Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks87 from public data
- GAN Prior Embedded Network for Blind Face Restoration in the Wild387
This work proposes a new method by first learning a GAN for high-quality face image generation and embedding it into a U-shaped DNN as a prior decoder, then fine-tuning the GAN prior embedded DNN with a set of synthesized low- quality face images.
- Attention-Aware Multi-Stroke Style Transfer198
This paper proposes to assemble self-attention mechanism into a style-agnostic reconstruction autoencoder framework, from which the attention map of a content image can be derived, and develops an attention-aware multi-stroke style transfer model.
- Diverse Image Inpainting with Bidirectional and Autoregressive Transformers182
BAT-Fill is proposed, an innovative image inpainting framework that introduces a novel bidirectional autoregressive transformer (BAT) for image inPainting that incorporates the masked language model like BERT, which enables bidirectionally modeling of contextual information of missing regions for better image completion.
- WaveFill: A Wavelet-based Generation Network for Image Inpainting146
WaveFill is presented, a wavelet-based inpainting network that decomposes images into multiple frequency bands and fills the missing regions in each frequency band separately and explicitly and effectively mitigate inter-frequency conflicts while completing images in spatial domain.
- FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation121
This paper presents FastInst, a simple, effective query-based framework for real-time instance segmentation, which follows the meta-architecture of recently introduced Mask2Former and outperforms most state-of-the-art real- time counterparts, including strong fully convolutional baselines, in both speed and accuracy.
- 113
- Hypergraph Transformer for Skeleton-based Action Recognition111
An underlying issue of graph models in general, i.e., pairwise aggregation essentially ignores the high-order kinematic dependencies between body joints is revealed, and a new self-attention mechanism on hypergraph is proposed, termed Hypergraph Self-Attention (HyperSA), to incorporate intrinsic higher-order relations into the model.
- Active Boundary Loss for Semantic Segmentation110
Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.
- DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders106
This work proposes DDColor, an end-to-end method with dual decoders for image colorization that establishes correlations between color and multi-scale semantic representations via cross-attention, significantly alleviating the color bleeding effect.
- Boosting Semantic Human Matting With Coarse Annotations102
This paper trains a mask prediction network to estimate the coarse semantic mask using the hybrid data, and proposes a quality unification network to unify the quality of the previous coarse mask outputs to boost end-to-end semantic human matting without trimaps as extra input.
- NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results94
The NTIRE 2022 challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images and the aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics.
- A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images91
A novel hierarchical representation network (HRN) is presented to achieve accurate and detailed face reconstruction from a single image and outperforms the existing methods in both reconstruction accuracy and visual effects.
- PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency89
The constructed PPR10K dataset provides a good bench-mark for studying automatic PPR methods, and experiments demonstrate that the proposed learning strategies are effective to improve the retouching performance.
- Improving Nighttime Driving-Scene Segmentation via Dual Image-Adaptive Learnable Filters88
DAIL-Filters can significantly improve the supervised segmentation performance on ACDC_Night and NightCity datasets, while it demonstrates the state-of-the-art performance on unsupervised nighttime semantic segmentation on Dark Zurich and Nighttime Driving testbeds.
- EMLight: Lighting Estimation via Spherical Distribution Approximation77
A novel spherical mover's loss is designed that guides to regress light distribution parameters accurately by taking advantage of the subtleties of spherical distribution and under the guidance of the predicted spherical distribution, light intensity and ambient term, the neural projector synthesizes panoramic illumination maps with realistic light frequency.
- Unbalanced Feature Transport for Exemplar-based Image Translation74
A general image translation framework that incorporates optimal transport for feature alignment between conditional inputs and style exemplars in image translation and a semantic-activation normalization scheme that injects style features of exemplars into the image translation process successfully is presented.
- 71
- Procontext: Exploring Progressive Context Transformer for Tracking64
This work revamped the tracking framework with Progressive Context Encoding Transformer Tracker (ProContEXT), which coherently exploits spatial and temporal contexts to predict object motion trajectories and raises a new pathway to multi-context modeling for transformer-based trackers.
- 63
- Attention-guided Temporally Coherent Video Object Matting48
A novel deep learning-based video object matting method that can achieve temporally coherent matting results by designing a novel loss term to train the attention weights, which drastically boosts the video matting performance.
- Noise-resistant Deep Metric Learning with Ranking-based Instance Selection45
A noise-resistant training technique for DML, which is named Probabilistic Ranking-based Instance Selection with Memory (PRISM), which identifies noisy data in a minibatch using average similarity against image features extracted by several previous versions of the neural network.
- Towards Counterfactual Image Manipulation via CLIP42
A novel contrastive loss is designed that exploits predefined CLIP-space directions to guide the editing toward desired directions from different perspectives and achieves accurate and realistic editing while driving by target texts with various counterfactual concepts.
- Tracking with Human-Intent Reasoning39
This work proposes a tracker called TrackGPT, which is capable of performing complex reasoning-based tracking, which uses LVLM to understand tracking instructions and condense the cues of what target to track into referring embeddings and generates the tracking results based on the embeddings.
- Adversarial Image Composition with Auxiliary Illumination37
An Adversarial Image Composition Net (AIC-Net) is proposed that achieves realistic image composition by considering potential shadows that the foreground object projects in the composed image.
- PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation33
The Multi-Hypothesis Pose Synthesis Domain Adaptation (PoSynDA) framework is presented, which simulates the 3D pose distribution in the target domain, filling the data diversity gap and paves the way for the practical application of 3D human pose estimation.
- 32
- 31
- Sparse Needlets for Lighting Estimation with Spherical Transport Loss27
NeedleLight is presented, a new lighting estimation model that represents illumination with needlets and allows lighting estimation in both frequency domain and spatial domain jointly and a new metric is proposed that is concise yet effective by directly evaluating the estimated illumination maps rather than rendered images.
- 27
- 24
- 24
- Longshortnet: Exploring Temporal and Semantic Features Fusion In Streaming Perception21
This work proposes LongShortNet, a novel dual-path network that captures long-term temporal motion and integrates it with short-term spatial semantics for real-time perception, enabling spatiotemporal feature fusion in streaming perception.
- 21
- 20
- 20
- 19
- 19
- Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness18
The investigation revealed strong variations in joint-to-joint relationships across different actions, exposing the limitations of a single adjacency matrix in capturing the variations of relational configurations emblematic of human movement, which is addressed by proposing an efficient refinement to Graph Convolutions - the BlockGC.
- 17
- 16
- 15
- 15
- 15
- 14
- 14
- 13
- 12
- 11
- 11
- 11
- 10
- MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis9
MetaDesigner introduces a transformative framework for artistic typography synthesis, powered by Large Language Models (LLMs) and grounded in a user-centric design paradigm, that dynamically adjusts hyperparameters to align with user-defined stylistic and thematic preferences.
- 9
- 8
- 7
- 7
- 7
- 6
- Generating Engaging Promotional Videos for E-commerce Platforms (Student Abstract)6
An algorithm called Shot Composition, Selection and Plotting (ShotCSP) is proposed, which generates visual storylines leveraging film-making principles to improve viewing experience and perceived persuasiveness.
- Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation5
The Refined Temporal Pyramidal Compression-and-Amplification (RTPCA) transformer is introduced, an approach that tackles a critical issue in current transformer-based methods: the underutilization of intra-and inter-block relations through attention mechanisms.
- KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration5
A groundbreaking facial landmark detection framework that stands out from existing methods, which utilizes a fully convolutional network to predict a distance map, which computes the distance between a Point of Interest (POI) and multiple anchor points.
- 5
- 4
- 4
- 4
- 4
- An AI-empowered Visual Storyline Generator4
Visual Storyline Generator is outlined, an artificial intelligence (AI)-empowered system that automatically generates visual storylines based on a set of images and video footages provided by the user, designed to produce engaging and persuasive promotional videos with an easy-to-use interface.
- 4
- 4
- 3
- WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope3
The challenge of simplifying artistic typography for non-professionals is addressed by offering a dynamic, adaptive, and computationally efficient alternative to traditional rigid templates by leveraging the power of LLMs to understand and interpret user input, facilitating a more intuitive design process.
- 3
- Personalized Video Summarization with Idiom Adaptation3
This paper presents a domain specific video summarization application with idiom adaptation that leverages multimedia content analysis and insights from cinematic and persuasive domains and validated the effectiveness of the demonstration on a TVC data-set with over 600 videos.
- DivAvatar: Diverse 3D Avatar Generation with a Single Prompt2
DivAvatar is a novel framework that generates diverse avatars, empowering 3D creatives with a multitude of distinct and richly varied 3D avatars from a single text prompt, and finetunes a 3D generative model (i.e., EVA3D), allowing diverse avatar generation from simply noise sampling in inference time.
- 2
- 2
- 2
- 2
- Domain Specific and Idiom Adaptive Video Summarization2
This work proposes a domain specific and idiom adaptive video summarization approach which first segments the input video and extracts high-level information from each segment, and uses max margin learning to identify the importance of the idioms and metrics in different domains.
- 1
- 1
- 1
- 1
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.