Search Results for author:
Found 74 papers, 20 papers with code
Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis
On top of these, a bi-reference attention mechanism is used to align both local-scale reference style embedding sequence and local-scale context style embedding sequence with corresponding phoneme embedding sequence.
Content Adaptive Latents and Decoder for Neural Image Compression
Although several content adaptive methods have been proposed by updating the encoder-side components, the adaptability of both latents and the decoder is not well exploited.
Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization
Weakly supervised temporal action localization (WTAL) aims to localize actions in untrimmed videos with only weak supervision information (e. g. video-level labels).
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline
We also propose a new 3D VQA framework to effectively predict the completely visually grounded and explainable answer.
Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation
In addition to previous methods that seek correspondences by hand-crafted or learnt geometric features, recent point cloud registration methods have tried to apply RGB-D data to achieve more accurate correspondence.
SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling
Reconstructing a 3D shape based on a single sketch image is challenging due to the large domain gap between a sparse, irregular sketch and a regular, dense 3D shape.
Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction
The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H. 264/H. 265 for both motion and residual compression.
Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound
Benefited from this new perspective, we first propose a new deep semi-supervised learning framework called Semi-supervised Learning by Empirical Distribution Alignment (SLEDA), in which existing technologies from the domain adaptation community can be readily used to address the semi-supervised learning problem through reducing the empirical distribution distance between labeled and unlabeled data.
3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
Observing that the 3D captioning task and the 3D grounding task contain both shared and complementary information in nature, in this work, we propose a unified framework to jointly solve these two distinct but closely related tasks in a synergistic fashion, which consists of both shared task-agnostic modules and lightweight task-specific modules.
LSVC: A Learning-Based Stereo Video Compression Framework
In this work, we propose the first end-to-end optimized framework for compressing automotive stereo videos (i. e., stereo videos from autonomous driving applications) from both left and right views.
Learning Based Multi-Modality Image and Video Compression
Specifically, given the image in the reference modality (e. g., the infrared image), we use the channel-wise alignment module to produce the aligned features based on the affine transform.
EndHiC: assemble large contigs into chromosomal-level scaffolds using the Hi-C links from contig ends
As the Hi-C links of two adjacent contigs concentrate only at the neighbor ends of the contigs, larger contig size will reduce the power to differentiate adjacent (signal) and non-adjacent (noise) contig linkages, leading to a higher rate of mis-assembly.
SRDAN: Scale-Aware and Range-Aware Domain Adaptation Network for Cross-Dataset 3D Object Detection
In this work, we propose a new cross-dataset 3D object detection method named Scale-aware and Range-aware Domain Adaptation Network (SRDAN).
NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning
In this paper, a novel second-order method called NG+ is proposed.
CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network
Furthermore, to achieve variable bitrate decoding with one single decoder, we propose a bitrate adaptive module to project the representation from a base bitrate to the expected representation at a target bitrate for transmission.
FVC: A New Framework towards Deep Video Compression in Feature Space
In this work, we propose a feature-space video coding network (FVC) by performing all major operations (i. e., motion estimation, motion compression, motion compensation and residual compression) in the feature space.
VoxelContext-Net: An Octree based Framework for Point Cloud Compression
In this paper, we propose a two-stage deep learning framework called VoxelContext-Net for both static and dynamic point cloud compression.
Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
Inspired by the back-tracing strategy in the conventional Hough voting methods, in this work, we introduce a new 3D object detection method, named as Back-tracing Representative Points Network (BRNet), which generatively back-traces the representative points from the vote centers and also revisits complementary seed points around these generated points, so as to better capture the fine local structural features surrounding the potential objects from the raw point clouds.
Ranked #9 on
3D Object Detection
on SUN-RGBD val
VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation
On the other hand, we also design an effective distribution alignment method to reduce the distribution divergence between the virtual domain and the target domain by gradually improving the compactness of the target domain distribution through model learning.
Salient Object Detection via Integrity Learning
We define the concept of integrity at both a micro and macro level.
StyleFormer: Real-Time Arbitrary Style Transfer via Parametric Style Composition
In this work, we propose a new feed-forward arbitrary style transfer method, referred to as StyleFormer, which can simultaneously fulfill fine-grained style diversity and semantic content coherency.
STVGBert: A Visual-Linguistic Transformer Based Framework for Spatio-Temporal Video Grounding
Spatio-temporal video grounding (STVG) aims to localize a spatio-temporal tube of a target object in an untrimmed video based on a query sentence.
3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds
Visual grounding on 3D point clouds is an emerging vision and language task that benefits various applications in understanding the 3D visual world.
Formal Language Constrained Markov Decision Processes
In order to satisfy safety conditions, an agent may be constrained from acting freely.
Inception Convolution with Efficient Dilation Search
To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed.
Human-centric Spatio-Temporal Video Grounding With Visual Transformers
HC-STVG is a video grounding task that requires both spatial (where) and temporal (when) localization.
Deep Learning Analysis and Age Prediction from Shoeprints
We collected 100, 000 shoeprints of subjects ranging from 7 to 80 years old and used the data to develop a deep learning end-to-end model ShoeNet to analyze age-related patterns and predict age.
A Method of Generating Measurable Panoramic Image for Indoor Mobile Measurement System
This paper designs a technique route to generate high-quality panoramic image with depth information, which involves two critical research hotspots: fusion of LiDAR and image data and image stitching.
A Simple and Efficient Registration of 3D Point Cloud and Image Data for Indoor Mobile Mapping System
Registration of 3D LiDAR point clouds with optical images is critical in the combination of multi-source data.
Improving Deep Video Compression by Resolution-adaptive Flow Coding
In this work, we propose a new framework called Resolution-adaptive Flow Coding (RaFC) to effectively compress the flow maps globally and locally, in which we use multi-resolution representations instead of single-resolution representations for both the input flow maps and the output motion features of the MV encoder.
Systematic Generation of Diverse Benchmarks for DNN Verification
The field of verification has advanced due to the interplay of theoretical development and empirical evaluation.
Simulating multi-exit evacuation using deep reinforcement learning
We propose a multi-exit evacuation simulation based on Deep Reinforcement Learning (DRL), referred to as the MultiExit-DRL, which involves in a Deep Neural Network (DNN) framework to facilitate state-to-action mapping.
Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods
In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions.
Sketchy Empirical Natural Gradient Methods for Deep Learning
Experiments on the distributed large-batch training show that the scaling efficiency is quite reasonable.
Content Adaptive and Error Propagation Aware Deep Video Compression
Therefore, the encoder is adaptive to different video contents and achieves better compression performance by reducing the domain gap between the training and testing datasets.
Channel Pruning Guided by Classification Loss and Feature Importance
To this end, we propose a new strategy to suppress the influence of unimportant features (i. e., the features will be removed at the next pruning stage).
A Unified End-to-End Framework for Efficient Deep Image Compression
Our EDIC method can also be readily incorporated with the Deep Video Compression (DVC) framework to further improve the video compression performance.
Translating multispectral imagery to nighttime imagery via conditional generative adversarial networks
The results of this study prove the possibility of multispectral-to-nighttime translation and further indicate that, with the additional social media data, the generated nighttime imagery can be very similar to the ground-truth imagery.
Formal Language Constraints for Markov Decision Processes
In order to satisfy safety conditions, an agent may be constrained from acting freely.
IntersectGAN: Learning Domain Intersection for Generating Images with Multiple Attributes
For example, given two image domains $X_1$ and $X_2$ with certain attributes, the intersection $X_1 \cap X_2$ denotes a new domain where images possess the attributes from both $X_1$ and $X_2$ domains.
Refactoring Neural Networks for Verification
Deep neural networks (DNN) are growing in capability and applicability.
Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study
Detecting inaccurate smart meters and targeting them for replacement can save significant resources.
Improving Action Localization by Progressive Cross-stream Cooperation
Specifically, we first generate a larger set of region proposals by combining the latest region proposals from both streams, from which we can readily obtain a larger set of labelled training samples to help learn better action detection models.
Hashing based Answer Selection
HAS adopts a hashing strategy to learn a binary matrix representation for each answer, which can dramatically reduce the memory cost for storing the matrix representations of answers.
Gated Group Self-Attention for Answer Selection
Nevertheless, it is difficult for RNN based models to capture the information about long-range dependency among words in the sentences of questions and answers.
DVC: An End-to-end Deep Video Compression Framework
Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information.
Constraining Action Sequences with Formal Languages for Deep Reinforcement Learning
We study the problem of deep reinforcement learning where the agent's action sequences are constrained, e. g., prohibition of dithering or overactuating action sequences that might damage a robot, drone, or other physical device.
Dividing and Aggregating Network for Multi-view Action Recognition
We then train view-specific action classifiers based on the view-specific representation for each view and a view classifier based on the shared representation at lower layers.
Deep Kalman Filtering Network for Video Compression Artifact Reduction
In this paper, we model the video artifact reduction task as a Kalman filtering procedure and restore decoded frames through a deep Kalman filtering network.
Collaborative and Adversarial Network for Unsupervised Domain Adaptation
In this paper, we propose a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN) through domain-collaborative and domain-adversarial training of neural networks.
Complex Event Detection by Identifying Reliable Shots From Untrimmed Videos
relevant) to the given event class, we formulate this task as a multi-instance learning (MIL) problem by taking each video as a bag and the video shots in each video as instances.
MUFold-SS: Protein Secondary Structure Prediction Using Deep Inception-Inside-Inception Networks
Results: Here, a very deep neural network, the deep inception-inside-inception networks (Deep3I), is proposed for protein secondary structure prediction and a software tool was implemented using this network.
Image Projective Invariants
In this paper, we propose relative projective differential invariants (RPDIs) which are invariant to general projective transformations.
SPFTN: A Self-Paced Fine-Tuning Network for Segmenting Objects in Weakly Labelled Videos
Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags.
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates
Skeleton-based human action recognition has attracted a lot of research attention during the past few years.
Ranked #6 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective
This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition.
Shape DNA: Basic Generating Functions for Geometric Moment Invariants
Two fundamental building blocks or generating functions (GFs) for invariants are discovered, which are dot product and vector product of point vectors in Euclidean space.
Learning Multi-level Deep Representations for Image Emotion Classification
The proposed MldrNet combines deep representations of different levels, i. e. image semantics, image aesthetics, and low-level visual features to effectively classify the emotion types of different kinds of images, such as abstract paintings and web images.
A Siamese Long Short-Term Memory Architecture for Human Re-Identification
Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance.
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
To handle the noise and occlusion in 3D skeleton data, we introduce new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell.
Ranked #8 on
Skeleton Based Action Recognition
on SBU
Full-Time Supervision based Bidirectional RNN for Factoid Question Answering
Hence, these existing models don't put supervision (loss or similarity calculation) at every time step, which will lose some useful information.
Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization
Trace-norm regularization plays an important role in many areas such as machine learning and computer vision.
Fast Algorithms for Linear and Kernel SVM+
The SVM+ approach has shown excellent performance in visual recognition tasks for exploiting privileged information in the training data.
Dimensionality-Dependent Generalization Bounds for $k$-Dimensional Coding Schemes
Can we obtain dimensionality-dependent generalization bounds for $k$-dimensional coding schemes that are tighter than dimensionality-independent bounds when data is in a finite-dimensional feature space?
Multi-View Domain Generalization for Visual Recognition
Considering the recent works show the domain generalization capability can be enhanced by fusing multiple SVM classifiers, we build upon exemplar SVMs to learn a set of SVM classifiers by using one positive sample and all negative samples in the source domain each time.
FaLRR: A Fast Low Rank Representation Solver
In this paper, we develop a fast LRR solver called FaLRR, by reformulating LRR as a new optimization problem with regard to factorized data (which is obtained by skinny SVD of the original data matrix).
Object-Based RGBD Image Co-Segmentation With Mutex Constraint
We present an object-based co-segmentation method that takes advantage of depth data and is able to correctly handle noisy images in which the common foreground object is missing.
Visual Recognition by Learning From Web Data: A Weakly Supervised Domain Generalization Approach
In this work, we formulate a new weakly supervised domain generalization problem for the visual recognition task by using loosely labeled web images/videos as training data.
Scalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient
Nuclear-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR).
Recognizing RGB Images by Learning from RGB-D Data
In this work, we propose a new framework for recognizing RGB images captured by the conventional cameras by leveraging a set of labeled RGB-D data, in which the depth features can be additionally extracted from the depth images.
Object-based Multiple Foreground Video Co-segmentation
We present a video co-segmentation method that uses category-independent object proposals as its basic element and can extract multiple foreground objects in a video set.
Learning by Associating Ambiguously Labeled Images
Our framework is motivated by the observation that samples from the same class repetitively appear in the collection of ambiguously labeled training images, while they are just ambiguously labeled in each image.
Event Recognition in Videos by Learning from Heterogeneous Web Sources
In this work, we propose to leverage a large number of loosely labeled web videos (e. g., from YouTube) and web images (e. g., from Google/Bing image search) for visual event recognition in consumer videos without requiring any labeled consumer videos.
Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
Spatial-Temporal Face Region Descriptor, STFRD) for images (resp.
