Search Results for author:
Found 30 papers, 15 papers with code
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
These innovations collectively make our framework highly efficient, flexible, and suitable for a wide range of tasks.
Training-free Regional Prompting for Diffusion Transformers
Diffusion models have demonstrated excellent capabilities in text-to-image generation.
InstantIR: Blind Image Restoration with Instant Generative Reference
In this paper, we introduce Instant-reference Image Restoration (InstantIR), a novel diffusion-based BIR method which dynamically adjusts generation condition during inference.
Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
This scheme adds varying numbers of noise steps to the latent representation of the watermarked image, followed by a controlled denoising process starting from this noisy latent representation.
Multi-scale Multi-instance Visual Sound Localization and Segmentation
Visual sound localization is a typical and challenging problem that predicts the location of objects corresponding to the sound source in a video.
CSGO: Content-Style Composition in Text-to-Image Generation
Based on this pipeline, we construct a dataset IMAGStyle, the first large-scale style transfer dataset containing 210k image triplets, available for the community to explore and research.
InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation
Style transfer is an inventive process designed to create an image that maintains the essence of the original while embracing the visual style of another.
Unified Video-Language Pre-training with Synchronized Audio
Video-language pre-training is a typical and challenging problem that aims at learning visual and textual representations from large-scale data in a self-supervised way.
Multimodal Sense-Informed Prediction of 3D Human Motions
Predicting future human pose is a fundamental application for machine intelligence, which drives robots to plan their behavior and paths ahead of time to seamlessly accomplish human-robot collaboration in real-world 3D scenarios.
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
Tuning-free diffusion-based models have demonstrated significant potential in the realm of image personalization and customization.
InstantID: Zero-shot Identity-Preserving Generation in Seconds
There has been significant progress in personalized image synthesis with methods such as Textual Inversion, DreamBooth, and LoRA.
Ranked #2 on
Diffusion Personalization Tuning Free
on AgeDB
Multimodal Sense-Informed Forecasting of 3D Human Motions
To address this limitation this work introduces a novel multi-modal sense-informed motion prediction approach which conditions high-fidelity generation on two modal information: external 3D scene and internal human gaze and is able to recognize their salience for future human activity.
Expressive Forecasting of 3D Whole-body Human Motions
Human motion forecasting, with the goal of estimating future human behavior over a period of time, is a fundamental task in many real-world applications.
Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
In particular, we build a tree-like Split-Ensemble architecture by performing iterative splitting and pruning from a shared backbone model, where each branch serves as a submodel corresponding to a subtask.
Synthesizing Physically Plausible Human Motions in 3D Scenes
We present a physics-based character control framework for synthesizing human-scene interactions.
1st Place Solution for PSG competition with ECCV'22 SenseHuman Workshop
Panoptic Scene Graph (PSG) generation aims to generate scene graph representations based on panoptic segmentation instead of rigid bounding boxes.
Test-time Personalizable Forecasting of 3D Human Poses
Current motion forecasting approaches typically train a deep end-to-end model from the source domain data, and then apply it directly to target subjects.
One-shot Implicit Animatable Avatars with Model-based Priors
Most of these methods fail to achieve realistic reconstruction when only a single image is available.
LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
To overcome the above issue, we present a novel mechanism for learning the translation relationship from a source modality space $\mathcal{S}$ to a target modality space $\mathcal{T}$ without the need for a joint latent space, which bridges the gap between visual and textual domains.
Ranked #13 on
Zero-Shot Video Retrieval
on MSVD
TransAug: Translate as Augmentation for Sentence Embeddings
In this paper, we present TransAug (Translate as Augmentation), which provide the first exploration of utilizing translated sentence pairs as data augmentation for text, and introduce a two-stage paradigm to advances the state-of-the-art sentence embeddings.
EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling
Extra rich non-paired single-modal text data is used for boosting the generalization of text branch.
When Differential Privacy Meets Interpretability: A Case Study
Given the increase in the use of personal data for training Deep Neural Networks (DNNs) in tasks such as medical imaging and diagnosis, differentially private training of DNNs is surging in importance and there is a large body of work focusing on providing better privacy-utility trade-off.
Automatic Speech Verification Spoofing Detection
Automatic speech verification (ASV) is the technology to determine the identity of a person based on their voice.
SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization
Interpretation of the underlying mechanisms of Deep Convolutional Neural Networks has become an important aspect of research in the field of deep learning due to their applications in high-risk environments.
Smoothed Geometry for Robust Attribution
Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs.
XDeep: An Interpretation Tool for Deep Neural Networks
XDeep is an open-source Python package developed to interpret deep models for both practitioners and researchers.
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.
Ranked #2 on
Error Understanding
on CUB-200-2011 (ResNet-101)
Contextual Local Explanation for Black Box Classifiers
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE.
Hybrid coarse-fine classification for head pose estimation
In this paper, to do the estimation without facial landmarks, we combine the coarse and fine regression output together for a deep network.
Ranked #3 on
Head Pose Estimation
on AFLW
