Search Results for author:
Found 32 papers, 12 papers with code
TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
In this paper, we propose a novel cross-modal distillation method, called TinyCLIP, for large-scale language-image pre-trained models.
Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement Learning
The proposed framework consists of a large language model (LLM), a diffusion-based image generator, and a series of visual rewards by design.
Semantic-Conditional Diffusion Networks for Image Captioning
The rich semantics are further regarded as semantic prior to trigger the learning of Diffusion Transformer, which produces the output sentence in a diffusion process.
Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization
Existing works attempt to solve the problem by explicitly imposing uncertainty on classifiers when OOD inputs are exposed to the classifier during training.
CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning
In this work, we quantitatively analyze the sub-text problem and present a simple yet effective design, COntrastive RElation (CORE) module, to mitigate that issue.
CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising
BERT-type structure has led to the revolution of vision-language pre-training and the achievement of state-of-the-art results on numerous vision-language downstream tasks.
Searching the Search Space of Vision Transformer
Vision Transformer has shown great visual representation power in substantial vision tasks such as recognition and detection, and thus been attracting fast-growing efforts on manually designing more effective architectures.
Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers
Given a sequence of style tokens, the TokenGAN is able to control the image synthesis by assigning the styles to the content tokens by attention mechanism with a Transformer.
Reference-based Defect Detection Network
To solve the partial visual confusion issue, we propose to leverage the carried context information of context reference, which is the concentric bigger box of each region proposal, to perform more accurate region classification and regression.
A Low Rank Promoting Prior for Unsupervised Contrastive Learning
In this paper, we construct a novel probabilistic graphical model that effectively incorporates the low rank promoting prior into the framework of contrastive learning, referred to as LORAC.
Rethinking and Improving Relative Position Encoding for Vision Transformer
We then propose new relative position encoding methods dedicated to 2D images, called image RPE (iRPE).
Ranked #140 on
Object Detection
on COCO minival
3D Human Body Reshaping with Anthropometric Modeling
First, we calculate full-body anthropometric parameters from limited user inputs by imputation technique, and thus essential anthropometric parameters for 3D body reshaping can be obtained.
Aggregated Contextual Transformations for High-Resolution Image Inpainting
For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task.
Ranked #9 on
Image Inpainting
on Places2
Learning Joint Spatial-Temporal Transformations for Video Inpainting
In this paper, we propose to learn a joint Spatial-Temporal Transformer Network (STTN) for video inpainting.
Ranked #5 on
Seeing Beyond the Visible
on KITTI360-EX
Mining Domain Knowledge: Improved Framework towards Automatically Standardizing Anatomical Structure Nomenclature in Radiotherapy
To solve these problems, we propose an automated structure nomenclature standardization framework, 3D Non-local Network with Voting (3DNNV).
Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysis
Interestingly, the principal component analysis exactly provides an effective way to define such a frame, i. e. setting the principal components as the frame axes.
WSOD2: Learning Bottom-up and Top-down Objectness Distillation forWeakly-supervised Object Detection
We study on weakly-supervised object detection (WSOD)which plays a vital role in relieving human involvement fromobject-level annotations.
WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
We study on weakly-supervised object detection (WSOD) which plays a vital role in relieving human involvement from object-level annotations.
Deep Metric Learning with Density Adaptivity
The problem of distance metric learning is mostly considered from the perspective of learning an embedding space, where the distances between pairs of examples are in correspondence with a similarity metric.
Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables
Deep models are capable of fitting complex high dimensional functions while usually yielding large computation load.
Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning
Moreover, the inherently recurrent dependency in RNN prevents parallelization within a sequence during training and therefore limits the computations.
Pointing Novel Objects in Image Captioning
Image captioning has received significant attention with remarkable improvements in recent advances.
Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting
As the missing content can be filled by attention transfer from deep to shallow in a pyramid fashion, both visual and semantic coherence for image inpainting can be ensured.
Face Recognition from Sequential Sparse 3D Data via Deep Registration
However, such devices only provide sparse(limited speckles in structured light system) and noisy 3D data which can not support face recognition directly.
Image Blind Denoising With Generative Adversarial Network Based Noise Modeling
In this paper, we consider a typical image blind denoising problem, which is to remove unknown noise from noisy images.
Jointly Localizing and Describing Events for Dense Video Captioning
A valid question is how to temporally localize and then describe events, which is known as "dense video captioning."
Deep Joint Face Hallucination and Recognition
However, we observe that directly feeding the hallucinated facial images into recog- nition models can even degrade the recognition performance despite the much better visualization quality.
Automatically Building Face Datasets of New Domains from Weakly Labeled Data with Pretrained Models
In this paper, we propose a method to automatically and incrementally construct datasets from massive weakly labeled data of the target domain which are readily available on the Internet under the help of a pretrained face model.
One-to-Many Network for Visually Pleasing Compression Artifacts Reduction
We consider the compression artifacts reduction problem, where a compressed image is transformed into an artifact-free image.
Joint Multiview Segmentation and Localization of RGB-D Images Using Depth-Induced Silhouette Consistency
In this paper, we propose an RGB-D camera localization approach which takes an effective geometry constraint, i. e. silhouette consistency, into consideration.
Deep Feature Learning with Relative Distance Comparison for Person Re-identification
Identifying the same individual across different scenes is an important yet difficult task in intelligent video surveillance.
Ranked #9 on
Person Re-Identification
on SYSU-30k
(using extra training data)
MeshStereo: A Global Stereo Model With Mesh Alignment Regularization for View Interpolation
We present a novel global stereo model designed for view interpolation.
