Search Results for author:
Found 82 papers, 40 papers with code
TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
The 3D position encoding guided by the epipolar field provides an efficient way of encoding correspondences between pixels of different views.
Equivariant Neural Network for Factor Graphs
Several indices used in a factor graph data structure can be permuted without changing the underlying probability distribution.
On the Difficulty of Segmenting Words with Attention
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks.
Multi-Sample based Contrastive Loss for Top-k Recommendation
Therefore, we propose a Multi-Sample based Contrastive Loss (MSCL) function which solves the two problems by balancing the importance of positive and negative samples and data augmentation.
Layout-to-Image Translation with Double Pooling Generative Adversarial Networks
In this paper, we address the task of layout-to-image translation, which aims to translate an input semantic layout to a realistic image.
Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
With the strength of deep generative models, 3D pose transfer regains intensive research interests in recent years.
Recurrent Mask Refinement for Few-Shot Medical Image Segmentation
Although having achieved great success in medical image segmentation, deep convolutional neural networks usually require a large dataset with manual annotations for training and are difficult to generalize to unseen classes.
Cross-View Exocentric to Egocentric Video Synthesis
Particularly, we propose a novel Bi-directional Spatial Temporal Attention Fusion Generative Adversarial Network (STA-GAN) to learn both spatial and temporal information to generate egocentric video sequences from the exocentric view.
Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
To overcome this limitation, we propose a Wide-Context Network (WiCoNet) for the semantic segmentation of HR RSIs.
Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes
Both generators are mutually connected and trained in an end-to-end fashion and explicitly form three cycled subnets, i. e., one image generation cycle and two guidance generation cycles.
Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
Controllable person image generation aims to produce realistic human images with desirable attributes (e. g., the given pose, cloth textures or hair style).
Transformer-Based Source-Free Domain Adaptation
In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation.
Cloth Interactive Transformer for Virtual Try-On
2D image-based virtual try-on has attracted increased attention from the multimedia and computer vision communities.
Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction
While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution operation.
Ranked #3 on
Depth Estimation
on NYU-Depth V2
Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images
To address this issue, we propose an adversarial shape learning network (ASLNet) to model the building shape patterns that improve the accuracy of building segmentation.
Semantically-Adaptive Upsampling for Layout-to-Image Translation
We propose the Semantically-Adaptive UpSampling (SA-UpSample), a general and highly effective upsampling method for the layout-to-image translation task.
Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
State-of-the-art CNN segmentation models apply either 2D or 3D convolutions on input images, with pros and cons associated with each method: 2D convolution is fast, less memory-intensive but inadequate for extracting 3D contextual information from volumetric images, while the opposite is true for 3D convolution.
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs
Current graph neural networks (GNNs) lack generalizability with respect to scales (graph sizes, graph diameters, edge weights, etc..) when solving many graph analysis problems.
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
We study how to learn a policy with compositional generalizability.
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
Current graph neural networks (GNNs) lack generalizability with respect to scales (graph sizes, graph diameters, edge weights, etc..) when solving many graph analysis problems.
Dual Attention GANs for Semantic Image Synthesis
We also propose two novel modules, i. e., position-wise Spatial Attention Module (SAM) and scale-wise Channel Attention Module (CAM), to capture semantic structure attention in spatial and channel dimensions, respectively.
Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention
Recent works have shown that attention mechanism is beneficial to the fusion process.
DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis
Synthesizing high-quality realistic images from text descriptions is a challenging task.
Ranked #1 on
Text-to-Image Generation
on CUB
Bipartite Graph Reasoning GANs for Person Image Generation
We present a novel Bipartite Graph Reasoning GAN (BiGraphGAN) for the challenging person image generation task.
Ranked #1 on
Pose Transfer
on Deep-Fashion
Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
In this paper we address the problem of unsupervised gaze correction in the wild, presenting a solution that works without the need for precise annotations of the gaze angle and the head pose.
Quantum Computation for Pricing the Collateralized Debt Obligations
Collateralized debt obligation (CDO) has been one of the most commonly used structured financial products and is intensively studied in quantitative finance.
Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
This is even more laborious when generating images with very different views.
XingGAN for Person Image Generation
We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i. e., translating the pose of a given person to a desired one.
Ranked #1 on
Pose Transfer
on Deep-Fashion
AMR Parsing with Latent Structural Information
Abstract Meaning Representations (AMRs) capture sentence-level semantics structural representations to broad-coverage natural sentences.
Belief Propagation Neural Networks
Learned neural solvers have successfully been used to solve combinatorial optimization and decision problems.
Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification
The idea is to allow the dependency graph to guide the representation learning of the transformer encoder and vice versa.
When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data
Then the activated dictionary atoms are assembled and passed to the compound dictionary learning and coding layers.
Relevant Region Prediction for Crowd Counting
The module builds a fully connected directed graph between the regions of different density where each node (region) is represented by weighted global pooled feature, and GCN is learned to map this region graph to a set of relation-aware regions representations.
Vector-Quantized Autoregressive Predictive Coding
Autoregressive Predictive Coding (APC), as a self-supervised objective, has enjoyed success in learning representations from large amounts of unlabeled data, and the learned representations are rich for many downstream tasks.
Edge Guided GANs with Semantic Preserving for Semantic Image Synthesis
To tackle the first challenge, we propose to use the edge as an intermediate representation which is further adopted to guide image generation via a proposed attention guided edge transfer module.
Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network
In this paper, we investigate exocentric (third-person) view to egocentric (first-person) view image generation.
Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation
In the first stage, the input image and the conditional semantic guidance are fed into a cycled semantic-guided generation network to produce initial coarse results.
AttentionAnatomy: A unified framework for whole-body organs at risk segmentation using multiple partially annotated datasets
Organs-at-risk (OAR) delineation in computed tomography (CT) is an important step in Radiation Therapy (RT) planning.
Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
To tackle this issue, in this work we consider learning the scene generation in a local context, and correspondingly design a local class-specific generative network with semantic maps as a guidance, which separately constructs and learns sub-generators concentrating on the generation of different classes, and is able to provide more scene details.
Asymmetric Generative Adversarial Networks for Image-to-Image Translation
In this paper, we analyze the limitation of the existing symmetric GAN models in asymmetric translation tasks, and propose an AsymmetricGAN model with both translation and reconstruction generators of unequal sizes and different parameter-sharing strategy to adapt to the asymmetric need in both unsupervised and supervised image-to-image translation tasks.
Unified Generative Adversarial Networks for Controllable Image-to-Image Translation
The proposed model consists of a single generator and a discriminator taking a conditional image and the target controllable structure as input.
Ranked #1 on
Cross-View Image-to-Image Translation
on Dayton (64x64) - ground-to-aerial
(LPIPS metric)
Facial Expression Translation
Gesture-to-Gesture Translation
+2
AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks
State-of-the-art methods in image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data.
Ranked #1 on
Facial Expression Translation
on AR Face
Improving Semantic Segmentation of Aerial Images Using Patch-based Attention
High-level features extracted from the late layers of a neural network are rich in semantic information, yet have blurred spatial details; low-level features extracted from the early layers of a network contain more pixel-level information, but are isolated and noisy.
Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
In this work, we propose a novel Cycle In Cycle Generative Adversarial Network (C$^2$GAN) for the task of keypoint-guided image generation.
NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation
Pulmonary nodule detection, false positive reduction and segmentation represent three of the most common tasks in the computeraided analysis of chest CT images.
Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation
However, in machine learning, this cross-modal learning is a nontrivial task because different modalities have no homogeneous properties.
Relating Simple Sentence Representations in Deep Neural Networks and the Brain
To the best of our knowledge, this is the first work showing that the MEG brain recording when reading a word in a sentence can be used to distinguish earlier words in the sentence.
GazeCorrection:Self-Guided Eye Manipulation in the wild using Self-Supervised Generative Adversarial Networks
Gaze correction aims to redirect the person's gaze into the camera by manipulating the eye region, and it can be considered as a specific image resynthesis problem.
Expression Conditional GAN for Facial Expression-to-Expression Translation
In this paper, we focus on the facial expression translation task and propose a novel Expression Conditional GAN (ECGAN) which can learn the mapping from one image domain to another one based on an additional expression attribute.
Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker verification (TD-SV).
Structured Discriminative Tensor Dictionary Learning for Unsupervised Domain Adaptation
However, the number of labeled source samples are always limited due to expensive annotation cost in practice, making sub-optimal performance been observed.
Joint Learning of Self-Representation and Indicator for Multi-View Image Clustering
Multi-view subspace clustering aims to divide a set of multisource data into several groups according to their underlying subspace structure.
Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation
In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes it possible to generate images of natural scenes in arbitrary viewpoints, based on an image of the scene and a novel semantic map.
Ranked #1 on
Cross-View Image-to-Image Translation
on Ego2Top
Bird View Synthesis
Cross-View Image-to-Image Translation
+1
VoiceID Loss: Speech Enhancement for Speaker Verification
In this paper, we propose VoiceID loss, a novel loss function for training a speech enhancement model to improve the robustness of speaker verification.
An Unsupervised Autoregressive Model for Speech Representation Learning
This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations.
Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation
To handle the limitation, in this paper we propose a novel Attention-Guided Generative Adversarial Network (AGGAN), which can detect the most discriminative semantic object and minimize changes of unwanted part for semantic manipulation problems without using extra data and models.
Ranked #1 on
Facial Expression Translation
on AR Face
Automated pulmonary nodule detection using 3D deep convolutional neural networks
Finally, we introduce a method to ensemble models from both stages via consensus to give the final predictions.
Automatic Pulmonary Lobe Segmentation Using Deep Learning
To validate the robustness and performance of our proposed framework trained with a small number of training examples, we further tested our model on CT scans from an independent dataset.
An End-to-end Framework For Integrated Pulmonary Nodule Detection and False Positive Reduction
Most of the existing deep learning nodule detection systems are constructed in two steps: a) nodule candidates screening and b) false positive reduction, using two different models trained separately.
Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling
Gatherings of thousands to millions of people frequently occur for an enormous variety of events, and automated counting of these high-density crowds is useful for safety, management, and measuring significance of an event.
Attribute-Guided Sketch Generation
To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end-to-end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation.
Fast and Robust Dynamic Hand Gesture Recognition via Key Frames Extraction and Feature Fusion
Gesture recognition is a hot topic in computer vision and pattern recognition, which plays a vitally important role in natural human-computer interface.
Ranked #1 on
Hand Gesture Recognition
on Cambridge
Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
State-of-the-art methods for image-to-image translation with Generative Adversarial Networks (GANs) can learn a mapping from one domain to another domain using unpaired image data.
Generalizing semi-supervised generative adversarial networks to regression using feature contrasting
We first demonstrate the capabilities of semi-supervised regression GANs on a toy dataset which allows for a detailed understanding of how they operate in various circumstances.
On The Inductive Bias of Words in Acoustics-to-Word Models
In addition, we study three types of inductive bias, leveraging a pronunciation dictionary, word boundary annotations, and constraints on word durations.
Frame-level speaker embeddings for text-independent speaker recognition and analysis of end-to-end model
In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition model for extracting robust speaker embeddings.
Deep Micro-Dictionary Learning and Coding Network
In this paper, we propose a novel Deep Micro-Dictionary Learning and Coding Network (DDLCN).
Integrated Server for Measurement-Device-Independent Quantum Key Distribution Network
Quantum key distribution (QKD), harnessing quantum physics and optoelectronics, may promise unconditionally secure information exchange in theory.
Quantum Physics
GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
Therefore, this task requires a high-level understanding of the mapping between the input source gesture and the output target gesture.
Ranked #1 on
Gesture-to-Gesture Translation
on NTU Hand Digit
On Training Recurrent Networks with Truncated Backpropagation Through Time in Speech Recognition
In this paper, we study recurrent networks' ability to learn long-term dependency in the context of speech recognition.
Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognition
However, it is relatively inexpensive to collect large amounts of unlabeled data from domains that we want the models to generalize to.
A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition
Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute.
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks.
Sequence Prediction with Neural Segmental Models
We explore end-to-end training for segmental models with various loss functions, and show how end-to-end training with marginal log loss can eliminate the need for detailed manual alignments.
End-to-End Neural Segmental Models for Speech Recognition
Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at a time.
Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition
We hypothesize that using intermediate representations as auxiliary supervision at lower levels of deep networks may be a good way of combining the advantages of end-to-end training and more traditional pipeline approaches.
End-to-End Training Approaches for Discriminative Segmental Models
Similarly to hybrid HMM-neural network models, segmental models of this class can be trained in two stages (frame classifier training followed by linear segmental model weight training), end to end (joint training of both frame classifier and linear weights), or with end-to-end fine-tuning after two-stage training.
Lexicon-Free Fingerspelling Recognition from Video: Data, Models, and Signer Adaptation
Recognizing fingerspelling is challenging for a number of reasons: It involves quick, small motions that are often highly coarticulated; it exhibits significant variation between signers; and there has been a dearth of continuous fingerspelling data collected.
Efficient Segmental Cascades for Speech Recognition
Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition.
Signer-independent Fingerspelling Recognition with Deep Neural Network Adaptation
Previous work has shown that it is possible to achieve almost 90% accuracies on fingerspelling recognition in a signer-dependent setting.
Discriminative Segmental Cascades for Feature-Rich Phone Recognition
A typical solution is to use approximate decoding, either by beam pruning in a single pass or by beam pruning to generate a lattice followed by a second pass.
