Search Results for author:
Found 18 papers, 4 papers with code
Towards Consistent Video Editing with Text-to-Image Diffusion Models
Existing works have advanced Text-to-Image (TTI) diffusion models for video editing in a one-shot learning manner.
DropKey for Vision Transformer
Given exploration on the above three questions, we present the novel DropKey method that regards Key as the drop unit and exploits decreasing schedule for drop ratio, improving ViTs in a general way.
Shadow Removal by High-Quality Shadow Synthesis
Specifically, the encoder extracts the shadow feature of a region identity which is then paired with another region identity to serve as the generator input to synthesize a pseudo image.
Multi-view Human Body Mesh Translator
Existing methods for human mesh recovery mainly focus on single-view frameworks, but they often fail to produce accurate results due to the ill-posed setup.
DropKey
Given exploration on the above three questions, we present the novel DropKey method that regards Key as the drop unit and exploits decreasing schedule for drop ratio, improving ViTs in a general way.
MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
With such multi-dimension and multi-scale factorization, our MorphMLP block can achieve a great accuracy-computation balance.
Ranked #24 on
Action Recognition
on Something-Something V2
(using extra training data)
Referring Image Segmentation via Cross-Modal Progressive Comprehension
In addition to the CMPC module, we further leverage a simple yet effective TGFE module to integrate the reasoned multimodal features from different levels with the guidance of textual information.
Ranked #10 on
Referring Expression Segmentation
on RefCOCO testB
Recurrent 3D-2D Dual Learning for Large-Pose Facial Landmark Detection
To address these challenging issues, we introduce a novel recurrent 3D-2D dual learning model that alternatively performs 2D-based 3D face model refinement and 3D-to-2D projection based 2D landmark refinement to reliably reason about self-occluded landmarks, precisely capture the subtle landmark displacement and accurately detect landmarks even in presence of extremely large poses.
Smart Mirror: Intelligent Makeup Recommendation and Synthesis
The female facial image beautification usually requires professional editing softwares, which are relatively difficult for common users.
Salient Object Detection with Semantic Priors
Salient object detection has increasingly become a popular topic in cognitive and computational sciences, including computer vision and artificial intelligence research.
Video Scene Parsing with Predictive Feature Learning
In this way, the network can effectively learn to capture video dynamics and temporal context, which are critical clues for video scene parsing, without requiring extra manual annotations.
Online Feature Selection with Group Structure Analysis
The problem assumes that features are generated individually but there are group structure in the feature stream.
Peak-Piloted Deep Network for Facial Expression Recognition
Objective functions for training of deep networks for face-related recognition tasks, such as facial expression recognition (FER), usually consider each sample independently.
Ranked #2 on
Facial Expression Recognition (FER)
on Oulu-CASIA
Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection
Then the concept detector can be fine-tuned based on these new instances.
Personalized Age Progression with Aging Dictionary
Second, it is challenging or even impossible to collect faces of all age groups for a particular subject, yet much easier and more practical to get face pairs from neighboring age groups.
Matching-CNN Meets KNN: Quasi-Parametric Human Parsing
Under the classic K Nearest Neighbor (KNN)-based nonparametric framework, the parametric Matching Convolutional Neural Network (M-CNN) is proposed to predict the matching confidence and displacements of the best matched region in the testing image for a particular semantic region in one KNN image.
Deep Human Parsing with Active Template Regression
The first CNN network is with max-pooling, and designed to predict the template coefficients for each label mask, while the second CNN network is without max-pooling to preserve sensitivity to label mask position and accurately predict the active shape parameters.
Computational Baby Learning
Then the concept detector can be fine-tuned based on these new instances.
