Search Results for author:
Found 50 papers, 19 papers with code
Personalized Image Aesthetics
To accommodate our study, we first collect two distinct datasets, a large image dataset from Flickr and annotated by Amazon Mechanical Turk, and a small dataset of real personal albums rated by owners.
Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images
Automatic and accurate Gleason grading of histopathology tissue slides is crucial for prostate cancer diagnosis, treatment, and prognosis.
Factorized Adversarial Networks for Unsupervised Domain Adaptation
In this paper, we propose Factorized Adversarial Networks (FAN) to solve unsupervised domain adaptation problems for image classification tasks.
EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch
In this paper, we propose an Ecologically-Inspired GENetic (EIGEN) approach that uses the concept of succession, extinction, mimicry, and gene duplication to search neural network structure from scratch with poorly initialized simple network and few constraints forced during the evolution, as we assume no prior knowledge about the task domain.
Human Motion Transfer from Poses in the Wild
In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video.
Neural Hair Rendering
Unlike existing supervised translation methods that require model-level similarity to preserve consistent structure representation for both real images and fake renderings, our method adopts an unsupervised solution to work on arbitrary hair models.
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i. e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance than the original dense network.
Teachers Do More Than Teach: Compressing Image-to-Image Models
In this work, we aim to address these issues by introducing a teacher network that provides a search space in which efficient network architectures can be found, in addition to performing knowledge distillation.
SMIL: Multimodal Learning with Severely Missing Modality
A common assumption in multimodal learning is the completeness of training data, i. e., full modalities are available in all training examples.
In&Out : Diverse Image Outpainting via GAN Inversion
Existing image outpainting methods pose the problem as a conditional image-to-image translation task, often generating repetitive structures and textures by replicating the content available in the input image.
Motion Representations for Articulated Animation
To facilitate animation and prevent the leakage of the shape of the driving object, we disentangle shape and pose of objects in the region space.
Ranked #1 on
Video Reconstruction
on Tai-Chi-HD (512)
A Good Image Generator Is What You Need for High-Resolution Video Synthesis
We introduce a motion generator that discovers the desired trajectory, in which content and motion are disentangled.
Ranked #32 on
Video Generation
on UCF-101
Flow Guided Transformable Bottleneck Networks for Motion Retargeting
Human motion retargeting aims to transfer the motion of one person in a "driving" video or set of images to another person.
BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection
Graph-based Anomaly Detection (GAD) is becoming prevalent due to the powerful representation abilities of graphs as well as recent advances in graph mining techniques.
InOut: Diverse Image Outpainting via GAN Inversion
Existing image outpainting methods pose the problem as a conditional image-to-image translation task, often generating repetitive structures and textures by replicating the content available in the input image.
A Critical Analysis of Image-based Camera Pose Estimation Techniques
Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR).
F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
Our approach achieves comparable and better performance, when compared not only to existing quantization techniques with INT32 multiplication or floating-point arithmetic, but also to the full-precision counterparts, achieving state-of-the-art performance.
Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning
In addition, our model can extract visual information as suggested by the text prompt, e. g., "an object in image one is moving northeast", and generate corresponding videos.
R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis
On the other hand, Neural Light Field (NeLF) presents a more straightforward representation over NeRF in novel view synthesis -- the rendering of a pixel amounts to one single forward pass without ray-marching.
Are Multimodal Transformers Robust to Missing Modality?
Based on these findings, we propose a principle method to improve the robustness of Transformer models by automatically searching for an optimal fusion strategy regarding input data.
EfficientFormer: Vision Transformers at MobileNet Speed
Our work proves that properly designed transformers can reach extremely low latency on mobile devices while maintaining high performance.
Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation
Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis.
Computer Vision-Aided Reconfigurable Intelligent Surface-Based Beam Tracking: Prototyping and Experimental Results
The vision-aided RIS prototype system is tested in two mobile scenarios: RIS works in near-field conditions as a passive array antenna of the base station; RIS works in far-field conditions to assist the communication between the base station and the user equipment.
Cross-Modal 3D Shape Generation and Manipulation
In this paper, we propose a generic multi-modal generative model that couples the 2D modalities and implicit 3D representations through shared latent spaces.
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation
In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth.
PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems
In this paper, we propose a method for training quantized networks to incorporate PIM quantization, which is ubiquitous to all PIM systems.
Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
Therefore, we analyze the feasibility and potentiality of using the layer freezing technique in sparse training and find it has the potential to save considerable training costs.
Make-A-Story: Visual Memory Conditioned Consistent Story Generation
Our experiments for story generation on the MUGEN, the PororoSV and the FlintstonesSV dataset show that our method not only outperforms prior state-of-the-art in generating frames with high visual quality, which are consistent with the story, but also models appropriate correspondences between the characters and the background.
SINE: SINgle Image Editing with Text-to-Image Diffusion Models
We propose a novel model-based guidance built upon the classifier-free guidance so that the knowledge from the model trained on a single image can be distilled into the pre-trained diffusion model, enabling content creation even with one given image.
Real-Time Neural Light Field on Mobile Devices
Nevertheless, to reach a similar rendering quality as NeRF, the network in NeLF is designed with intensive computation, which is not mobile-friendly.
Rethinking Vision Transformers for MobileNet Size and Speed
With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices.
Unsupervised Volumetric Animation
We propose a novel approach for unsupervised 3D animation of non-rigid deformable objects.
Invertible Neural Skinning
Next, we combine PIN with a differentiable LBS module to build an expressive and end-to-end Invertible Neural Skinning (INS) pipeline.
3D generation on ImageNet
Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the scene.
Two-Bit RIS-Aided Communications at 3.5GHz: Some Insights from the Measurement Results Under Multiple Practical Scenes
In particular, we adopt a self-developed broadband intelligent communication system 40MHz-Net (BICT-40N) terminal in order to fully acquire the channel information.
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks.
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
We achieve so by introducing efficient network architecture and improving step distillation.
Robust and Efficient Fault Diagnosis of mm-Wave Active Phased Arrays using Baseband Signal
One key communication block in 5G and 6G radios is the active phased array (APA).
Fast and Automatic 3D Modeling of Antenna Structure Using CNN-LSTM Network for Efficient Data Generation
In this study, we proposed a deep learning-assisted and image-based intelligent modeling approach for accelerating the data acquisition of antenna samples with different physical structures.
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors.
CLGT: A Graph Transformer for Student Performance Prediction in Collaborative Learning
Based on this student interaction graph, we present an extended graph transformer framework for collaborative learning (CLGT) for evaluating and predicting the performance of students.
HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
Our model enforces the joint learning of image appearance, spatial relationship, and geometry in a unified network, where each branch in the model complements to each other with both structural awareness and textural richness.
iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis
Our approach focuses on maximizing the reuse of visible pixels from the source image.
E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
One highly promising direction for enabling flexible real-time on-device image editing is utilizing data distillation by leveraging large-scale text-to-image diffusion models, such as Stable Diffusion, to generate paired datasets used for training generative adversarial networks (GANs).
AToM: Amortized Text-to-Mesh using 2D Diffusion
We introduce Amortized Text-to-Mesh (AToM), a feed-forward text-to-mesh framework optimized across multiple text prompts simultaneously.
SPAD : Spatially Aware Multiview Diffusers
We present SPAD, a novel approach for creating consistent multi-view images from text prompts or single images.
Visual Concept-driven Image Generation with Text-to-Image Diffusion Model
We illustrate that such joint alternating refinement leads to the learning of better tokens for concepts and, as a bi-product, latent masks.
Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis
Since video content is highly redundant, we argue that naively bringing advances of image models to the video generation domain reduces motion fidelity, visual quality and impairs scalability.
Ranked #1 on
Text-to-Video Generation
on MSR-VTT
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Next, we finetune a retrieval model on a small subset where the best caption of each video is manually selected and then employ the model in the whole dataset to select the best caption as the annotation.
TextCraftor: Your Text Encoder Can be Image Quality Controller
Our findings reveal that, instead of replacing the CLIP text encoder used in Stable Diffusion with other large language models, we can enhance it through our proposed fine-tuning approach, TextCraftor, leading to substantial improvements in quantitative benchmarks and human assessments.
