semi-supervised learning (SSL) frameworks have shown great performance on deep pre-trained language models such as BERT, and are expected to significantly reduce the demand for manual labeling.
Crash Report Data Analysis for Creating Scenario-Wise, Spatio-Temporal Attention Guidance to Support Computer Vision-based Perception of Fatal Crash Risks
Then, exploratory analysis of location- and time-related variables of the crash report data suggests reducing fatal crashes to spatially defined groups.
Towards Vivid and Diverse Image Colorization with Generative Color Prior
Codes are available at https://github. com/ToTheBeginning/GCP-Colorization.
Spatial-Temporal Deep Intention Destination Networks for Online Travel Planning
Therefore, in this paper, we focus on predicting users' intention destinations in online travel platforms.
Information Bottleneck Approach to Spatial Attention Learning
Extensive experiments show that the proposed IB-inspired spatial attention mechanism can yield attention maps that neatly highlight the regions of interest while suppressing backgrounds, and bootstrap standard DNN structures for visual recognition tasks (e. g., image classification, fine-grained recognition, cross-domain classification).
LHRM: A LBS based Heterogeneous Relations Model for User Cold Start Recommendation in Online Travel Platform
To alleviate this problem, existing user cold start methods either apply deep learning to build a cross-domain recommender system or map user attributes into the space of user behaviour.
Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents
It confirms that the Grad-CAM chosen by this study can generate high-quality, human-interpretable saliency maps (with 1. 23 Normalized Scanpath Saliency) for explaining the crash anticipation decision.
Protein-RNA interaction prediction with deep learning: Structure matters
Protein-RNA interactions are of vital importance to a variety of cellular activities.
Tracking Instances as Queries
Recently, query based deep networks catch lots of attention owing to their end-to-end pipeline and competitive results on several fundamental computer vision tasks, such as object detection, semantic segmentation, and instance segmentation.
Learning Temporal Consistency for Low Light Video Enhancement From Single Images
Based on this idea, we propose our method which can infer motion prior for single image low light video enhancement and enforce temporal consistency.
A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents
Visual cues for predicting a future accident are embedded deeply in dashcam video data.
Ranked #1 on
Accident Anticipation
on CCD
A system of vision sensor based deep neural networks for complex driving scene analysis in support of crash risk assessment and prevention
The paper further evaluates the performance of the Multi-Net and the efficiency of the developed system.
The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity
Humans are increasingly interacting with machines through language, sometimes in contexts where the user may not know they are talking to a machine (like over the phone or a text chatbot).
Towards Emotional Support Dialog Systems
Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats.
TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks
To be specific, we first build a similarity graph on test instances and training samples, and we conduct graph-based semi-supervised learning to extract contextual features.
AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions.
Instances as Queries
The key insight of QueryInst is to leverage the intrinsic one-to-one correspondence in object queries across different stages, as well as one-to-one correspondence between mask RoI features and object queries in the same stage.
Ranked #13 on
Object Detection
on COCO-O
(using extra training data)
LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing
We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk.
MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
Consequently, we propose a novel learning-based solution to model such contradictions for AE detection.
DEUX: An Attribute-Guided Framework for Sociable Recommendation Dialog Systems
It is important for sociable recommendation dialog systems to perform as both on-task content and social content to engage users and gain their favor.
Crossover Learning for Fast Online Video Instance Segmentation
For temporal information modeling in VIS, we present a novel crossover learning scheme that uses the instance feature in the current frame to pixel-wisely localize the same instance in other frames.
Ranked #34 on
Video Instance Segmentation
on OVIS validation
Beyond Categorical Label Representations for Image Classification
Our experiments reveal that high dimensional, high entropy labels achieve comparable accuracy to text (categorical) labels on the standard image classification task, but features learned through our label representations exhibit more robustness under various adversarial attacks and better effectiveness with a limited amount of training data.
CLiMP: A Benchmark for Chinese Language Model Evaluation
CLiMP consists of sets of 1, 000 minimal pairs (MPs) for 16 syntactic contrasts in Mandarin, covering 9 major Mandarin linguistic phenomena.
Effects of spin orbit coupling in superconducting proximity devices -- application to $\mathrm{CoSi_2 / TiSi_2}$ heterostructures
Motivated by the recent findings of unconventional superconductivity in $\mathrm{CoSi_2 / TiSi_2}$ heterostructures, we study the effect of interface induced Rashba spin orbit coupling on the conductance of a three terminal ``T" shape superconducting device.
Superconductivity Mesoscale and Nanoscale Physics
Towards Real-World Blind Face Restoration with Generative Facial Prior
Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details.
Ranked #2 on
Blind Face Restoration
on CelebA-Test
Refine and Imitate: Reducing Repetition and Inconsistency in Dialogue Generation via Reinforcement Learning and Human Demonstration
Despite the recent success of large-scale language models on various downstream NLP tasks, the repetition and inconsistency problems still persist in dialogue response generation.
AggMask: Exploring locally aggregated learning of mask representations for instance segmentation
Recently proposed one-stage instance segmentation models (\emph{e. g.}, SOLO) learn to directly predict location-specific object mask with fully-convolutional networks.
A Framework For Differentiable Discovery Of Graph Algorithms
Recently there is a surge of interests in using graph neural networks (GNNs) to learn algorithms.
Exploring Balanced Feature Spaces for Representation Learning
Motivated by this question, we conduct a series of studies on the performance of self-supervised contrastive learning and supervised learning methods over multiple datasets where training instance distributions vary from a balanced one to a long-tailed one.
Ranked #40 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration
Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.
Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance
To be specific, the reflection layer is firstly estimated due to that it generally is much simpler and is relatively easier to estimate.
Interactive Key-Value Memory-augmented Attention for Image Paragraph Captioning
In this paper, we propose an Interactive key-value Memory- augmented Attention model for image Paragraph captioning (IMAP) to keep track of the attention history (salient objects coverage information) along with the update-chain of the decoder state and therefore avoid generating repetitive or incomplete image descriptions.
Gunrock 2.0: A User Adaptive Social Conversational System
Gunrock 2. 0 is built on top of Gunrock with an emphasis on user adaptation.
A Multi-Persona Chatbot for Hotline Counselor Training
Suicide prevention hotline counselors aid individuals during difficult times through millions of calls and chats.
A Simple Yet Effective Method for Video Temporal Grounding with Cross-Modality Attention
The task of language-guided video temporal grounding is to localize the particular video clip corresponding to a query sentence in an untrimmed video.
DeepDyve: Dynamic Verification for Deep Neural Networks
The key to enabling such lightweight checking is that the smaller neural network only needs to produce approximate results for the initial task without sacrificing fault coverage much.
Dual Semantic Fusion Network for Video Object Detection
Video object detection is a tough task due to the deteriorated quality of video sequences captured under complex environments.
Towards Structured Prediction in Bioinformatics with Deep Learning
However, in addition to the standard classification or regression problems, in bioinformatics, we often need to predict more complex structured targets, such as 2D images and 3D molecular structures.
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals.
Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.
Learning to Stop While Learning to Predict
Similar to algorithms, the optimal depth of a deep architecture may be different for different input instances, either to avoid ``over-thinking'', or because we want to compute less for operations converged already.
Realistic Large-Scale Fine-Depth Dehazing Dataset from 3D Videos
We select a large number of high-quality frames of real outdoor scenes and render haze on them using depth from stereo.
RNA Secondary Structure Prediction By Learning Unrolled Algorithms
The key idea of E2Efold is to directly predict the RNA base-pairing matrix, and use an unrolled algorithm for constrained programming as the template for deep architectures to enforce constraints.
Fast Video Object Segmentation using the Global Context Module
Therefore, it uses constant memory regardless of the video length and costs substantially less memory and computation.
Asymmetric GAN for Unpaired Image-to-image Translation
While in situations where two domains are asymmetric in complexity, i. e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity.
Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test
DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution.
End-to-End Trainable Non-Collaborative Dialog System
End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task.
On Functional Test Generation for Deep Neural Network IPs
Considering the large amount of training data and know-how required to generate the network, it is more practical to use third-party DNN intellectual property (IP) cores for many designs.
Unsupervised Learning for Intrinsic Image Decomposition from a Single Image
Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene.
Accurate Trajectory Prediction for Autonomous Vehicles
Predicting vehicle trajectories, angle and speed is important for safe and comfortable driving.
Classification Calibration for Long-tail Instance Segmentation
In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals.
Winning the ICCV 2019 Learning to Drive Challenge
Autonomous driving has a significant impact on society.
Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models
Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks.
Multi-sensor cloud and cloud shadow segmentation with a convolutional neural network
The rule-based Fmask method takes significantly longer (277. 8 s/megapixel) and produces results with an accuracy of 0. 75, Kappa of 0. 60 and Dice coefficient of 0. 72.
Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset
Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark.
Ranked #1 on
Low-Light Image Enhancement
on 3DMatch Benchmark
(using extra training data)
Semantic Guided Single Image Reflection Removal
Reflection is common in images capturing scenes behind a glass window, which is not only a disturbance visually but also influence the performance of other computer vision algorithms.
Hyperspectral City V1.0 Dataset and Benchmark
This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark.
Computer-aided Detection of Squamous Carcinoma of the Cervix in Whole Slide Images
Traditionally, the most indispensable diagnosis of cervix squamous carcinoma is histopathological assessment which is achieved under microscope by pathologist.
Image-based reconstruction for the impact problems by using DPNNs
Therefore, in this study, an improved ReConNN method is proposed to address the mentioned weaknesses.
Deep learning in bioinformatics: introduction, application, and perspective in big data era
Deep learning, which is especially formidable in handling big data, has achieved great success in various fields, including bioinformatics.
On Configurable Defense against Adversarial Example Attacks
Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications.
Sample-Efficient Policy Learning based on Completely Behavior Cloning
Direct policy search is one of the most important algorithm of reinforcement learning.
Style Separation and Synthesis via Generative Adversarial Networks
The S3-GAN consists of an encoder network, a generator network, and an adversarial network.
Image-Based Reconstruction for a 3D-PFHS Heat Transfer Problem by ReConNN
Therefore, an image-based reconstruction model of a heat transfer process for a 3D-PFHS is established.
Fast and accurate algorithms for the computation of spherically symmetric nonlocal diffusion operators on lattices
We present a unified treatment of the Fourier spectra of spherically symmetric nonlocal diffusion operators.
Numerical Analysis 33C20, 41A20
PromID: human promoter prediction by deep learning
In this work we further develop our deep learning approach that was relatively successful to discriminate short promoter and non-promoter sequences.
Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks
However, depth estimation is a dense prediction problem and low-resolution feature maps usually generate blurred depth map which is undesirable in application.
On the Decision Boundary of Deep Neural Networks
We demonstrate, both theoretically and empirically, that the last weight layer of a neural network converges to a linear SVM trained on the output of the last hidden layer, for both the binary case and the multi-class case with the commonly used cross-entropy loss.
Clause Vivification by Unit Propagation in CDCL SAT Solvers
Original and learnt clauses in Conflict-Driven Clause Learning (CDCL) SAT solvers often contain redundant literals.
SupportNet: solving catastrophic forgetting in class incremental learning with support data
A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting.
Webpage Saliency Prediction with Two-stage Generative Adversarial Networks
Web page saliency prediction is a challenge problem in image transformation and computer vision.
DLBI: Deep learning guided Bayesian inference for structure reconstruction of super-resolution fluorescence microscopy
Our method combines the strength of deep learning and statistical inference, where deep learning captures the underlying distribution of the fluorophores that are consistent with the observed time-series fluorescent images by exploring local features and correlation along time-axis, and statistical inference further refines the ultrastructure extracted by deep learning and endues physical meaning to the final image.
Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method
In such a framework, a reconstruction neural network (ReConNN) model designed for simulation-based physical field's reconstruction is proposed.
I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators
Deep learning has become the de-facto computational paradigm for various kinds of perception problems, including many privacy-sensitive applications such as online medical image analysis.
Can CNN Construct Highly Accurate Models Efficiently for High-Dimensional Problems in Complex Product Designs?
In order to evaluate the proposed CNN metamodel for hundreds-dimensional and strong nonlinear problems, CNN is compared with other metamodeling techniques.
LIME: Low-light Image Enhancement via Illumination Map Estimation
When one captures images in low-light conditions, the images often suffer from low visibility.
Ranked #1 on
Low-Light Image Enhancement
on 10 Monkey Species
(using extra training data)
Haze Visibility Enhancement: A Survey and Quantitative Benchmarking
This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes.
Rain Streak Removal Using Layer Priors
This paper addresses the problem of rain streak removal from a single image.
Nighttime Haze Removal With Glow and Multiple Light Colors
We demonstrate the effectiveness of our nighttime haze model and correction method on a number of examples and compare our results with existing daytime and nighttime dehazing methods' results.
SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs
However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint.
Single Image Layer Separation using Relative Smoothness
This problem arises most notably in intrinsic image decomposition and reflection interference removal.
