Search Results for author:
Found 95 papers, 33 papers with code
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
To further improve the performance of our unified model, we adopt two key strategies: (i) decoupling the understanding and generation encoders, and (ii) aligning their representations during unified training.
Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition
To this end, we introduce the idempotency constraint to form a stronger consistency regularization in the feature space, to push the features only to maintain the critical information of motion semantics for the recognition task.
MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion
For the first time, we leverage diffusion models as effective skeleton representation learners.
FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image Translation
To guide T2I generation with a reference image, we propose to decompose diverse guiding factors with different frequency bands of diffusion features in the DCT spectral space, and accordingly devise a novel frequency band substitution layer which realizes dynamic control of the reference image to the T2I generation result in a plug-and-play manner.
Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generation
Artistic text generation includes artistic text stylization and semantic typography.
Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition
To this end, considering the crucial role of the body parts in the spatially concentrated human actions, we attend to the mixing augmentations and propose a novel method, Shap-Mix, which improves long-tailed learning by mining representative motion patterns for tail categories.
Ranked #5 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Frequency-Controlled Diffusion Model for Versatile Text-Guided Image-to-Image Translation
At the heart of our framework is a feature-space frequency-domain filtering module based on Discrete Cosine Transform, which filters the latent features of the source image in the DCT domain, yielding filtered image features bearing different DCT spectral bands as different control signals to the pre-trained Latent Diffusion Model.
Coding for Intelligence from the Perspective of Category
This framework helps identify the challenges and essential elements in solving the specific derived Minimal Description Length (MDL) optimization problem from a broader range, providing opportunities to build a more intelligent system for handling multiple tasks/applications with coding ideas/tools.
Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond
Following the taxonomy of context-based, generative learning, and contrastive learning approaches, we make a thorough review and benchmark of existing works and shed light on the future possible directions.
Algorithmic Fairness: A Tolerance Perspective
Recent advancements in machine learning and deep learning have brought algorithmic fairness into sharp focus, illuminating concerns over discriminatory decision making that negatively impacts certain individuals or groups.
Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder
We build a diffusion model and design a novel paradigm that combines the diffusion model and an end-to-end decoder, and the latter is responsible for transmitting the privileged information extracted at the encoder side.
Zero-Reference Low-Light Enhancement via Physical Quadruple Priors
This prior serves as the bridge between normal and low-light images.
Diffusion Enhancement for Cloud Removal in Ultra-Resolution Remote Sensing Imagery
The presence of cloud layers severely compromises the quality and effectiveness of optical remote sensing (RS) images.
Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning
Moreover, combining these two paradigms in a naive manner leaves the synergy between them untapped and can lead to interference in training.
Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation
Low-light conditions not only hamper human visual experience but also degrade the model's performance on downstream vision tasks.
Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution
Diffusion models, as a kind of powerful generative model, have given impressive results on image super-resolution (SR) tasks.
Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation
Moreover, to fully unlock model capabilities for high-quality video generation and promote the development of the field, we curate a large-scale and open-source video dataset called HD-VG-130M.
Ranked #1 on
Text-to-Video Generation
on WebVid
Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition
However, these methods treat the motion and static parts equally, and lack an adaptive design for different parts, which has a negative impact on the accuracy of action recognition.
Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generation
Language-guided image generation has achieved great success nowadays by using diffusion models.
Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations
In this paper, we investigate the potential of adopting strong augmentations and propose a general hierarchical consistent contrastive learning framework (HiCLR) for skeleton-based action recognition.
Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation
Low light conditions not only degrade human visual experience, but also reduce the performance of downstream machine analytics.
AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation
To address this issue, we propose a Prompt-based Cross-Modal Generation Framework (PCM-Frame) to leverage two powerful pre-trained models, including CLIP and StyleGAN.
Learning Hierarchical Dynamics with Spatial Adjacency for Image Enhancement
In various real-world image enhancement applications, the degradations are always non-uniform or non-homogeneous and diverse, which challenges most deep networks with fixed parameters during the inference phase.
Ranked #16 on
Image Dehazing
on SOTS Indoor
Meta-Interpolation: Time-Arbitrary Frame Interpolation via Dual Meta-Learning
Extensive qualitative and quantitative evaluations, as well as ablation studies, demonstrate that, via introducing meta-learning in our framework in such a well-designed way, our method not only achieves superior performance to state-of-the-art frame interpolation approaches but also owns an extended capacity to support the interpolation at an arbitrary time-step.
S$^{5}$Mars: Semi-Supervised Learning for Mars Semantic Segmentation
We first present a newdataset S5Mars for Semi-SuperviSed learning on Mars Semantic Segmentation, which contains 6K high-resolution images and is sparsely annotated based on confidence, ensuring the high quality of labels.
Semi-Supervised Learning for Mars Imagery Classification and Segmentation
For segmentation, we extend supervised inter-class contrastive learning into an element-wise mode and use online pseudo labels for supervision on unlabeled areas.
Neural Data-Dependent Transform for Learned Image Compression
Learned image compression has achieved great success due to its excellent modeling capacity, but seldom further considers the Rate-Distortion Optimization (RDO) of each input image.
Web of Scholars: A Scholar Knowledge Graph
In this work, we demonstrate a novel system, namely Web of Scholars, which integrates state-of-the-art mining techniques to search, mine, and visualize complex networks behind scholars in the field of Computer Science.
Deep Graph Learning for Anomalous Citation Detection
To address this open issue, we propose a novel deep graph learning model, namely GLAD (Graph Learning for Anomaly Detection), to identify anomalies in citation networks.
Towards Low Light Enhancement with RAW Images
In this paper, we make the first benchmark effort to elaborate on the superiority of using RAW images in the low light enhancement and develop a novel alternative route to utilize RAW images in a more flexible and practical way.
Learning-Based Video Coding with Joint Deep Compression and Enhancement
Second, we reuse the DPEG network in both motion compensation and quality enhancement modules, which are further combined with other necessary modules to formulate our JCEVC framework.
Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics
By keeping in mind the transferability among different machine vision tasks (e. g. high-level semantic and mid-level geometry-related), we aim to support multiple tasks jointly at low bit rates.
SalienTrack: providing salient information for semi-automated self-tracking feedback with model explanations
Finally, we created interfaces to present salient information and conducted a formative user study to gain insights about how SalienTrack could be integrated into an interface for reflection.
Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective
Visual analytics have played an increasingly critical role in the Internet of Things, where massive visual signals have to be compressed and fed into machines.
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Sparse connectivity: there is no connection across channels, and each position is connected to the positions within a small local window.
HLA-Face: Joint High-Low Adaptation for Low Light Face Detection
To reduce the burden of building new datasets for low light conditions, we make full use of existing normal light data and explore how to adapt face detectors from normal light to low light.
Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos
In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics.
Progressive residual learning for single image dehazing
The recent physical model-free dehazing methods have achieved state-of-the-art performances.
Matching Algorithms: Fundamentals, Applications and Challenges
Based on the preference list access, matching problems are divided into two categories, i. e., explicit matching and implicit matching.
Information Retrieval
Recommendation Systems
Social and Information Networks
Progressive Depth Learning for Single Image Dehazing
However, we note that the guidance of the depth information for transmission estimation could remedy the decreased visibility as distances increase.
Template-Free Try-on Image Synthesis via Semantic-guided Optimization
Afterward, given an in-shop clothing image, a user image, and a synthesized pose, we propose a novel model for synthesizing a human try-on image with the target clothing in the best fitting pose.
MS$^2$L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition
To realize this goal, we integrate motion prediction, jigsaw puzzle recognition, and contrastive learning to learn skeleton features from different aspects.
Consistent Video Style Transfer via Relaxation and Regularization
In this article, we address the problem by jointly considering the intrinsic properties of stylization and temporal consistency.
Understanding the Advisor-advisee Relationship via Scholarly Data Analysis
Advisor-advisee relationship is important in academic networks due to its universality and necessity.
Shifu2: A Network Representation Learning Based Model for Advisor-advisee Relationship Mining
The advisor-advisee relationship represents direct knowledge heritage, and such relationship may not be readily available from academic libraries and search engines.
Random Walks: A Review of Algorithms and Applications
In this paper, we aim to provide a comprehensive review of classical random walks and quantum walks.
DINE: A Framework for Deep Incomplete Network Embedding
Empirically, we evaluate DINE over three networks on multi-label classification and link prediction tasks.
From Design Draft to Real Attire: Unaligned Fashion Image Translation
Moreover, built upon the sampling network, we present design draft to real fashion item translation network (D2RNet), where two separate translation streams that focus on texture and shape, respectively, are combined tactfully to get both benefits.
Recurrent Exposure Generation for Low-Light Face Detection
REG produces progressively and efficiently intermediate images corresponding to various exposure settings, and such pseudo-exposures are then fused by MED to detect faces across different lighting conditions.
Fashion Meets Computer Vision: A Survey
Fashion is the way we present ourselves to the world and has become one of the world's largest industries.
Learning End-to-End Lossy Image Compression: A Benchmark
In this paper, we first conduct a comprehensive literature survey of learned image compression methods.
Modality Compensation Network: Cross-Modal Adaptation for Action Recognition
In this work, we propose a Modality Compensation Network (MCN) to explore the relationships of different modalities, and boost the representations for human action recognition.
Combining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering
For (2), we extract both intra-frame and inter-frame side information for better context modeling.
Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics
Meanwhile, we systematically review state-of-the-art techniques in video compression and feature compression from the unique perspective of MPEG standardization, which provides the academic and industrial evidence to realize the collaborative compression of video and feature streams in a broad range of AI applications.
Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches
We present a sketch refinement strategy, as inspired by the coarse-to-fine drawing process of the artists, which we show can help our model well adapt to casual and varied sketches without the need for real sketch training data.
An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal
To this end, we make endeavors in leveraging the strength of predictive and generative models to support advanced compression techniques for both machine and human vision tasks simultaneously, in which visual features serve as a bridge to connect signal-level and task-level compact representations in a scalable manner.
Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach
In this paper, we come up with a novel image coding framework by leveraging both the compressive and the generative models, to support machine vision and human perception tasks jointly.
Single Image Deraining: From Model-Based to Data-Driven and Beyond
The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation.
Disentangled Image Matting
Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap.
A Comprehensive Benchmark for Single Image Compression Artifacts Reduction
We present a comprehensive study and evaluation of existing single image compression artifacts removal algorithms, using a new 4K resolution benchmark including diversified foreground objects and background scenes with rich structures, called Large-scale Ideal Ultra high definition 4K (LIU4K) benchmark.
Reprojection R-CNN: A Fast and Accurate Object Detector for 360° Images
Specifically, we adapt the terminologies of the traditional object detection task to the omnidirectional scenarios, and propose a novel two-stage object detector, i. e., Reprojection R-CNN by combining both ERP and perspective projection.
Deep Reference Generation with Multi-Domain Hierarchical Constraints for Inter Prediction
In this paper, we address the problem by proposing a deep frame interpolation network to generate additional reference frames in coding scenarios.
TE141K: Artistic Text Benchmark for Text Effect Transfer
To the best of our knowledge, this is the largest dataset for text effect transfer to date.
Controllable Artistic Text Style Transfer via Shape-Matching GAN
In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter.
UG$^{2+}$ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
The UG$^{2+}$ challenge in IEEE CVPR 2019 aims to evoke a comprehensive discussion and exploration about how low-level vision techniques can benefit the high-level automatic visual recognition in various scenarios.
Unsupervised Person Image Generation with Semantic Parsing Transformation
Firstly, a semantic generative network is proposed to transform between semantic parsing maps, in order to simplify the non-rigid deformation learning.
Bridging the Gap Between Computational Photography and Visual Recognition
From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area.
TET-GAN: Text Effects Transfer via Stylization and Destylization
The key idea is to train our network to accomplish both the objective of style transfer and style removal, so that it can learn to disentangle and recombine the content and style features of text effects images.
Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning
We consider spatial contexts, for which we solve so-called jigsaw puzzles, i. e., each image is cut into grids and then disordered, and the goal is to recover the correct configuration.
Optimized Skeleton-based Action Recognition via Sparsified Graph Regression
In this paper, we represent skeletons naturally on graphs, and propose a graph regression based GCN (GR-GCN) for skeleton-based action recognition, aiming to capture the spatio-temporal variation in the data.
Ranked #2 on
Skeleton Based Action Recognition
on Florence 3D
Generalized Coarse-to-Fine Visual Recognition with Progressive Training
Computer vision is difficult, partly because the desired mathematical function connecting input and output data is often complex, fuzzy and thus hard to learn.
Temporal Bilinear Networks for Video Action Recognition
Temporal modeling in videos is a fundamental yet challenging problem in computer vision.
Weakly Supervised Scene Parsing with Point-based Distance Metric Learning
Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected.
Context-Aware Text-Based Binary Image Stylization and Synthesis
The stylization is then followed by a context-aware layout design algorithm, where cues for both seamlessness and aesthetics are employed to determine the optimal layout of the shape in the background.
Deep Retinex Decomposition for Low-Light Enhancement
Based on the decomposition, subsequent lightness enhancement is conducted on illumination by an enhancement network called Enhance-Net, and for joint denoising there is a denoising operation on reflectance.
Progressive Spatial Recurrent Neural Network for Intra Prediction
With preceding pixels as the context, traditional intra prediction schemes generate linear predictions based on several predefined directions (i. e. modes) for blocks to be encoded.
A Group Variational Transformation Neural Network for Fractional Interpolation of Video Coding
Then a group variational transformation technique is used to transform a group of copied shared feature maps to samples at different sub-pixel positions.
Multimedia
DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal
JPEG is one of the most commonly used standards among lossy image compression methods.
Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos
In this paper, we address the problem of video rain removal by constructing deep recurrent convolutional networks.
Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration
In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels in one model.
Joint Enhancement and Denoising Method via Sequential Decomposition
Many low-light enhancement methods ignore intensive noise in original images.
Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
This injection of visual attention to both generative and discriminative networks is the main contribution of this paper.
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding
Despite the fact that many 3D human activity benchmarks being proposed, most existing action datasets focus on the action recognition tasks for the segmented videos.
Dual Recovery Network with Online Compensation for Image Super-Resolution
In particular, we infer the HF information based on both the LR image and similar HR references which are retrieved online.
Demystifying Neural Style Transfer
Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry.
Awesome Typography: Statistics-Based Text Effects Transfer
It allows our algorithm to produce artistic typography that fits for both local texture patterns and the global spatial distribution in the example.
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
In this work, we propose an end-to-end spatial and temporal attention model for human action recognition from skeleton data.
Ranked #114 on
Skeleton Based Action Recognition
on NTU RGB+D
Factorized Bilinear Models for Image Recognition
Although Deep Convolutional Neural Networks (CNNs) have liberated their power in various computer vision tasks, the most important components of CNN, convolutional layers and fully connected layers, are still limited to linear transformations.
Deep Joint Rain Detection and Removal from a Single Image
Based on the first model, we develop a multi-task deep learning architecture that learns the binary rain streak map, the appearance of rain streaks, and the clean background, which is our ultimate output.
Photo Stylistic Brush: Robust Style Transfer via Superpixel-Based Bipartite Graph
With the rapid development of social network and multimedia technology, customized image and video stylization has been widely used for various social-media applications.
MARLow: A Joint Multiplanar Autoregressive and Low-Rank Approach for Image Completion
In this paper, we propose a novel multiplanar autoregressive (AR) model to exploit the correlation in cross-dimensional planes of a similar patch group collected in an image, which has long been neglected by previous AR models.
Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution
To address this essentially ill-posed problem, we introduce a Deep Edge Guided REcurrent rEsidual~(DEGREE) network to progressively recover the high-frequency details.
Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks
In this paper, we study the problem of online action detection from streaming skeleton data.
Revisiting Batch Normalization For Practical Domain Adaptation
However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific domain.
