Search Results for author:
Found 38 papers, 18 papers with code
Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation
Recent advances in text-to-image diffusion models have been driven by the increasing availability of paired 2D data.
Automated 3D Physical Simulation of Open-world Scene with Gaussian Splatting
Recent advancements in 3D generation models have opened new possibilities for simulating dynamic 3D object movements and customizing behaviors, yet creating this content remains challenging.
Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction
Comprehensive experiments demonstrate the effectiveness of PC-MRL in motion interpolation for desired skeletons without supervision from native datasets.
Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses
Our key idea is that with multiple RoIs as input, we can estimate multiple local cameras and have the opportunity to design and apply additional constraints between cameras to improve the accuracy of the cameras and, in turn, the accuracy of the corresponding 3D mesh.
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery
In this way, we obtain a meta-model, the meta-parameter of which is friendly to the test-time optimization.
Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection
Video Anomaly Detection (VAD) has been extensively studied under the settings of One-Class Classification (OCC) and Weakly-Supervised learning (WS), which however both require laborious human-annotated normal/abnormal labels.
Disentangled Representation Learning for Controllable Person Image Generation
Unlike the existing works leveraging the semantic masks to obtain the representation of each component, we propose to generate disentangled latent code via a novel attribute encoder with transformers trained in a manner of curriculum learning from a relatively easy step to a gradually hard one.
Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition
Micro-expressions are spontaneous, rapid and subtle facial movements that can neither be forged nor suppressed.
Micro Expression Recognition
Micro-Expression Recognition
+2
Learning Dynamic Style Kernels for Artistic Style Transfer
Arbitrary style transfer has been demonstrated to be efficient in artistic image generation.
Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation
Deriving sophisticated 3D motions from sparse keyframes is a particularly challenging problem, due to continuity and exceptionally skeletal precision.
Explore Contextual Information for 3D Scene Graph Generation
3D scene graph generation (SGG) has been of high interest in computer vision.
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space
In this paper, we propose a novel sampling strategy for sampling very diverse results from an imbalanced multimodal distribution learned by a deep generative model.
Ranked #2 on
Human Pose Forecasting
on HumanEva-I
Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
Our proposed approach is extensively validated on the ViSha dataset and a self-annotated dataset.
Social Interpretable Tree for Pedestrian Trajectory Prediction
Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications.
Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
This motivates us to propose a novel two-stage prediction framework, including an init-prediction network that just computes the good guess and then a formal-prediction network that predicts the target future poses based on the guess.
Ranked #10 on
Human Pose Forecasting
on Human3.6M
CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation
Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations.
Luminance Attentive Networks for HDR Image and Panorama Reconstruction
Based on this observation, we propose a novel normalization method called " HDR calibration " for HDR images stored in relative luminance, calibrating HDR images into a similar luminance scale according to the LDR images.
CANet: A Context-Aware Network for Shadow Removal
In this paper, we propose a novel two-stage context-aware network named CANet for shadow removal, in which the contextual information from non-shadow regions is transferred to shadow regions at the embedded feature spaces.
DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer
The style code is modeled as the shared parameters for Dynamic ResBlocks connecting both the style encoding network and the style transfer network.
A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
In this paper, we propose $\text{HF}^2$-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection.
Ranked #1 on
Video Anomaly Detection
on Ped2
MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
The extracted features at each scale are then combined and decoded to obtain the residuals between the input and target poses.
Ranked #13 on
Human Pose Forecasting
on Human3.6M
Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning
With the well-designed Dual-GCN, we can make the linguistic transformer better understand the relationship between different objects in a single image and make full use of similar images as auxiliary information to generate a reasonable caption description for a single image.
Deep Image-based Illumination Harmonization
Specifically, we firstly apply a physically-based rendering method to construct a large-scale, high-quality dataset (named IH) for our task, which contains various types of foreground objects and background scenes with different lighting conditions.
CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation
Based on those constraints, a category-consistent and relativistic diverse conditional GAN (CRD-CGAN) is proposed to synthesize $K$ photo-realistic images simultaneously.
SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians.
Multi-Level Attentive Convoluntional Neural Network for Crowd Counting
Recently the crowd counting has received more and more attention.
A Two-Stage Attentive Network for Single Image Super-Resolution
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress.
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Meanwhile, we use a sparse directed temporal graph to model the motion tendency, thus to facilitate the prediction based on the observed direction.
A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization
Moreover, our temporal semi-soft and hard attention modules, calculating two attention scores for each video snippet, help to focus on the less discriminative frames of an action to capture the full action boundary.
Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations
Deep neural networks have achieved great success in many real-world applications, yet it remains unclear and difficult to explain their decision-making process to an end-user.
RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal
To our best knowledge, we are the first one to explore residual and illumination for shadow removal.
ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
In this paper we propose an attentive recurrent generative adversarial network (ARGAN) to detect and remove shadows in an image.
Generative Adversarial Network
Shadow Detection And Removal
+1
VITAL: A Visual Interpretation on Text with Adversarial Learning for Image Labeling
In this paper, we propose a novel way to interpret text information by extracting visual feature presentation from multiple high-resolution and photo-realistic synthetic images generated by Text-to-image Generative Adversarial Network (GAN) to improve the performance of image labeling.
A Coarse-to-fine Deep Convolutional Neural Network Framework for Frame Duplication Detection and Localization in Forged Videos
First, an I3D network finds coarse-level matches between candidate duplicated frame sequences and the corresponding selected original frame sequences.
Deep Neural Networks In Fully Connected CRF For Image Labeling With Social Network Metadata
We propose a novel method for predicting image labels by fusing image content descriptors with the social media context of each image.
Correlational Gaussian Processes for Cross-Domain Visual Recognition
A set of correlational tensors is adopted to model the relationship within a single domain as well as across multiple domains.
L2GSCI: Local to Global Seam Cutting and Integrating for Accurate Face Contour Extraction
Current face alignment algorithms can robustly find a set of landmarks along face contour.
Multi-Class Multi-Annotator Active Learning With Robust Gaussian Process for Visual Recognition
Based on the EP approximation inference, a generalized Expectation Maximization (GEM) algorithm is derived to estimate both the parameters for instances and the quality of each individual annotator.
