Search Results for author:
Found 56 papers, 25 papers with code
Delving into Multimodal Prompting for Fine-grained Visual Classification
In this paper, we aim to fully exploit the capabilities of cross-modal description to tackle FGVC tasks and propose a novel multimodal prompting solution, denoted as MP-FGVC, based on the contrastive language-image pertaining (CLIP) model.
NPF-200: A Multi-Modal Eye Fixation Dataset and Method for Non-Photorealistic Videos
Non-photorealistic videos are in demand with the wave of the metaverse, but lack of sufficient research studies.
RIGID: Recurrent GAN Inversion and Editing of Real Face Videos
In this paper, we propose a unified recurrent framework, named \textbf{R}ecurrent v\textbf{I}deo \textbf{G}AN \textbf{I}nversion and e\textbf{D}iting (RIGID), to explicitly and simultaneously enforce temporally coherent GAN inversion and facial editing of real videos.
DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting
Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets.
Disentangling Multi-view Representations Beyond Inductive Bias
In this paper, we propose a novel multi-view representation disentangling method that aims to go beyond inductive biases, ensuring both interpretability and generalizability of the resulting representations.
Single-View View Synthesis with Self-Rectified Pseudo-Stereo
In this way, the challenging novel view synthesis process is decoupled into two simpler problems of stereo synthesis and 3D reconstruction.
SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing
The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details.
Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one.
Ranked #2 on
Image Dehazing
on SOTS Outdoor
Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval
Specifically, the employed student model is initially a heavy model to fruitfully learn distilled knowledge in the early training epochs, and the student model is gradually compressed during the training.
CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting
Video inpainting aims at filling in missing regions of a video.
Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization
The rationale behind is that we aim to locate a centroid latent position in a conditional StyleGAN, where the corresponding output image on that centroid can maximize the similarity with the given samples.
Deep Video Demoireing via Compact Invertible Dyadic Decomposition
Removing moire patterns from videos recorded on screens or complex textures is known as video demoireing.
Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion
To address the above issues, we propose Diffuse3D which employs a pre-trained diffusion model for global synthesis, while amending the model to activate depth-aware inference.
Monocular BEV Perception of Road Scenes via Front-to-Top View Projection
We propose a front-to-top view projection (FTVP) module, which takes the constraint of cycle consistency between views into account and makes full use of their correlation to strengthen the view transformation and scene understanding.
Self-supervised Matting-specific Portrait Enhancement and Generation
Particularly, we invert an input portrait into the latent code of StyleGAN, and our aim is to discover whether there is an enhanced version in the latent space which is more compatible with a reference matting model.
Editing Out-of-domain GAN Inversion via Differential Activations
Consequently, in the decomposition phase, we further present a GAN prior based deghosting network for separating the final fine edited image from the coarse reconstruction.
A Simple Data Mixing Prior for Improving Self-Supervised Learning
More notably, our SDMP is the first method that successfully leverages data mixing to improve (rather than hurt) the performance of Vision Transformers in the self-supervised setting.
Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting
To enable training under this new setting, we convert the crowd count regression problem to a ranking potential prediction problem.
High-resolution Face Swapping via Latent Semantics Disentanglement
Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space.
Faithful Extreme Rescaling via Generative Prior Reciprocated Invertible Representations
This paper presents a Generative prior ReciprocAted Invertible rescaling Network (GRAIN) for generating faithful high-resolution (HR) images from low-resolution (LR) invertible images with an extreme upscaling factor (64x).
Shunted Self-Attention via Multi-Scale Token Aggregation
This novel merging scheme enables the self-attention to learn relationships between objects with different sizes and simultaneously reduces the token numbers and the computational cost.
Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement
In particular, we introduce a novel locality-aware context fusion based segmentation model to process local patches, where the relevance between local patch and its various contexts are jointly and complementarily utilized to handle the semantic regions with large variations.
Ranked #2 on
Land Cover Classification
on DeepGlobe
Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation
To this end, we propose to untangle \emph{domain-invariant} crowd and \emph{domain-specific} background from crowd images and design a fine-grained domain adaption method for crowd counting.
Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting
In this way, we can transfer the original spatial labeling redundancy caused by individual similarities to effective supervision signals on the unlabeled regions.
Unifying Global-Local Representations in Salient Object Detection with Transformer
In this paper, we introduce a new attention-based encoder, vision transformer, into salient object detection to ensure the globalization of the representations from shallow to deep layers.
From Continuity to Editability: Inverting GANs with Consecutive Images
This inborn property is used for two unique purposes: 1) regularizing the joint inversion process, such that each of the inverted code is semantically accessible from one of the other and fastened in a editable domain; 2) enforcing inter-image coherence, such that the fidelity of each inverted code can be maximized with the complement of other images.
Co-advise: Cross Inductive Bias Distillation
Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks.
Reciprocal Transformations for Unsupervised Video Object Segmentation
Additionally, to exclude the information of the moving background objects from motion features, our transformation module enables to reciprocally transform the appearance features to enhance the motion features, so as to focus on the moving objects with salient appearance while removing the co-moving outliers.
Delving Deep Into Many-to-Many Attention for Few-Shot Video Object Segmentation
The key is to model the relationship between the query videos and the support images for propagating the object information.
Discovering Interpretable Latent Space Directions of GANs Beyond Binary Attributes
In this way, arbitrary attributes can be edited by collecting positive data only, and the proposed method learns a controllable representation enabling manipulation of non-binary attributes like anime styles and facial characteristics.
Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip Reading
To these ends, we introduce a trainable "master" network which ingests both audio signals and silent lip videos instead of a pretrained teacher.
Spatially-Invariant Style-Codes Controlled Makeup Transfer
In this paper, we take a different perspective to break down the makeup transfer problem into a two-step extraction-assignment process.
Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View Transformation
Furthermore, our model runs at 35 FPS on a single GPU, which is efficient and applicable for real-time panorama HD map reconstruction.
Autonomous Driving
Monocular Cross-View Road Scene Parsing(Road)
+2
Mask-ShadowNet: Towards Shadow Removal via Masked Adaptive Instance Normalization
Shadow removal is an important yet challenging task in image processing and computer vision.
Smart Scribbles for Image Mating
Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles.
Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics
Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spatial location and dominant color of the largest color diversity along the temporal axis, etc.
TENet: Triple Excitation Network for Video Salient Object Detection
In this paper, we propose a simple yet effective approach, named Triple Excitation Network, to reinforce the training of video salient object detection (VSOD) from three aspects, spatial, temporal, and online excitations.
Over-crowdedness Alert! Forecasting the Future Crowd Distribution
In this paper, we formulate a novel crowd analysis problem, in which we aim to predict the crowd distribution in the near future given sequential frames of a crowd video without any identity annotations.
Context-aware and Scale-insensitive Temporal Repetition Counting
It avoids the heavy computation of exhaustively searching all the cycle lengths in the video, and, instead, it propagates the coarse prediction for further refinement in a hierarchical manner.
Laplacian Denoising Autoencoder
This can be naturally generalized to span multiple scales with a Laplacian pyramid representation of the input data.
Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery
We conduct comparison experiments on this dataset and demonstrate that our model outperforms the state-of-the-art in tasks of recovering segmentation mask and appearance for occluded vehicles.
Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
We conduct extensive experiments with C3D to validate the effectiveness of our proposed approach.
Ranked #47 on
Self-Supervised Action Recognition
on HMDB51
Active Matting
Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts.
Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement
We first propose a facial component guided deep Convolutional Neural Network (CNN) to restore a coarse face image, which is denoted as the base image where the facial component is automatically generated from the input face image.
Deformable Object Tracking with Gated Fusion
In addition, we also propose a gated fusion scheme to control how the variations captured by the deformable convolution affect the original appearance.
SINet: A Scale-insensitive Convolutional Neural Network for Fast Vehicle Detection
Based on these findings, we present a scale-insensitive convolutional neural network (SINet) for fast detecting vehicles with a large variance of scales.
Egocentric Hand Detection Via Dynamic Region Growing
Egocentric videos, which mainly record the activities carried out by the users of the wearable cameras, have drawn much research attentions in recent years.
Delving Into Salient Object Subitizing and Detection
Experiments show that the proposed multi-task network outperforms existing multi-task architectures, and the auxiliary subitizing network provides strong guidance to salient object detection by reducing false positives and producing coherent saliency maps.
Stylizing Face Images via Multiple Exemplars
We address the problem of transferring the style of a headshot photo to face images.
Learning to Hallucinate Face Images via Component Generation and Enhancement
We propose a two-stage method for face hallucination.
DeshadowNet: A Multi-Context Embedding Deep Network for Shadow Removal
Two levels of features are derived from the global network and transferred to two parallel networks.
RGBD Salient Object Detection via Deep Fusion
Numerous efforts have been made to design different low level saliency cues for the RGBD saliency detection, such as color or depth contrast features, background and color compactness priors.
Ranked #25 on
RGB-D Salient Object Detection
on NJU2K
Exemplar-Driven Top-Down Saliency Detection via Deep Association
To address it, we design a two-stage deep model to learn the intra-class association between the exemplars and query objects.
Real-Time Salient Object Detection With a Minimum Spanning Tree
In this paper, we present a real-time salient object detection system based on the minimum spanning tree.
Ranked #5 on
Video Salient Object Detection
on MCL
(using extra training data)
Oriented Object Proposals
In this paper, we propose a new approach to generate oriented object proposals (OOPs) to reduce the detection error caused by various orientations of the object.
Visual Tracking via Locality Sensitive Histograms
A robust tracking framework based on the locality sensitive histograms is proposed, which consists of two main components: a new feature for tracking that is robust to illumination changes and a novel multi-region tracking algorithm that runs in realtime even with hundreds of regions.
