Search Results for author:
Found 96 papers, 49 papers with code
Great~Truths~are ~Always ~Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
Commonsense reasoning in natural language is a desired ability of artificial intelligent systems.
Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network
In this paper, we study how to continually pre-train language models for improving the understanding of math problems.
Improving Conversational Recommendation Systems via Counterfactual Data Simulation
To develop our approach, we characterize user preference and organize the conversation flow by the entities involved in the dialogue, and design a multi-stage recommendation dialogue simulator based on a conversation flow language model.
Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning
Based on this finding, we propose a new approach that can deliberate the reasoning steps with tool interfaces, namely \textbf{DELI}.
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
To improve the reasoning abilities, we propose \textbf{ChatCoT}, a tool-augmented chain-of-thought reasoning framework for chat-based LLMs.
Evaluating Object Hallucination in Large Vision-Language Models
Despite the promising progress on LVLMs, we find that LVLMs suffer from the hallucination problem, i. e. they tend to generate objects that are inconsistent with the target images in the descriptions.
StructGPT: A General Framework for Large Language Model to Reason over Structured Data
Specially, we propose an \emph{invoking-linearization-generation} procedure to support LLMs in reasoning on the structured data with the help of the external interfaces.
Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation
To solve it, we propose Diffusion-NAT, which introduces discrete diffusion models~(DDM) into NAR text-to-text generation and integrates BART to improve the performance.
A Survey of Large Language Models
To discriminate the difference in parameter scale, the research community has coined the term large language models (LLM) for the PLMs of significant size.
NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
Neural radiance fields (NeRF) show great success in novel view synthesis.
Diffusion Models for Non-autoregressive Text Generation: A Survey
In this survey, we review the recent progress in diffusion models for NAR text generation.
A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance
We propose a unified structured light, consisting of an LED array and an LCD mask, for high-quality acquisition of both shape and reflectance from a single view.
Visually-augmented pretrained language models for NLP tasks without images
Although pre-trained language models~(PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense.
MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers
Dense retrieval aims to map queries and passages into low-dimensional vector space for efficient similarity measuring, showing promising effectiveness in various large-scale retrieval tasks.
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
To achieve high-quality results with low computational cost, we present a novel pixel spread model (PSM) that iteratively employs decoupled probabilistic modeling, combining the optimization efficiency of GANs with the prediction tractability of probabilistic models.
UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph
Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question on a large-scale Knowledge Graph (KG).
Mutual Guidance and Residual Integration for Image Enhancement
To address those issues, we propose a novel mutual guidance network (MGN) to perform effective bidirectional global-local information exchange while keeping a compact architecture.
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.
Mixed Emotion Modelling for Emotional Voice Conversion
Each attribute measures the degree of the relevance between the speech recordings belonging to different emotion types.
SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval
Thus, we propose a simple ambiguous negatives sampling method, SimANS, which incorporates a new sampling probability distribution to sample more ambiguous negatives.
Speech Synthesis with Mixed Emotions
We then incorporate our formulation into a sequence-to-sequence emotional text-to-speech framework.
Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning
Our approach unifies the recommendation and conversation subtasks into the prompt learning paradigm, and utilizes knowledge-enhanced prompts based on a fixed pre-trained language model (PLM) to fulfill both subtasks in a unified approach.
Ranked #1 on
Text Generation
on ReDial
JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding
Considering the complex nature of mathematical texts, we design a novel curriculum pre-training approach for improving the learning of mathematical PLMs, consisting of both basic and advanced courses.
NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations
To improve the efficiency of a traditional hair growth algorithm, we adopt a local neural implicit function to grow strands based on the estimated 3D hair geometric features.
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
Commonsense reasoning in natural language is a desired ability of artificial intelligent systems.
Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks
We present a learning algorithm that uses bone-driven motion networks to predict the deformation of loose-fitting garment meshes at interactive rates.
Debiased Contrastive Learning of Unsupervised Sentence Representations
In DCLR, we design an instance weighting method to punish false negatives and generate noise-based negatives to guarantee the uniformity of the representation space.
Efficient Reflectance Capture with a Deep Gated Mixture-of-Experts
A common, pre-trained latent transform module is also appended to each decoder, to offset the burden of the increased number of decoders.
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem.
Ranked #1 on
Image Inpainting
on CelebA-HQ
NeuralReshaper: Single-image Human-body Retouching with Deep Neural Networks
In this paper, we present NeuralReshaper, a novel method for semantic reshaping of human bodies in single images using deep generative networks.
Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation
Without the bells and whistles, our plug-and-play TCL is capable of improving the performance of existing VFI frameworks.
Ranked #1 on
Video Frame Interpolation
on Vimeo90K
DiFT: Differentiable Differential Feature Transform for Multi-View Stereo
We present a novel framework to automatically learn to transform the differential cues from a stack of images densely captured with a rotational motion into spatially discriminative and view-invariant per-pixel features at each view.
Filter-enhanced MLP is All You Need for Sequential Recommendation
Recently, deep neural networks such as RNN, CNN and Transformer have been applied in the task of sequential recommendation, which aims to capture the dynamic preference characteristics from logged user behavior data for accurate recommendation.
Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction
However, as source images are often misaligned due to the large disparities among the camera settings, strong assumptions have been made in the past with respect to the camera(s) or/and the object in interest, limiting the application of such techniques.
Emotion Intensity and its Control for Emotional Voice Conversion
As desired, the proposed network controls the fine-grained emotion intensity in the output speech.
C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System
To implement this framework, we design both coarse-grained and fine-grained procedures for modeling user preference, where the former focuses on more general, coarse-grained semantic fusion and the latter focuses on more specific, fine-grained semantic fusion.
Ranked #1 on
Recommendation Systems
on ReDial
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic.
Learning Implicit Body Representations from Double Diffusion Based Neural Radiance Fields
In this paper, we present a novel double diffusion based neural radiance field, dubbed DD-NeRF, to reconstruct human body geometry and render the human body appearance in novel views from a sparse set of images.
Revisiting Temporal Alignment for Video Restoration
Long-range temporal alignment is critical yet challenging for video restoration tasks.
Ranked #1 on
Video Super-Resolution
on Vimeo-90K
Disentanglement of Emotional Style and Speaker Identity for Expressive Voice Conversion
Expressive voice conversion performs identity conversion for emotional speakers by jointly converting speaker identity and emotional style.
Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models
To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs.
Unsupervised Image Generation with Infinite Generative Adversarial Networks
Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision.
Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals
The final response is selected according to the predicted knowledge, the goal to achieve, and the context.
Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Traditional voice conversion(VC) has been focused on speaker identity conversion for speech with a neutral expression.
Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation
Due to the flexibility in modelling data heterogeneity, heterogeneous information network (HIN) has been adopted to characterize complex and heterogeneous auxiliary data in top-$N$ recommender systems, called \emph{HIN-based recommendation}.
Emotional Voice Conversion: Theory, Databases and ESD
In this paper, we first provide a review of the state-of-the-art emotional voice conversion research, and the existing emotional speech databases.
LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond
Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version.
Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training
In stage 2, we perform emotion training with a limited amount of emotional speech data, to learn how to disentangle emotional style and linguistic information from the speech.
Best-Buddy GANs for Highly Detailed Image Super-Resolution
We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input.
Learning Efficient Photometric Feature Transform for Multi-view Stereo
We present a novel framework to learn to convert the perpixel photometric information at each view into spatially distinctive and view-invariant low-level features, which can be plugged into existing multi-view stereo pipeline for enhanced 3D reconstruction.
BERT4SO: Neural Sentence Ordering by Fine-tuning BERT
Sentence ordering aims to arrange the sentences of a given text in the correct order.
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
In this paper, we examine the robustness of state-of-the-art action recognizers against adversarial attack, which has been rarely investigated so far.
BASAR:Black-box Attack on Skeletal Action Recognition
The robustness of skeleton-based activity recognizers has been questioned recently, which shows that they are vulnerable to adversarial attacks when the full-knowledge of the recognizer is accessible to the attacker.
High-order Differentiable Autoencoder for Nonlinear Model Reduction
This paper provides a new avenue for exploiting deep neural networks to improve physics-based simulation.
In-game Residential Home Planning via Visual Context-aware Global Relation Learning
In this paper, we propose an effective global relation learning algorithm to recommend an appropriate location of a building unit for in-game customization of residential home complex.
One-shot Face Reenactment Using Appearance Adaptive Normalization
The paper proposes a novel generative adversarial network for one-shot face reenactment, which can animate a single face image to a different pose-and-expression (provided by a driving image) while keeping its original appearance.
Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
In this paper we tackle the problem of pose guided person image generation, which aims to transfer a person image from the source pose to a novel target pose while maintaining the source appearance.
Neural Sentence Ordering Based on Constraint Graphs
Our experiments on five benchmark datasets show that our method outperforms all the existing baselines significantly, achieving a new state-of-the-art performance.
Content Selection Network for Document-grounded Retrieval-based Chatbots
It is thus crucial to select the part of document content relevant to the current conversation context.
CRSLab: An Open-Source Toolkit for Building Conversational Recommender System
In recent years, conversational recommender system (CRS) has received much attention in the research community.
Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension
Weakly supervised machine reading comprehension (MRC) task is practical and promising for its easily available and massive training data, but inevitablely introduces noise.
VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech
Emotional voice conversion (EVC) aims to convert the emotion of speech from one state to another while preserving the linguistic content and speaker identity.
Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset
Emotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity.
Towards Topic-Guided Conversational Recommender System
To develop an effective CRS, the support of high-quality datasets is essential.
Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.
Second-order Neural Network Training Using Complex-step Directional Derivative
We believe our method will inspire a wide-range of new algorithms for deep learning and numerical optimization.
Dynamic Future Net: Diversified Human Motion Generation
We evaluate our model on a wide range of motions and compare it with the state-of-the-art methods.
Leveraging Historical Interaction Data for Improving Conversational Recommender System
Most of the existing CRS methods focus on learning effective preference representations for users from conversation data alone.
Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks
In this paper, we introduce a method for one-shot face reenactment, which uses the reconstructed 3D meshes (i. e., the source mesh and driving mesh) as guidance to learn the optical flow needed for the reenacted face synthesis.
S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization
To tackle this problem, we propose the model S^3-Rec, which stands for Self-Supervised learning for Sequential Recommendation, based on the self-attentive neural architecture.
Spectrum and Prosody Conversion for Cross-lingual Voice Conversion with CycleGAN
It relies on non-parallel training data from two different languages, hence, is more challenging than mono-lingual voice conversion.
VAW-GAN for Singing Voice Conversion with Non-parallel Training Data
We train an encoder to disentangle singer identity and singing prosody (F0 contour) from phonetic content.
Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations.
Ranked #3 on
Text Generation
on ReDial
AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph
We base our work on the assumption that most human-made objects are constituted by parts and these parts can be well represented by generalized primitives.
Converting Anyone's Emotion: Towards Speaker-Independent Emotional Voice Conversion
We consider that there is a common code between speakers for emotional expression in a spoken language, therefore, a speaker-independent mapping between emotional states is possible.
Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks
In this paper, we introduce a method to reconstruct 3D facial shapes with high-fidelity textures from single-view images in-the-wild, without the need to capture a large-scale face texture database.
HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation
Estimating 3D human pose from a single image is a challenging task.
SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks
We introduce SketchGNN, a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches.
Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting
Open-domain retrieval-based dialogue systems require a considerable amount of training data to learn their parameters.
Transforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data
Many studies require parallel speech data between different emotional patterns, which is not practical in real life.
EmbedMask: Embedding Coupling for One-stage Instance Segmentation
The pixel-level clustering enables EmbedMask to generate high-resolution masks without missing details from repooling, and the existence of proposal embedding simplifies and strengthens the clustering procedure to achieve high speed with higher performance than segmentation-based methods.
Ranked #84 on
Instance Segmentation
on COCO test-dev
SMART: Skeletal Motion Action Recognition aTtack
In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions.
HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation
Estimating 3D human pose from a single image is a challenging task.
Ranked #1 on
Monocular 3D Human Pose Estimation
on Human3.6M
(Use Video Sequence metric, using extra
training data)
Unsupervised Context Rewriting for Open Domain Conversation
Context modeling has a pivotal role in open domain conversation.
DeepSketchHair: Deep Sketch-based 3D Hair Modeling
The key enablers of our system are two carefully designed neural networks, namely, S2ONet, which converts an input sketch to a dense 2D hair orientation field; and O2VNet, which maps the 2D orientation field to a 3D vector field.
Graphics
Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image.
CaricatureShop: Personalized and Photorealistic Caricature Sketching
To construct the mapping between 2D sketches and a vertex-wise scaling field, a novel deep learning architecture is developed.
FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
Although significant advances have been made in the area of human poses estimation from images using deep Convolutional Neural Network (ConvNet), it remains a big challenge to perform 3D pose inference in-the-wild.
Ranked #193 on
3D Human Pose Estimation
on Human3.6M
DeepWarp: DNN-based Nonlinear Deformation
DeepWarp is an efficient and highly re-usable deep neural network (DNN) based nonlinear deformable simulation framework.
Graphics
Radiometric Calibration From Faces in Images
We present a method for radiometric calibration of cameras from a single image that contains a human face.
Specular Highlight Removal in Facial Images
An important practical feature of the proposed method is that the skin color model is utilized in a way that does not require color calibration of the camera.
Intrinsic Light Field Images
We present a method to automatically decompose a light field into its intrinsic shading and albedo components.
Segmentation Rectification for Video Cutout via One-Class Structured Learning
Comprehensive experiments on both RGB and RGB-D data demonstrate that our simple and effective method significantly outperforms the segmentation propagation methods adopted in the state-of-the-art video cutout systems, and the results also suggest the potential usefulness of our method in image cutout system.
A Geodesic-Preserving Method for Image Warping
The image projections will turn the straight lines into curved "geodesic lines", and it is fundamentally impossible to keep all these lines straight.
Simulating Makeup Through Physics-Based Manipulation of Intrinsic Image Layers
We present a method for simulating makeup in a face image.
Bayesian Depth-from-Defocus with Shading Constraints
We present a method that enhances the performance of depth-from-defocus (DFD) through the use of shading information.
