Search Results for author:
Found 27 papers, 9 papers with code
Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
In particular, we use a motion estimation network to capture motion information from neighborhoods, thereby adaptively estimating spatially-variant motion flow, mask, kernels, weights, and offsets to obtain the MISC Filter.
Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery
To counteract this inefficiency, we opt to cluster only the unlabelled instances and subsequently expand the cluster prototypes with our introduced potential prototypes to fast explore novel classes.
Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera
The pixel array of light-emitting diodes used for display diffracts and attenuates incident light, causing various degradations as the light intensity changes.
Dual Relation Alignment for Composed Image Retrieval
Unlike the general image-text retrieval problem with only one alignment relation, i. e., image-text, we argue for the existence of two types of relations in composed image retrieval.
Knowledge Transfer-Driven Few-Shot Class-Incremental Learning
Concretely, RESA mimics the real incremental setting and constructs pseudo incremental tasks globally and locally, where the global pseudo incremental tasks are designed to coincide with the learning objective of FSCIL and the local pseudo incremental tasks are designed to improve the model's plasticity, respectively.
Logic Diffusion for Knowledge Graph Reasoning
Most recent works focus on answering first order logical queries to explore the knowledge graph reasoning via multi-hop logic predictions.
Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution
Existing real-world video super-resolution (VSR) methods focus on designing a general degradation pipeline for open-domain videos while ignoring data intrinsic characteristics which strongly limit their performance when applying to some specific domains (eg., animation videos).
Space-time Prompting for Video Class-incremental Learning
In this paper, we will fill this gap by learning multiple prompts based on a powerful image-language pre-trained model, i. e., CLIP, making it fit for video class-incremental learning (VCIL).
FSI: Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras
In this paper, we introduce a new perspective to handle various diffraction in UDC images by jointly exploring the feature restoration in the frequency and spatial domains, and present a Frequency and Spatial Interactive Learning Network (FSI).
CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection
For better category-level feature alignment, we propose a novel DAOD framework of joint category and scale information, dubbed CSDA, such a design enables effective object learning for different scales.
Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning
The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, while the latter aims to compensate the lost spatio-temporal details in the Frame Condensing stage.
4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement
In particular, we first introduce a lightweight context encoder and a parameter encoder to learn a context map for the pixel-level category and a group of image-adaptive coefficients, respectively.
Ranked #7 on
Image Enhancement
on MIT-Adobe 5k
(SSIM on proRGB metric)
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation
In particular, we formulate the warped features with inconsistent motions as query tokens, and formulate relevant regions in a motion trajectory from two original consecutive frames into keys and values.
Learning Trajectory-Aware Transformer for Video Super-Resolution
Existing approaches usually align and aggregate video frames from limited adjacent frames (e. g., 5 or 7 frames), which prevents these approaches from satisfactory results.
Ranked #4 on
Video Super-Resolution
on UDM10 - 4x upscaling
Multi-Sample based Contrastive Loss for Top-k Recommendation
Therefore, we propose a Multi-Sample based Contrastive Loss (MSCL) function which solves the two problems by balancing the importance of positive and negative samples and data augmentation.
Generating Superpixels for High-resolution Images with Decoupled Patch Calibration
Superpixel segmentation has recently seen important progress benefiting from the advances in differentiable deep learning.
ReGO: Reference-Guided Outpainting for Scenery Image
We aim to tackle the challenging yet practical scenery image outpainting task in this work.
Diversity Regularized Interests Modeling for Recommender Systems
Each interest of the user should have a certain degree of distinction, thus we introduce three strategies as the diversity regularized separator to separate multiple user interest vectors.
AINet: Association Implantation for Superpixel Segmentation
However, simply applying a series of convolution operations with limited receptive fields can only implicitly perceive the relations between the pixel and its surrounding grids.
DONet: Dual Objective Networks for Skin Lesion Segmentation
Skin lesion segmentation is a crucial step in the computer-aided diagnosis of dermoscopic images.
Sketch-Guided Scenery Image Outpainting
In this work, we take the image outpainting one step forward by allowing users to harvest personal custom outpainting results using sketches as the guidance.
Crowd Scene Analysis by Output Encoding
In addition, proper receptive field sizes are crucial for crowd analysis due to human size variations.
Preparing Lessons: Improve Knowledge Distillation with Better Supervision
Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance.
Position Focused Attention Network for Image-Text Matching
Then, an attention mechanism is proposed to model the relations between the image region and blocks and generate the valuable position feature, which will be further utilized to enhance the region expression and model a more reliable relationship between the visual image and the textual sentence.
VrR-VG: Refocusing Visually-Relevant Relationships
Relationships encode the interactions among individual instances, and play a critical role in deep visual scene understanding.
GraphSeq2Seq: Graph-Sequence-to-Sequence for Neural Machine Translation
In this paper, we propose a Graph-Sequence-to-Sequence(GraphSeq2Seq) model to fuse the dependency graph among words into the traditional Seq2Seq framework.
Adaptive Co-weighting Deep Convolutional Features For Object Retrieval
Aggregating deep convolutional features into a global image vector has attracted sustained attention in image retrieval.
